Image-Text-to-Text
MLX
Safetensors
English
inkling2_loop
mlx-vlm
inkling2
Mixture of Experts
quantized
gptq
apple-silicon
tool-calling
agents
conversational
8-bit precision
Instructions to use VisualInference/Inkling-2-Mini-MLX-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use VisualInference/Inkling-2-Mini-MLX-3bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("VisualInference/Inkling-2-Mini-MLX-3bit") config = load_config("VisualInference/Inkling-2-Mini-MLX-3bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use VisualInference/Inkling-2-Mini-MLX-3bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "VisualInference/Inkling-2-Mini-MLX-3bit"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "VisualInference/Inkling-2-Mini-MLX-3bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use VisualInference/Inkling-2-Mini-MLX-3bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "VisualInference/Inkling-2-Mini-MLX-3bit"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default VisualInference/Inkling-2-Mini-MLX-3bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use VisualInference/Inkling-2-Mini-MLX-3bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "VisualInference/Inkling-2-Mini-MLX-3bit"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "VisualInference/Inkling-2-Mini-MLX-3bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download model.safetensors.index.json from VisualInference/Inkling-2-Mini-MLX-3bit: direct link, hf CLI and curl.
- Browser
- Download file 182 kB
-
https://huggingface.co/VisualInference/Inkling-2-Mini-MLX-3bit/resolve/main/model.safetensors.index.json
- Command line
-
hf download hf://VisualInference/Inkling-2-Mini-MLX-3bit/model.safetensors.index.json
-
curl -L -o model.safetensors.index.json https://huggingface.co/VisualInference/Inkling-2-Mini-MLX-3bit/resolve/main/model.safetensors.index.json
182 kB
{
"metadata": {
"total_size": 12789021696
},
"weight_map": {
"language_model.lm_head.biases": "model-00003-of-00003.safetensors",
"language_model.lm_head.scales": "model-00003-of-00003.safetensors",
"language_model.lm_head.weight": "model-00003-of-00003.safetensors",
"language_model.model.embed_norm.weight": "model-00001-of-00003.safetensors",
"language_model.model.embed_tokens.biases": "model-00001-of-00003.safetensors",
"language_model.model.embed_tokens.scales": "model-00001-of-00003.safetensors",
"language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
"language_model.model.final_input.query": "model-00003-of-00003.safetensors",
"language_model.model.layers.0.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.attn.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.attn.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.attn.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.k.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.k.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.k.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.mlp.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.mlp.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.mlp.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.v.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.v.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.v.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.11.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.attn.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.attn.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.attn.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.k.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.k.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.k.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.mlp.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.mlp.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.mlp.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.v.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.v.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.controllers.v.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.k_input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.q_input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.k_sconv.static_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.k_sconv.weight_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.v_sconv.static_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.self_attn.v_sconv.weight_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.11.v_input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.attn.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.attn.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.attn.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.k.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.k.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.k.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.mlp.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.mlp.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.mlp.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.v.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.v.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.controllers.v.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.k_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.12.self_attn.v_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.attn.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.attn.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.attn.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.k.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.k.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.k.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.mlp.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.mlp.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.mlp.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.v.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.v.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.controllers.v.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.k_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.13.self_attn.v_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.attn.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.attn.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.attn.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.k.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.k.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.k.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.mlp.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.mlp.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.mlp.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.v.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.v.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.controllers.v.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.k_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.14.self_attn.v_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.attn.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.attn.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.attn.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.k.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.k.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.k.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.mlp.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.mlp.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.mlp.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.v.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.v.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.controllers.v.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.k_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.15.self_attn.v_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.attn.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.attn.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.attn.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.k.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.k.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.k.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.mlp.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.mlp.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.mlp.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.v.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.v.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.controllers.v.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.k_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.16.self_attn.v_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.attn.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.attn.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.attn.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.k.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.k.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.k.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.mlp.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.mlp.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.mlp.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.v.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.v.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.controllers.v.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.k_input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.q_input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.k_sconv.static_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.k_sconv.weight_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.v_sconv.static_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.self_attn.v_sconv.weight_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.17.v_input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.k_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.18.self_attn.v_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.k_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.19.self_attn.v_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.2.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.2.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.20.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.mlp_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.k_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.20.self_attn.v_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.attention_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.attn_sconv.conv.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.mlp.e_score_correction_bias": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.mlp.gate_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.mlp_input.query": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.mlp_sconv.conv.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.21.self_attn.gate_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.gate_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.gate_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.k_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.q_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.r_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.r_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.r_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.rel_proj": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.rel_scale": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.sink_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.21.self_attn.v_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.22.attention_input.query": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.attn_sconv.conv.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.e_score_correction_bias": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.gate_weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp_input.query": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.mlp_sconv.conv.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.gate_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.gate_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.k_sconv.conv.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.q_scale": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.r_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.r_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.r_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.rel_proj": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.rel_scale": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.sink_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.22.self_attn.v_sconv.conv.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.attention_input.query": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.attn_sconv.conv.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.k_input_layernorm.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.e_score_correction_bias": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.gate_weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp_input.query": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.mlp_sconv.conv.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.q_input_layernorm.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.gate_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.gate_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.gate_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.k_sconv.static_weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.k_sconv.weight_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.q_scale": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.r_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.r_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.r_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.rel_proj": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.rel_scale": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.sink_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.v_sconv.static_weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.self_attn.v_sconv.weight_proj.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.23.v_input_layernorm.weight": "model-00003-of-00003.safetensors",
"language_model.model.layers.3.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.3.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.4.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.k_input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.q_input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.k_sconv.static_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.k_sconv.weight_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.v_sconv.static_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.self_attn.v_sconv.weight_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.5.v_input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.attn.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.attn.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.attn.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.k.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.k.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.k.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.mlp.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.mlp.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.mlp.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.v.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.v.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.controllers.v.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.6.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.attn.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.attn.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.attn.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.k.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.k.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.k.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.mlp.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.mlp.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.mlp.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.v.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.v.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.controllers.v.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.7.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.attn.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.attn.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.attn.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.k.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.k.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.k.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.mlp.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.mlp.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.mlp.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.v.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.v.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.controllers.v.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.8.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.attn.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.attn.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.attn.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.k.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.k.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.k.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.mlp.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.mlp.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.mlp.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.v.down_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.v.forget_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.controllers.v.gain_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.9.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.message_queries": "model-00003-of-00003.safetensors",
"language_model.model.norm.weight": "model-00003-of-00003.safetensors",
"vision_tower.embeddings.class_embedding": "model-00003-of-00003.safetensors",
"vision_tower.embeddings.cls_position_embedding": "model-00003-of-00003.safetensors",
"vision_tower.embeddings.patch_embedding.weight": "model-00003-of-00003.safetensors",
"vision_tower.embeddings.position_embedding": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.lambda_1": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.lambda_2": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.layernorm_after.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.layernorm_after.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.layernorm_before.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.layernorm_before.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.mlp.fc1.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.mlp.fc1.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.mlp.fc1.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.mlp.fc1.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.mlp.fc2.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.mlp.fc2.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.mlp.fc2.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.mlp.fc2.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.out_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.out_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
"vision_tower.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"vision_tower.pre_layernorm.bias": "model-00003-of-00003.safetensors",
"vision_tower.pre_layernorm.weight": "model-00003-of-00003.safetensors",
"vision_tower.proj_in.biases": "model-00003-of-00003.safetensors",
"vision_tower.proj_in.scales": "model-00003-of-00003.safetensors",
"vision_tower.proj_in.weight": "model-00003-of-00003.safetensors",
"vision_tower.proj_out.biases": "model-00003-of-00003.safetensors",
"vision_tower.proj_out.scales": "model-00003-of-00003.safetensors",
"vision_tower.proj_out.weight": "model-00003-of-00003.safetensors"
}
}
{
"metadata": {
"total_size": 12789021696
},
"weight_map": {
"language_model.lm_head.biases": "model-00003-of-00003.safetensors",
"language_model.lm_head.scales": "model-00003-of-00003.safetensors",
"language_model.lm_head.weight": "model-00003-of-00003.safetensors",
"language_model.model.embed_norm.weight": "model-00001-of-00003.safetensors",
"language_model.model.embed_tokens.biases": "model-00001-of-00003.safetensors",
"language_model.model.embed_tokens.scales": "model-00001-of-00003.safetensors",
"language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
"language_model.model.final_input.query": "model-00003-of-00003.safetensors",
"language_model.model.layers.0.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.0.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.attn_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.e_score_correction_bias": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.gate_weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.mlp_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.gate_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.gate_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.gate_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.k_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.q_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.r_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.r_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.r_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.rel_proj": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.rel_scale": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.sink_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.1.self_attn.v_sconv.conv.weight": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.attention_input.query": "model-00001-of-00003.safetensors",
"language_model.model.layers.10.attn_sconv.conv.weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.attn.down_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.attn.forget_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.attn.gain_weight": "model-00002-of-00003.safetensors",
"language_model.model.layers.10.controllers.k.down_weight": "model-00002-of-00003.safetensors",