Instructions to use tiny-random/raon-1-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/raon-1-mini with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tiny-random/raon-1-mini", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tiny-random/raon-1-mini", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiny-random/raon-1-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/raon-1-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/raon-1-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiny-random/raon-1-mini

SGLang

How to use tiny-random/raon-1-mini with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tiny-random/raon-1-mini" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/raon-1-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tiny-random/raon-1-mini" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/raon-1-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/raon-1-mini with Docker Model Runner:
```
docker model run hf.co/tiny-random/raon-1-mini
```

yujiepan commited on 3 days ago

Commit

6466a4d

verified ·

1 Parent(s): 7869d31

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

README.md +9 -306
config.json +3 -20
model.safetensors +2 -2

README.md CHANGED Viewed

@@ -11,10 +11,10 @@ Structural comparison with `KRAFTON/Raon-1-mini-preview`:
 | Feature | Source | Tiny |
 |---|---:|---:|
 | Vocabulary / tied embeddings | 259,840 / untied | same |
-| Layers | 25 | same |
-| RDA / NoPE MLA layer cadence | 18 / 7 | same |
 | Raon mHC streams | 4 | same |
-| Dense prefix / MoE layers | layer 0 / 24 layers | same |
 | Routed experts / active experts | 128 / 6 | 64 / 6 |
 | Hidden width / attention head dimension | 2,560 / 128 | 32 / 32 |
 | RDA, MLA and LoRA dimensions | source widths | 32-wide compatible projections |
@@ -28,7 +28,7 @@ not implemented by PyTorch; it does not change the serialized precision.
 | File path | Size |
 |------|------|
-| model.safetensors | 40.3MB |
 ### Example usage:
@@ -70,13 +70,16 @@ folder = Path(save_folder)
 folder.mkdir(parents=True, exist_ok=True)
 raw = json.loads(Path(hf_hub_download(source_model_id, "config.json", revision=source_revision)).read_text())
 raw.update(
-    hidden_size=32, head_dim=32, num_attention_heads=1, intermediate_size=128,
     num_experts=64, num_experts_per_token=6, moe_intermediate_size=32,
     q_lora_rank=32, kv_lora_rank=32, qk_nope_head_dim=32,
     qk_rope_head_dim=32, v_head_dim=32, rda_decay_rank=32,
     max_position_embeddings=4096,
 )
-raw["rda_config"].update(num_heads=1, head_dim=32)
 # Build the public remote-code graph in BF16 first.  The source's MXFP8
 # modules cannot initialize random float8 parameters directly, then the
 # routed experts are converted back to the source's E4M3 + E8M0 format.
@@ -312,306 +315,6 @@ Raon1MiniForCausalLM(
           )
         )
       )
-      (8-10): 3 x Raon1MiniDecoderLayer(
-        (input_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (post_attention_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (self_attn): Raon1MiniRDA(
-          (q_proj): Linear(in_features=32, out_features=32, bias=False)
-          (k_proj): Linear(in_features=32, out_features=32, bias=False)
-          (v_proj): Linear(in_features=32, out_features=32, bias=False)
-          (q_conv1d): Raon1MiniShortConv()
-          (k_conv1d): Raon1MiniShortConv()
-          (v_conv1d): Raon1MiniShortConv()
-          (f_a_proj): Linear(in_features=32, out_features=32, bias=False)
-          (f_b_proj): Linear(in_features=32, out_features=32, bias=False)
-          (b_proj): Linear(in_features=32, out_features=1, bias=False)
-          (rda_w_proj): Linear(in_features=32, out_features=1, bias=False)
-          (g_proj): Linear(in_features=32, out_features=32, bias=False)
-          (o_norm): Raon1MiniRMSNorm((32,), eps=1e-05)
-          (o_proj): Linear(in_features=32, out_features=32, bias=False)
-        )
-        (self_attn_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (mlp_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (moe): Raon1MiniMoE(
-          (gate): Raon1MiniRouter()
-          (experts): ModuleList(
-            (0-63): 64 x Raon1MiniExpert(
-              (gate_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (up_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (down_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-            )
-          )
-          (shared_experts): Raon1MiniMLP(
-            (gate_proj): Linear(in_features=32, out_features=32, bias=False)
-            (up_proj): Linear(in_features=32, out_features=32, bias=False)
-            (down_proj): Linear(in_features=32, out_features=32, bias=False)
-          )
-        )
-      )
-      (11): Raon1MiniDecoderLayer(
-        (input_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (post_attention_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (self_attn): Raon1MiniMLA(
-          (q_a_proj): Linear(in_features=32, out_features=32, bias=False)
-          (q_a_layernorm): Raon1MiniRMSNorm((32,), eps=1e-06)
-          (q_b_proj): Linear(in_features=32, out_features=64, bias=False)
-          (kv_a_proj_with_mqa): Linear(in_features=32, out_features=64, bias=False)
-          (kv_a_layernorm): Raon1MiniRMSNorm((32,), eps=1e-06)
-          (kv_b_proj): Linear(in_features=32, out_features=64, bias=False)
-          (g_proj): Linear(in_features=32, out_features=32, bias=False)
-          (o_proj): Linear(in_features=32, out_features=32, bias=False)
-        )
-        (self_attn_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (mlp_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (moe): Raon1MiniMoE(
-          (gate): Raon1MiniRouter()
-          (experts): ModuleList(
-            (0-63): 64 x Raon1MiniExpert(
-              (gate_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (up_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (down_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-            )
-          )
-          (shared_experts): Raon1MiniMLP(
-            (gate_proj): Linear(in_features=32, out_features=32, bias=False)
-            (up_proj): Linear(in_features=32, out_features=32, bias=False)
-            (down_proj): Linear(in_features=32, out_features=32, bias=False)
-          )
-        )
-      )
-      (12-14): 3 x Raon1MiniDecoderLayer(
-        (input_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (post_attention_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (self_attn): Raon1MiniRDA(
-          (q_proj): Linear(in_features=32, out_features=32, bias=False)
-          (k_proj): Linear(in_features=32, out_features=32, bias=False)
-          (v_proj): Linear(in_features=32, out_features=32, bias=False)
-          (q_conv1d): Raon1MiniShortConv()
-          (k_conv1d): Raon1MiniShortConv()
-          (v_conv1d): Raon1MiniShortConv()
-          (f_a_proj): Linear(in_features=32, out_features=32, bias=False)
-          (f_b_proj): Linear(in_features=32, out_features=32, bias=False)
-          (b_proj): Linear(in_features=32, out_features=1, bias=False)
-          (rda_w_proj): Linear(in_features=32, out_features=1, bias=False)
-          (g_proj): Linear(in_features=32, out_features=32, bias=False)
-          (o_norm): Raon1MiniRMSNorm((32,), eps=1e-05)
-          (o_proj): Linear(in_features=32, out_features=32, bias=False)
-        )
-        (self_attn_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (mlp_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (moe): Raon1MiniMoE(
-          (gate): Raon1MiniRouter()
-          (experts): ModuleList(
-            (0-63): 64 x Raon1MiniExpert(
-              (gate_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (up_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (down_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-            )
-          )
-          (shared_experts): Raon1MiniMLP(
-            (gate_proj): Linear(in_features=32, out_features=32, bias=False)
-            (up_proj): Linear(in_features=32, out_features=32, bias=False)
-            (down_proj): Linear(in_features=32, out_features=32, bias=False)
-          )
-        )
-      )
-      (15): Raon1MiniDecoderLayer(
-        (input_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (post_attention_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (self_attn): Raon1MiniMLA(
-          (q_a_proj): Linear(in_features=32, out_features=32, bias=False)
-          (q_a_layernorm): Raon1MiniRMSNorm((32,), eps=1e-06)
-          (q_b_proj): Linear(in_features=32, out_features=64, bias=False)
-          (kv_a_proj_with_mqa): Linear(in_features=32, out_features=64, bias=False)
-          (kv_a_layernorm): Raon1MiniRMSNorm((32,), eps=1e-06)
-          (kv_b_proj): Linear(in_features=32, out_features=64, bias=False)
-          (g_proj): Linear(in_features=32, out_features=32, bias=False)
-          (o_proj): Linear(in_features=32, out_features=32, bias=False)
-        )
-        (self_attn_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (mlp_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (moe): Raon1MiniMoE(
-          (gate): Raon1MiniRouter()
-          (experts): ModuleList(
-            (0-63): 64 x Raon1MiniExpert(
-              (gate_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (up_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (down_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-            )
-          )
-          (shared_experts): Raon1MiniMLP(
-            (gate_proj): Linear(in_features=32, out_features=32, bias=False)
-            (up_proj): Linear(in_features=32, out_features=32, bias=False)
-            (down_proj): Linear(in_features=32, out_features=32, bias=False)
-          )
-        )
-      )
-      (16-18): 3 x Raon1MiniDecoderLayer(
-        (input_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (post_attention_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (self_attn): Raon1MiniRDA(
-          (q_proj): Linear(in_features=32, out_features=32, bias=False)
-          (k_proj): Linear(in_features=32, out_features=32, bias=False)
-          (v_proj): Linear(in_features=32, out_features=32, bias=False)
-          (q_conv1d): Raon1MiniShortConv()
-          (k_conv1d): Raon1MiniShortConv()
-          (v_conv1d): Raon1MiniShortConv()
-          (f_a_proj): Linear(in_features=32, out_features=32, bias=False)
-          (f_b_proj): Linear(in_features=32, out_features=32, bias=False)
-          (b_proj): Linear(in_features=32, out_features=1, bias=False)
-          (rda_w_proj): Linear(in_features=32, out_features=1, bias=False)
-          (g_proj): Linear(in_features=32, out_features=32, bias=False)
-          (o_norm): Raon1MiniRMSNorm((32,), eps=1e-05)
-          (o_proj): Linear(in_features=32, out_features=32, bias=False)
-        )
-        (self_attn_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (mlp_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (moe): Raon1MiniMoE(
-          (gate): Raon1MiniRouter()
-          (experts): ModuleList(
-            (0-63): 64 x Raon1MiniExpert(
-              (gate_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (up_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (down_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-            )
-          )
-          (shared_experts): Raon1MiniMLP(
-            (gate_proj): Linear(in_features=32, out_features=32, bias=False)
-            (up_proj): Linear(in_features=32, out_features=32, bias=False)
-            (down_proj): Linear(in_features=32, out_features=32, bias=False)
-          )
-        )
-      )
-      (19): Raon1MiniDecoderLayer(
-        (input_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (post_attention_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (self_attn): Raon1MiniMLA(
-          (q_a_proj): Linear(in_features=32, out_features=32, bias=False)
-          (q_a_layernorm): Raon1MiniRMSNorm((32,), eps=1e-06)
-          (q_b_proj): Linear(in_features=32, out_features=64, bias=False)
-          (kv_a_proj_with_mqa): Linear(in_features=32, out_features=64, bias=False)
-          (kv_a_layernorm): Raon1MiniRMSNorm((32,), eps=1e-06)
-          (kv_b_proj): Linear(in_features=32, out_features=64, bias=False)
-          (g_proj): Linear(in_features=32, out_features=32, bias=False)
-          (o_proj): Linear(in_features=32, out_features=32, bias=False)
-        )
-        (self_attn_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (mlp_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (moe): Raon1MiniMoE(
-          (gate): Raon1MiniRouter()
-          (experts): ModuleList(
-            (0-63): 64 x Raon1MiniExpert(
-              (gate_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (up_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (down_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-            )
-          )
-          (shared_experts): Raon1MiniMLP(
-            (gate_proj): Linear(in_features=32, out_features=32, bias=False)
-            (up_proj): Linear(in_features=32, out_features=32, bias=False)
-            (down_proj): Linear(in_features=32, out_features=32, bias=False)
-          )
-        )
-      )
-      (20-22): 3 x Raon1MiniDecoderLayer(
-        (input_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (post_attention_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (self_attn): Raon1MiniRDA(
-          (q_proj): Linear(in_features=32, out_features=32, bias=False)
-          (k_proj): Linear(in_features=32, out_features=32, bias=False)
-          (v_proj): Linear(in_features=32, out_features=32, bias=False)
-          (q_conv1d): Raon1MiniShortConv()
-          (k_conv1d): Raon1MiniShortConv()
-          (v_conv1d): Raon1MiniShortConv()
-          (f_a_proj): Linear(in_features=32, out_features=32, bias=False)
-          (f_b_proj): Linear(in_features=32, out_features=32, bias=False)
-          (b_proj): Linear(in_features=32, out_features=1, bias=False)
-          (rda_w_proj): Linear(in_features=32, out_features=1, bias=False)
-          (g_proj): Linear(in_features=32, out_features=32, bias=False)
-          (o_norm): Raon1MiniRMSNorm((32,), eps=1e-05)
-          (o_proj): Linear(in_features=32, out_features=32, bias=False)
-        )
-        (self_attn_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (mlp_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (moe): Raon1MiniMoE(
-          (gate): Raon1MiniRouter()
-          (experts): ModuleList(
-            (0-63): 64 x Raon1MiniExpert(
-              (gate_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (up_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (down_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-            )
-          )
-          (shared_experts): Raon1MiniMLP(
-            (gate_proj): Linear(in_features=32, out_features=32, bias=False)
-            (up_proj): Linear(in_features=32, out_features=32, bias=False)
-            (down_proj): Linear(in_features=32, out_features=32, bias=False)
-          )
-        )
-      )
-      (23-24): 2 x Raon1MiniDecoderLayer(
-        (input_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (post_attention_layernorm): Raon1MiniRMSNorm((32,), eps=1e-05)
-        (self_attn): Raon1MiniMLA(
-          (q_a_proj): Linear(in_features=32, out_features=32, bias=False)
-          (q_a_layernorm): Raon1MiniRMSNorm((32,), eps=1e-06)
-          (q_b_proj): Linear(in_features=32, out_features=64, bias=False)
-          (kv_a_proj_with_mqa): Linear(in_features=32, out_features=64, bias=False)
-          (kv_a_layernorm): Raon1MiniRMSNorm((32,), eps=1e-06)
-          (kv_b_proj): Linear(in_features=32, out_features=64, bias=False)
-          (g_proj): Linear(in_features=32, out_features=32, bias=False)
-          (o_proj): Linear(in_features=32, out_features=32, bias=False)
-        )
-        (self_attn_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (mlp_raon_mhc): RaonMHC(
-          (res): RaonMHCStreamMix()
-        )
-        (moe): Raon1MiniMoE(
-          (gate): Raon1MiniRouter()
-          (experts): ModuleList(
-            (0-63): 64 x Raon1MiniExpert(
-              (gate_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (up_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-              (down_proj): Raon1MiniRoutedLinear(in_features=32, out_features=32, bias=False)
-            )
-          )
-          (shared_experts): Raon1MiniMLP(
-            (gate_proj): Linear(in_features=32, out_features=32, bias=False)
-            (up_proj): Linear(in_features=32, out_features=32, bias=False)
-            (down_proj): Linear(in_features=32, out_features=32, bias=False)
-          )
-        )
-      )
     )
     (norm): Raon1MiniRMSNorm((32,), eps=1e-05)
   )

 | Feature | Source | Tiny |
 |---|---:|---:|
 | Vocabulary / tied embeddings | 259,840 / untied | same |
+| Layers | 25 | 8; two 3-RDA + 1-MLA cycles |
+| RDA / NoPE MLA layer cadence | 18 / 7 | 6 / 2 |
 | Raon mHC streams | 4 | same |
+| Dense prefix / MoE layers | layer 0 / 24 layers | layer 0 / 7 layers |
 | Routed experts / active experts | 128 / 6 | 64 / 6 |
 | Hidden width / attention head dimension | 2,560 / 128 | 32 / 32 |
 | RDA, MLA and LoRA dimensions | source widths | 32-wide compatible projections |
 | File path | Size |
 |------|------|
+| model.safetensors | 35.3MB |
 ### Example usage:
 folder.mkdir(parents=True, exist_ok=True)
 raw = json.loads(Path(hf_hub_download(source_model_id, "config.json", revision=source_revision)).read_text())
 raw.update(
+    hidden_size=32, head_dim=32, num_attention_heads=1, num_hidden_layers=8, intermediate_size=128,
     num_experts=64, num_experts_per_token=6, moe_intermediate_size=32,
     q_lora_rank=32, kv_lora_rank=32, qk_nope_head_dim=32,
     qk_rope_head_dim=32, v_head_dim=32, rda_decay_rank=32,
     max_position_embeddings=4096,
 )
+raw["rda_config"].update(
+    num_heads=1, head_dim=32,
+    rda_layers=[1, 2, 3, 5, 6, 7], mla_layers=[4, 8],
+)
 # Build the public remote-code graph in BF16 first.  The source's MXFP8
 # modules cannot initialize random float8 parameters directly, then the
 # routed experts are converted back to the source's E4M3 + E8M0 format.
           )
         )
       )
     )
     (norm): Raon1MiniRMSNorm((32,), eps=1e-05)
   )

config.json CHANGED Viewed

@@ -5,7 +5,7 @@
   "model_type": "raon1_mini",
   "dtype": "bfloat16",
   "hidden_size": 32,
-  "num_hidden_layers": 25,
   "num_attention_heads": 1,
   "head_dim": 32,
   "vocab_size": 259840,
@@ -42,12 +42,7 @@
     "gate_lower_bound": -5.0,
     "mla_layers": [
       4,
-      8,
-      12,
-      16,
-      20,
-      24,
-      25
     ],
     "rda_layers": [
       1,
@@ -55,19 +50,7 @@
       3,
       5,
       6,
-      7,
-      9,
-      10,
-      11,
-      13,
-      14,
-      15,
-      17,
-      18,
-      19,
-      21,
-      22,
-      23
     ]
   },
   "auto_map": {

   "model_type": "raon1_mini",
   "dtype": "bfloat16",
   "hidden_size": 32,
+  "num_hidden_layers": 8,
   "num_attention_heads": 1,
   "head_dim": 32,
   "vocab_size": 259840,
     "gate_lower_bound": -5.0,
     "mla_layers": [
       4,
+      8
     ],
     "rda_layers": [
       1,
       3,
       5,
       6,
+      7
     ]
   },
   "auto_map": {

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c328474bb170ac4328ce2f6c85561774a0bb1eb4ec98b6b5a57dcd1ee68421
-size 40263592

 version https://git-lfs.github.com/spec/v1
+oid sha256:2d95179de018937f323151c604da87fb9fdf9348799c48a922b767e5513319d0
+size 35338328