Instructions to use mlx-community/flint-oQ4e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/flint-oQ4e with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/flint-oQ4e")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use mlx-community/flint-oQ4e with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/flint-oQ4e"

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": "mlx-community/flint-oQ4e"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use mlx-community/flint-oQ4e with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/flint-oQ4e"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/flint-oQ4e"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/flint-oQ4e",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use mlx-community/flint-oQ4e 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 "mlx-community/flint-oQ4e"

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 mlx-community/flint-oQ4e

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/flint-oQ4e with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/flint-oQ4e"

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 "mlx-community/flint-oQ4e" \
  --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"

flint-oQ4e / config.json

itsmechico

Add flint oQ4e (oMLX e2396c7)

a289427 verified 1 day ago

Raw History Blame Contribute Delete

93.9 kB

{
  "architectures": [
    "FlintForCausalLM"
  ],
  "model_type": "flint",
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 150000,
  "decoder_sparse_step": 1,
  "eos_token_id": [
    150001,
    150003,
    150005,
    150018
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 6144,
  "layer_types": [
    "full_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "max_position_embeddings": 262144,
  "mlp_only_layers": [
    0,
    1
  ],
  "moe_intermediate_size": 512,
  "norm_topk_prob": true,
  "num_attention_heads": 32,
  "num_experts": 256,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 49,
  "num_key_value_heads": 4,
  "no_rope_layer_indices": [
    0,
    1,
    5,
    9,
    13,
    17,
    21,
    25,
    29,
    33,
    37,
    41,
    45,
    48
  ],
  "output_router_logits": false,
  "pad_token_id": 150001,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "router_aux_loss_coef": 0.0005,
  "router_score_function": "sigmoid",
  "shared_expert_intermediate_size": 1024,
  "sliding_window": 513,
  "softmax_type": "learnable",
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "use_cache": true,
  "use_sliding_window": true,
  "vocab_size": 150144,
  "transformers_version": "5.12.1",
  "quantization": {
    "group_size": 64,
    "bits": 4,
    "mode": "affine",
    "language_model.model.layers.5.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.12.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.12.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.23.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.12.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.13.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.13.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.13.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.14.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.14.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.14.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.15.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.15.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.15.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.16.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.16.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.24.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.24.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.24.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.25.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.25.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.25.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.26.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.26.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.26.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.27.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.27.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.27.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.27.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.27.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.3.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.3.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.3.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.30.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.30.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.30.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.31.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.31.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.31.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.32.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.32.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.32.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.33.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.33.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.33.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.34.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.34.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.34.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.35.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.35.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.35.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.36.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.36.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.36.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.37.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.37.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.37.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.38.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.38.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.38.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.39.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.39.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.39.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.4.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.4.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.4.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.40.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.40.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.40.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.41.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.41.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.41.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.42.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.42.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.42.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.43.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.43.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.43.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.44.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.44.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.44.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.45.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.45.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.45.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.46.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.46.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.46.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.47.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.47.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.47.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.48.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.48.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.48.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.5.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.5.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.5.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.6.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.6.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.6.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.6.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.6.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.6.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.7.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.7.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.7.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.8.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.8.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.8.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.9.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.9.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.9.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.embed_tokens": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.16.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.17.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.17.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.27.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.28.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.28.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.28.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.28.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.28.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.28.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.29.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.29.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.29.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.7.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.7.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.7.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.8.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.8.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.8.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.lm_head": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.down_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.up_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.mlp.down_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.mlp.up_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.10.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.10.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.10.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.10.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.10.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.10.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.10.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.11.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.11.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.11.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.11.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.11.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.11.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.11.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.12.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.12.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.12.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.12.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.13.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.13.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.13.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.13.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.14.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.14.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.14.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.14.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.15.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.15.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.15.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.15.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.16.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.16.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.16.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.16.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.17.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.17.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.17.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.17.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.17.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.18.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.18.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.18.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.18.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.18.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.18.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.18.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.19.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.19.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.19.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.19.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.19.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.19.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.19.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.2.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.2.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.2.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.2.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.2.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.2.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.2.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.20.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.20.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.20.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.20.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.20.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.20.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.20.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.21.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.21.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.21.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.21.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.21.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.21.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.21.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.22.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.22.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.22.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.22.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.22.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.22.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.22.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.23.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.23.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.23.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.23.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.23.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.23.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.25.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.25.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.25.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.25.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.26.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.26.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.26.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.26.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.27.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.28.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.29.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.29.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.29.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.29.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.3.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.3.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.3.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.3.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.30.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.30.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.30.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.30.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.31.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.31.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.31.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.31.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.32.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.32.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.32.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.32.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.33.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.33.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.33.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.33.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.34.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.34.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.34.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.34.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.35.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.35.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.35.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.35.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.36.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.36.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.36.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.36.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.37.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.37.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.37.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.37.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.38.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.38.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.38.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.38.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.39.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.39.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.39.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.39.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.4.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.4.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.4.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.4.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.40.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.40.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.40.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.40.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.41.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.41.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.41.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.41.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.42.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.42.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.42.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.42.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.43.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.43.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.43.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.43.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.44.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.44.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.44.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.44.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.45.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.45.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.45.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.45.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.46.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.46.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.46.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.46.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.47.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.47.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.47.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.47.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.48.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.48.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.48.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.48.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.5.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.5.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.5.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.6.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.7.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.8.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.9.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.9.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.9.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.9.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    }
  },
  "quantization_config": {
    "group_size": 64,
    "bits": 4,
    "mode": "affine",
    "language_model.model.layers.5.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.12.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.12.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.23.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.12.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.13.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.13.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.13.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.14.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.14.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.14.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.15.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.15.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.15.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.16.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.16.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.24.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.24.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.24.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.25.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.25.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.25.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.26.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.26.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.26.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.27.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.27.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.27.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.27.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.27.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.3.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.3.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.3.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.30.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.30.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.30.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.31.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.31.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.31.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.32.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.32.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.32.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.33.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.33.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.33.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.34.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.34.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.34.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.35.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.35.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.35.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.36.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.36.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.36.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.37.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.37.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.37.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.38.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.38.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.38.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.39.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.39.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.39.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.4.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.4.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.4.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.40.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.40.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.40.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.41.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.41.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.41.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.42.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.42.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.42.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.43.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.43.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.43.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.44.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.44.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.44.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.45.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.45.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.45.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.46.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.46.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.46.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.47.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.47.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.47.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.48.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.48.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.48.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.5.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.5.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.5.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.6.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.6.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.6.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.6.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.6.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.6.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.7.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.7.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.7.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.8.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.8.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.8.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.9.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.9.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.9.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.embed_tokens": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.16.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.17.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.17.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.27.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.28.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.28.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.28.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.28.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.28.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.28.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.29.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.29.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.29.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.7.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.7.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.7.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.8.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.8.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.8.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.lm_head": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.down_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.up_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.mlp.down_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.mlp.up_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.1.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.10.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.10.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.10.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.10.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.10.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.10.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.10.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.11.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.11.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.11.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.11.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.11.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.11.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.11.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.12.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.12.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.12.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.12.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.13.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.13.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.13.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.13.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.14.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.14.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.14.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.14.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.15.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.15.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.15.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.15.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.16.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.16.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.16.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.16.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.17.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.17.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.17.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.17.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.17.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.18.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.18.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.18.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.18.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.18.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.18.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.18.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.19.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.19.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.19.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.19.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.19.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.19.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.19.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.2.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.2.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.2.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.2.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.2.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.2.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.2.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.20.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.20.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.20.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.20.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.20.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.20.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.20.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.21.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.21.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.21.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.21.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.21.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.21.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.21.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.22.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.22.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.22.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.22.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.22.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.22.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.22.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.23.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.23.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.23.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.23.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.23.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.23.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.25.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.25.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.25.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.25.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.26.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.26.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.26.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.26.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.27.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.28.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.29.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.29.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.29.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.29.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.3.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.3.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.3.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.3.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.30.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.30.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.30.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.30.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.31.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.31.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.31.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.31.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.32.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.32.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.32.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.32.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.33.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.33.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.33.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.33.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.34.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.34.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.34.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.34.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.35.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.35.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.35.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.35.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.36.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.36.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.36.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.36.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.37.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.37.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.37.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.37.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.38.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.38.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.38.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.38.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.39.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.39.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.39.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.39.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.4.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.4.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.4.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.4.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.40.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.40.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.40.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.40.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.41.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.41.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.41.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.41.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.42.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.42.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.42.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.42.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.43.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.43.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.43.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.43.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.44.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.44.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.44.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.44.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.45.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.45.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.45.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.45.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.46.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.46.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.46.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.46.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.47.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.47.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.47.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.47.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.48.mlp.shared_expert.down_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.48.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.48.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.48.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.5.mlp.shared_expert.gate_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.5.mlp.shared_expert.up_proj": {
      "bits": 8,
      "group_size": 128,
      "mode": "affine"
    },
    "language_model.model.layers.5.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.6.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.7.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.8.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.9.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.9.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.9.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.9.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    }
  }
}