Instructions to use jelegend/GLM-5.2-FP8-Finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jelegend/GLM-5.2-FP8-Finetuned with Transformers:

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

pipe = pipeline("text-generation", model="jelegend/GLM-5.2-FP8-Finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jelegend/GLM-5.2-FP8-Finetuned")
model = AutoModelForCausalLM.from_pretrained("jelegend/GLM-5.2-FP8-Finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jelegend/GLM-5.2-FP8-Finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jelegend/GLM-5.2-FP8-Finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jelegend/GLM-5.2-FP8-Finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jelegend/GLM-5.2-FP8-Finetuned

SGLang

How to use jelegend/GLM-5.2-FP8-Finetuned 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 "jelegend/GLM-5.2-FP8-Finetuned" \
    --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": "jelegend/GLM-5.2-FP8-Finetuned",
		"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 "jelegend/GLM-5.2-FP8-Finetuned" \
        --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": "jelegend/GLM-5.2-FP8-Finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jelegend/GLM-5.2-FP8-Finetuned with Docker Model Runner:
```
docker model run hf.co/jelegend/GLM-5.2-FP8-Finetuned
```

jelegend commited on 5 days ago

Commit

092ba9e

verified ·

1 Parent(s): 8f232d6

Upload config.json

Browse files

Files changed (1) hide show

config.json +859 -0

config.json ADDED Viewed

	@@ -0,0 +1,859 @@

+{
+  "architectures": [
+    "GlmMoeDsaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "index_head_dim": 128,
+  "index_n_heads": 32,
+  "index_share_for_mtp_iteration": true,
+  "index_skip_topk_offset": 3,
+  "index_topk": 2048,
+  "index_topk_freq": 4,
+  "index_topk_pattern": null,
+  "indexer_rope_interleave": true,
+  "indexer_types": [
+    "full",
+    "full",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared"
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "kv_lora_rank": 512,
+  "layer_types": [
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention",
+    "deepseek_sparse_attention"
+  ],
+  "max_position_embeddings": 1048576,
+  "mlp_bias": false,
+  "mlp_layer_types": [
+    "dense",
+    "dense",
+    "dense",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse"
+  ],
+  "model_type": "glm_moe_dsa",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts": 256,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 78,
+  "num_key_value_heads": 64,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 154820,
+  "pretraining_tp": 1,
+  "q_lora_rank": 2048,
+  "qk_head_dim": 256,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "dequantize": false,
+    "modules_to_not_convert": [
+      "model.layers.59.post_attention_layernorm",
+      "model.layers.47.mlp.gate.e_score_correction_bias",
+      "model.layers.71.self_attn.kv_a_layernorm",
+      "model.layers.46.mlp.gate.e_score_correction_bias",
+      "model.layers.30.self_attn.kv_a_layernorm",
+      "model.layers.23.self_attn.kv_a_layernorm",
+      "model.layers.73.mlp.gate.e_score_correction_bias",
+      "model.layers.36.mlp.gate",
+      "model.layers.12.self_attn.q_a_layernorm",
+      "model.layers.51.mlp.gate",
+      "model.layers.47.self_attn.kv_a_layernorm",
+      "model.layers.45.self_attn.q_a_layernorm",
+      "model.layers.15.self_attn.q_a_layernorm",
+      "model.layers.39.input_layernorm",
+      "model.layers.50.self_attn.kv_a_layernorm",
+      "model.layers.19.post_attention_layernorm",
+      "model.layers.71.input_layernorm",
+      "model.layers.72.self_attn.kv_a_layernorm",
+      "model.layers.70.mlp.gate",
+      "model.layers.52.input_layernorm",
+      "model.layers.78.self_attn.kv_a_layernorm",
+      "model.layers.48.post_attention_layernorm",
+      "model.layers.4.self_attn.q_a_layernorm",
+      "model.layers.62.self_attn.q_a_layernorm",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.38.self_attn.indexers_proj",
+      "model.layers.61.mlp.gate.e_score_correction_bias",
+      "model.layers.14.mlp.gate.e_score_correction_bias",
+      "model.layers.36.self_attn.kv_a_layernorm",
+      "model.layers.65.mlp.gate",
+      "model.layers.13.self_attn.kv_a_layernorm",
+      "model.layers.57.mlp.gate",
+      "model.layers.65.self_attn.kv_a_layernorm",
+      "model.layers.68.input_layernorm",
+      "model.layers.70.self_attn.kv_a_layernorm",
+      "model.layers.24.mlp.gate.e_score_correction_bias",
+      "model.layers.4.input_layernorm",
+      "model.layers.20.input_layernorm",
+      "model.layers.65.self_attn.q_a_layernorm",
+      "model.layers.38.mlp.gate",
+      "model.layers.76.mlp.gate.e_score_correction_bias",
+      "model.layers.62.input_layernorm",
+      "model.layers.45.input_layernorm",
+      "model.layers.68.post_attention_layernorm",
+      "model.layers.72.input_layernorm",
+      "model.layers.32.mlp.gate.e_score_correction_bias",
+      "model.layers.27.input_layernorm",
+      "model.layers.16.post_attention_layernorm",
+      "model.layers.35.self_attn.q_a_layernorm",
+      "model.layers.58.self_attn.indexers_proj",
+      "model.layers.3.mlp.gate.e_score_correction_bias",
+      "model.layers.49.self_attn.q_a_layernorm",
+      "model.layers.66.mlp.gate.e_score_correction_bias",
+      "model.layers.10.self_attn.q_a_layernorm",
+      "model.layers.51.mlp.gate.e_score_correction_bias",
+      "model.layers.64.self_attn.q_a_layernorm",
+      "model.layers.70.input_layernorm",
+      "model.layers.71.post_attention_layernorm",
+      "model.layers.67.post_attention_layernorm",
+      "model.layers.6.self_attn.indexer.k_norm",
+      "model.layers.3.mlp.gate",
+      "model.layers.11.mlp.gate",
+      "model.layers.17.input_layernorm",
+      "model.layers.13.mlp.gate",
+      "model.layers.15.mlp.gate",
+      "model.layers.71.self_attn.q_a_layernorm",
+      "model.layers.33.mlp.gate.e_score_correction_bias",
+      "model.layers.72.mlp.gate.e_score_correction_bias",
+      "model.layers.65.post_attention_layernorm",
+      "model.layers.78.hnorm",
+      "model.layers.40.post_attention_layernorm",
+      "model.layers.12.mlp.gate.e_score_correction_bias",
+      "model.layers.8.input_layernorm",
+      "model.layers.73.mlp.gate",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.61.input_layernorm",
+      "model.layers.14.self_attn.kv_a_layernorm",
+      "model.layers.39.self_attn.kv_a_layernorm",
+      "model.layers.70.self_attn.indexer.k_norm",
+      "model.layers.45.mlp.gate",
+      "model.layers.51.self_attn.q_a_layernorm",
+      "model.layers.64.post_attention_layernorm",
+      "model.layers.20.post_attention_layernorm",
+      "model.layers.66.self_attn.kv_a_layernorm",
+      "model.layers.10.self_attn.indexer.k_norm.bias",
+      "model.layers.23.input_layernorm",
+      "model.layers.38.self_attn.indexer.k_norm",
+      "model.layers.19.self_attn.kv_a_layernorm",
+      "model.layers.40.self_attn.q_a_layernorm",
+      "model.layers.10.self_attn.indexer.k_norm",
+      "model.layers.44.post_attention_layernorm",
+      "model.layers.70.post_attention_layernorm",
+      "model.layers.41.mlp.gate.e_score_correction_bias",
+      "model.layers.36.post_attention_layernorm",
+      "model.layers.30.self_attn.indexer.k_norm.bias",
+      "model.layers.54.self_attn.q_a_layernorm",
+      "model.layers.59.mlp.gate",
+      "model.layers.69.post_attention_layernorm",
+      "lm_head",
+      "model.layers.77.self_attn.kv_a_layernorm",
+      "model.layers.75.self_attn.q_a_layernorm",
+      "model.layers.56.self_attn.q_a_layernorm",
+      "model.layers.50.self_attn.indexer.k_norm.bias",
+      "model.layers.54.mlp.gate",
+      "model.layers.6.self_attn.indexer.k_norm.bias",
+      "model.layers.15.input_layernorm",
+      "model.layers.29.self_attn.q_a_layernorm",
+      "model.layers.54.self_attn.indexers_proj",
+      "model.layers.73.self_attn.kv_a_layernorm",
+      "model.layers.0.self_attn.indexer.k_norm",
+      "model.layers.58.self_attn.indexer.k_norm",
+      "model.layers.36.input_layernorm",
+      "model.layers.47.self_attn.q_a_layernorm",
+      "model.layers.26.mlp.gate.e_score_correction_bias",
+      "model.layers.50.input_layernorm",
+      "model.layers.16.self_attn.q_a_layernorm",
+      "model.layers.19.mlp.gate.e_score_correction_bias",
+      "model.layers.78.input_layernorm",
+      "model.layers.27.mlp.gate",
+      "model.layers.19.self_attn.q_a_layernorm",
+      "model.layers.25.input_layernorm",
+      "model.layers.33.self_attn.kv_a_layernorm",
+      "model.layers.32.mlp.gate",
+      "model.layers.61.self_attn.kv_a_layernorm",
+      "model.layers.50.self_attn.indexers_proj",
+      "model.layers.34.self_attn.indexers_proj",
+      "model.layers.4.mlp.gate.e_score_correction_bias",
+      "model.layers.76.post_attention_layernorm",
+      "model.layers.57.post_attention_layernorm",
+      "model.layers.73.post_attention_layernorm",
+      "model.layers.68.mlp.gate.e_score_correction_bias",
+      "model.layers.34.self_attn.kv_a_layernorm",
+      "model.layers.78.enorm",
+      "model.layers.30.mlp.gate",
+      "model.layers.10.self_attn.indexers_proj",
+      "model.layers.34.input_layernorm",
+      "model.layers.34.post_attention_layernorm",
+      "model.layers.20.mlp.gate.e_score_correction_bias",
+      "model.layers.54.self_attn.indexer.k_norm.bias",
+      "model.layers.44.mlp.gate",
+      "model.layers.25.mlp.gate.e_score_correction_bias",
+      "model.layers.26.self_attn.indexers_proj",
+      "model.layers.66.self_attn.indexer.k_norm.bias",
+      "model.layers.41.post_attention_layernorm",
+      "model.layers.51.post_attention_layernorm",
+      "model.layers.22.self_attn.indexer.k_norm.bias",
+      "model.layers.21.mlp.gate.e_score_correction_bias",
+      "model.layers.15.self_attn.kv_a_layernorm",
+      "model.layers.25.self_attn.kv_a_layernorm",
+      "model.layers.55.mlp.gate",
+      "model.layers.11.self_attn.q_a_layernorm",
+      "model.layers.72.mlp.gate",
+      "model.layers.21.self_attn.kv_a_layernorm",
+      "model.layers.59.mlp.gate.e_score_correction_bias",
+      "model.layers.2.input_layernorm",
+      "model.layers.5.mlp.gate",
+      "model.layers.54.self_attn.kv_a_layernorm",
+      "model.layers.0.self_attn.indexers_proj",
+      "model.layers.71.mlp.gate.e_score_correction_bias",
+      "model.layers.6.self_attn.q_a_layernorm",
+      "model.layers.14.mlp.gate",
+      "model.layers.44.self_attn.kv_a_layernorm",
+      "model.layers.61.post_attention_layernorm",
+      "model.layers.64.self_attn.kv_a_layernorm",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.4.mlp.gate",
+      "model.layers.22.post_attention_layernorm",
+      "model.layers.21.self_attn.q_a_layernorm",
+      "model.layers.74.self_attn.q_a_layernorm",
+      "model.layers.18.self_attn.indexers_proj",
+      "model.layers.75.input_layernorm",
+      "model.layers.70.self_attn.q_a_layernorm",
+      "model.layers.22.self_attn.indexer.k_norm",
+      "model.layers.42.mlp.gate.e_score_correction_bias",
+      "model.layers.5.self_attn.kv_a_layernorm",
+      "model.layers.31.mlp.gate.e_score_correction_bias",
+      "model.layers.62.self_attn.indexer.k_norm.bias",
+      "model.layers.29.post_attention_layernorm",
+      "model.layers.6.self_attn.kv_a_layernorm",
+      "model.layers.48.input_layernorm",
+      "model.layers.74.self_attn.indexer.k_norm.bias",
+      "model.layers.7.input_layernorm",
+      "model.layers.39.self_attn.q_a_layernorm",
+      "model.layers.41.input_layernorm",
+      "model.layers.54.self_attn.indexer.k_norm",
+      "model.layers.32.self_attn.q_a_layernorm",
+      "model.layers.39.mlp.gate.e_score_correction_bias",
+      "model.layers.42.input_layernorm",
+      "model.layers.43.mlp.gate",
+      "model.layers.72.self_attn.q_a_layernorm",
+      "model.layers.37.mlp.gate.e_score_correction_bias",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.28.mlp.gate",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.49.post_attention_layernorm",
+      "model.layers.43.self_attn.kv_a_layernorm",
+      "model.layers.12.input_layernorm",
+      "model.layers.56.mlp.gate",
+      "model.layers.5.input_layernorm",
+      "model.layers.29.mlp.gate.e_score_correction_bias",
+      "model.layers.4.self_attn.kv_a_layernorm",
+      "model.layers.20.self_attn.q_a_layernorm",
+      "model.layers.59.self_attn.q_a_layernorm",
+      "model.layers.68.mlp.gate",
+      "model.layers.21.post_attention_layernorm",
+      "model.layers.26.self_attn.q_a_layernorm",
+      "model.layers.52.self_attn.q_a_layernorm",
+      "model.layers.29.self_attn.kv_a_layernorm",
+      "model.layers.24.input_layernorm",
+      "model.layers.34.self_attn.indexer.k_norm.bias",
+      "model.layers.43.input_layernorm",
+      "model.layers.27.self_attn.kv_a_layernorm",
+      "model.layers.31.input_layernorm",
+      "model.layers.69.mlp.gate",
+      "model.layers.26.post_attention_layernorm",
+      "model.layers.3.self_attn.q_a_layernorm",
+      "model.layers.37.post_attention_layernorm",
+      "model.layers.52.mlp.gate",
+      "model.layers.73.input_layernorm",
+      "model.layers.19.input_layernorm",
+      "model.layers.13.self_attn.q_a_layernorm",
+      "model.layers.76.input_layernorm",
+      "model.layers.8.mlp.gate",
+      "model.layers.63.post_attention_layernorm",
+      "model.layers.58.mlp.gate",
+      "model.layers.31.post_attention_layernorm",
+      "model.layers.23.mlp.gate.e_score_correction_bias",
+      "model.layers.34.self_attn.q_a_layernorm",
+      "model.layers.78.self_attn.indexer.k_norm.bias",
+      "model.layers.13.mlp.gate.e_score_correction_bias",
+      "model.layers.71.mlp.gate",
+      "model.layers.14.input_layernorm",
+      "model.layers.17.mlp.gate.e_score_correction_bias",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.45.self_attn.kv_a_layernorm",
+      "model.layers.46.self_attn.indexer.k_norm",
+      "model.layers.20.self_attn.kv_a_layernorm",
+      "model.layers.78.self_attn.indexer.k_norm",
+      "model.layers.37.mlp.gate",
+      "model.layers.7.mlp.gate",
+      "model.layers.30.mlp.gate.e_score_correction_bias",
+      "model.layers.67.mlp.gate",
+      "model.layers.73.self_attn.q_a_layernorm",
+      "model.layers.10.self_attn.kv_a_layernorm",
+      "model.layers.61.mlp.gate",
+      "model.layers.22.mlp.gate.e_score_correction_bias",
+      "model.layers.58.input_layernorm",
+      "model.layers.8.self_attn.kv_a_layernorm",
+      "model.layers.33.self_attn.q_a_layernorm",
+      "model.layers.55.self_attn.q_a_layernorm",
+      "model.layers.32.input_layernorm",
+      "model.layers.17.self_attn.kv_a_layernorm",
+      "model.layers.46.self_attn.indexer.k_norm.bias",
+      "model.layers.11.mlp.gate.e_score_correction_bias",
+      "model.layers.9.input_layernorm",
+      "model.layers.77.input_layernorm",
+      "model.layers.16.self_attn.kv_a_layernorm",
+      "model.layers.45.post_attention_layernorm",
+      "model.layers.74.mlp.gate",
+      "model.layers.68.self_attn.q_a_layernorm",
+      "model.layers.55.self_attn.kv_a_layernorm",
+      "model.layers.44.input_layernorm",
+      "model.layers.60.self_attn.kv_a_layernorm",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.62.self_attn.indexers_proj",
+      "model.layers.0.self_attn.q_a_layernorm",
+      "model.layers.72.post_attention_layernorm",
+      "model.layers.78.post_attention_layernorm",
+      "model.layers.60.mlp.gate.e_score_correction_bias",
+      "model.layers.26.self_attn.indexer.k_norm.bias",
+      "model.layers.38.post_attention_layernorm",
+      "model.layers.50.post_attention_layernorm",
+      "model.layers.28.input_layernorm",
+      "model.layers.30.self_attn.indexer.k_norm",
+      "model.layers.37.self_attn.q_a_layernorm",
+      "model.layers.56.input_layernorm",
+      "model.layers.27.post_attention_layernorm",
+      "model.layers.74.input_layernorm",
+      "model.layers.78.self_attn.q_a_layernorm",
+      "model.layers.42.self_attn.q_a_layernorm",
+      "model.layers.26.self_attn.indexer.k_norm",
+      "model.layers.42.self_attn.kv_a_layernorm",
+      "model.layers.1.self_attn.indexer.k_norm",
+      "model.layers.39.post_attention_layernorm",
+      "model.layers.48.mlp.gate.e_score_correction_bias",
+      "model.layers.74.post_attention_layernorm",
+      "model.layers.69.self_attn.q_a_layernorm",
+      "model.layers.13.input_layernorm",
+      "model.layers.74.self_attn.indexer.k_norm",
+      "model.layers.29.mlp.gate",
+      "model.layers.7.mlp.gate.e_score_correction_bias",
+      "model.layers.3.self_attn.kv_a_layernorm",
+      "model.layers.35.self_attn.kv_a_layernorm",
+      "model.layers.46.self_attn.indexers_proj",
+      "model.layers.0.self_attn.kv_a_layernorm",
+      "model.layers.43.self_attn.q_a_layernorm",
+      "model.norm",
+      "model.layers.1.self_attn.kv_a_layernorm",
+      "model.layers.38.self_attn.indexer.k_norm.bias",
+      "model.layers.30.self_attn.q_a_layernorm",
+      "model.layers.0.input_layernorm",
+      "model.layers.47.input_layernorm",
+      "model.layers.8.self_attn.q_a_layernorm",
+      "model.layers.61.self_attn.q_a_layernorm",
+      "model.layers.1.self_attn.indexer.k_norm.bias",
+      "model.layers.62.mlp.gate.e_score_correction_bias",
+      "model.layers.66.self_attn.q_a_layernorm",
+      "model.layers.46.self_attn.kv_a_layernorm",
+      "model.layers.66.mlp.gate",
+      "model.layers.69.input_layernorm",
+      "model.layers.69.self_attn.kv_a_layernorm",
+      "model.layers.22.input_layernorm",
+      "model.layers.30.post_attention_layernorm",
+      "model.layers.24.self_attn.q_a_layernorm",
+      "model.layers.48.mlp.gate",
+      "model.layers.7.self_attn.kv_a_layernorm",
+      "model.layers.67.input_layernorm",
+      "model.layers.27.self_attn.q_a_layernorm",
+      "model.layers.23.mlp.gate",
+      "model.layers.45.mlp.gate.e_score_correction_bias",
+      "model.layers.76.self_attn.kv_a_layernorm",
+      "model.layers.22.self_attn.q_a_layernorm",
+      "model.layers.78.mlp.gate",
+      "model.layers.9.mlp.gate",
+      "model.layers.57.self_attn.q_a_layernorm",
+      "model.layers.78.mlp.gate.e_score_correction_bias",
+      "model.layers.23.post_attention_layernorm",
+      "model.layers.38.self_attn.q_a_layernorm",
+      "model.layers.53.mlp.gate",
+      "model.layers.77.self_attn.q_a_layernorm",
+      "model.layers.62.self_attn.kv_a_layernorm",
+      "model.layers.12.mlp.gate",
+      "model.layers.34.self_attn.indexer.k_norm",
+      "model.layers.46.self_attn.q_a_layernorm",
+      "model.layers.36.self_attn.q_a_layernorm",
+      "model.layers.58.self_attn.indexer.k_norm.bias",
+      "model.layers.60.post_attention_layernorm",
+      "model.layers.28.post_attention_layernorm",
+      "model.layers.2.self_attn.kv_a_layernorm",
+      "model.layers.70.self_attn.indexers_proj",
+      "model.layers.16.mlp.gate.e_score_correction_bias",
+      "model.layers.2.self_attn.indexer.k_norm",
+      "model.layers.31.self_attn.kv_a_layernorm",
+      "model.layers.64.input_layernorm",
+      "model.layers.6.mlp.gate.e_score_correction_bias",
+      "model.layers.50.self_attn.indexer.k_norm",
+      "model.layers.58.self_attn.q_a_layernorm",
+      "model.layers.57.mlp.gate.e_score_correction_bias",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.28.self_attn.kv_a_layernorm",
+      "model.layers.31.self_attn.q_a_layernorm",
+      "model.layers.1.self_attn.q_a_layernorm",
+      "model.layers.17.mlp.gate",
+      "model.layers.15.post_attention_layernorm",
+      "model.layers.18.self_attn.indexer.k_norm.bias",
+      "model.layers.18.self_attn.indexer.k_norm",
+      "model.layers.43.mlp.gate.e_score_correction_bias",
+      "model.layers.11.input_layernorm",
+      "model.layers.9.post_attention_layernorm",
+      "model.layers.33.input_layernorm",
+      "model.layers.66.input_layernorm",
+      "model.layers.78.self_attn.indexers_proj",
+      "model.layers.54.post_attention_layernorm",
+      "model.layers.53.mlp.gate.e_score_correction_bias",
+      "model.layers.5.mlp.gate.e_score_correction_bias",
+      "model.layers.19.mlp.gate",
+      "model.layers.49.mlp.gate",
+      "model.layers.66.self_attn.indexers_proj",
+      "model.layers.14.self_attn.indexer.k_norm.bias",
+      "model.layers.41.mlp.gate",
+      "model.layers.42.self_attn.indexer.k_norm.bias",
+      "model.layers.65.input_layernorm",
+      "model.layers.75.mlp.gate",
+      "model.layers.12.self_attn.kv_a_layernorm",
+      "model.layers.53.input_layernorm",
+      "model.layers.58.self_attn.kv_a_layernorm",
+      "model.layers.60.self_attn.q_a_layernorm",
+      "model.layers.6.mlp.gate",
+      "model.layers.49.self_attn.kv_a_layernorm",
+      "model.layers.16.mlp.gate",
+      "model.layers.22.mlp.gate",
+      "model.layers.58.post_attention_layernorm",
+      "model.layers.15.mlp.gate.e_score_correction_bias",
+      "model.layers.26.input_layernorm",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.6.input_layernorm",
+      "model.layers.22.self_attn.kv_a_layernorm",
+      "model.layers.16.input_layernorm",
+      "model.layers.33.post_attention_layernorm",
+      "model.layers.17.post_attention_layernorm",
+      "model.layers.35.mlp.gate",
+      "model.layers.56.post_attention_layernorm",
+      "model.layers.7.self_attn.q_a_layernorm",
+      "model.layers.24.mlp.gate",
+      "model.layers.24.post_attention_layernorm",
+      "model.layers.36.mlp.gate.e_score_correction_bias",
+      "model.layers.56.mlp.gate.e_score_correction_bias",
+      "model.layers.32.post_attention_layernorm",
+      "model.layers.47.post_attention_layernorm",
+      "model.layers.40.mlp.gate",
+      "model.layers.41.self_attn.kv_a_layernorm",
+      "model.layers.52.self_attn.kv_a_layernorm",
+      "model.layers.9.self_attn.kv_a_layernorm",
+      "model.layers.77.mlp.gate.e_score_correction_bias",
+      "model.layers.78.shared_head.norm",
+      "model.layers.53.post_attention_layernorm",
+      "model.layers.63.self_attn.kv_a_layernorm",
+      "model.layers.48.self_attn.kv_a_layernorm",
+      "model.layers.28.mlp.gate.e_score_correction_bias",
+      "model.layers.8.mlp.gate.e_score_correction_bias",
+      "model.layers.52.mlp.gate.e_score_correction_bias",
+      "model.layers.52.post_attention_layernorm",
+      "model.layers.18.self_attn.q_a_layernorm",
+      "model.layers.50.mlp.gate.e_score_correction_bias",
+      "model.layers.64.mlp.gate.e_score_correction_bias",
+      "model.layers.38.mlp.gate.e_score_correction_bias",
+      "model.layers.59.input_layernorm",
+      "model.layers.21.input_layernorm",
+      "model.layers.39.mlp.gate",
+      "model.layers.77.post_attention_layernorm",
+      "model.layers.76.self_attn.q_a_layernorm",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.43.post_attention_layernorm",
+      "model.layers.35.input_layernorm",
+      "model.layers.62.mlp.gate",
+      "model.layers.38.self_attn.kv_a_layernorm",
+      "model.layers.63.mlp.gate",
+      "model.layers.27.mlp.gate.e_score_correction_bias",
+      "model.layers.18.mlp.gate",
+      "model.layers.25.post_attention_layernorm",
+      "model.layers.55.mlp.gate.e_score_correction_bias",
+      "model.layers.66.self_attn.indexer.k_norm",
+      "model.layers.48.self_attn.q_a_layernorm",
+      "model.layers.78.eh_proj",
+      "model.layers.77.mlp.gate",
+      "model.layers.6.self_attn.indexers_proj",
+      "model.layers.14.self_attn.q_a_layernorm",
+      "model.layers.2.self_attn.q_a_layernorm",
+      "model.layers.42.mlp.gate",
+      "model.layers.54.mlp.gate.e_score_correction_bias",
+      "model.layers.60.input_layernorm",
+      "model.layers.40.self_attn.kv_a_layernorm",
+      "model.layers.51.self_attn.kv_a_layernorm",
+      "model.layers.18.input_layernorm",
+      "model.layers.30.self_attn.indexers_proj",
+      "model.layers.53.self_attn.kv_a_layernorm",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.70.self_attn.indexer.k_norm.bias",
+      "model.layers.54.input_layernorm",
+      "model.layers.41.self_attn.q_a_layernorm",
+      "model.layers.18.mlp.gate.e_score_correction_bias",
+      "model.layers.34.mlp.gate.e_score_correction_bias",
+      "model.layers.47.mlp.gate",
+      "model.layers.46.mlp.gate",
+      "model.layers.25.self_attn.q_a_layernorm",
+      "model.layers.63.mlp.gate.e_score_correction_bias",
+      "model.layers.66.post_attention_layernorm",
+      "model.layers.76.mlp.gate",
+      "model.embed_tokens",
+      "model.layers.67.self_attn.kv_a_layernorm",
+      "model.layers.67.mlp.gate.e_score_correction_bias",
+      "model.layers.26.self_attn.kv_a_layernorm",
+      "model.layers.31.mlp.gate",
+      "model.layers.18.self_attn.kv_a_layernorm",
+      "model.layers.34.mlp.gate",
+      "model.layers.55.post_attention_layernorm",
+      "model.layers.30.input_layernorm",
+      "model.layers.50.mlp.gate",
+      "model.layers.63.input_layernorm",
+      "model.layers.11.self_attn.kv_a_layernorm",
+      "model.layers.24.self_attn.kv_a_layernorm",
+      "model.layers.75.mlp.gate.e_score_correction_bias",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.1.self_attn.indexers_proj",
+      "model.layers.42.self_attn.indexers_proj",
+      "model.layers.46.input_layernorm",
+      "model.layers.23.self_attn.q_a_layernorm",
+      "model.layers.63.self_attn.q_a_layernorm",
+      "model.layers.14.self_attn.indexer.k_norm",
+      "model.layers.14.self_attn.indexers_proj",
+      "model.layers.60.mlp.gate",
+      "model.layers.70.mlp.gate.e_score_correction_bias",
+      "model.layers.53.self_attn.q_a_layernorm",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.35.mlp.gate.e_score_correction_bias",
+      "model.layers.75.self_attn.kv_a_layernorm",
+      "model.layers.1.input_layernorm",
+      "model.layers.42.post_attention_layernorm",
+      "model.layers.37.input_layernorm",
+      "model.layers.9.mlp.gate.e_score_correction_bias",
+      "model.layers.46.post_attention_layernorm",
+      "model.layers.26.mlp.gate",
+      "model.layers.65.mlp.gate.e_score_correction_bias",
+      "model.layers.67.self_attn.q_a_layernorm",
+      "model.layers.44.mlp.gate.e_score_correction_bias",
+      "model.layers.33.mlp.gate",
+      "model.layers.29.input_layernorm",
+      "model.layers.18.post_attention_layernorm",
+      "model.layers.75.post_attention_layernorm",
+      "model.layers.44.self_attn.q_a_layernorm",
+      "model.layers.10.mlp.gate",
+      "model.layers.21.mlp.gate",
+      "model.layers.58.mlp.gate.e_score_correction_bias",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.50.self_attn.q_a_layernorm",
+      "model.layers.9.self_attn.q_a_layernorm",
+      "model.layers.2.self_attn.indexers_proj",
+      "model.layers.0.self_attn.indexer.k_norm.bias",
+      "model.layers.74.self_attn.kv_a_layernorm",
+      "model.layers.74.mlp.gate.e_score_correction_bias",
+      "model.layers.49.mlp.gate.e_score_correction_bias",
+      "model.layers.62.post_attention_layernorm",
+      "model.layers.57.self_attn.kv_a_layernorm",
+      "model.layers.40.input_layernorm",
+      "model.layers.69.mlp.gate.e_score_correction_bias",
+      "model.layers.35.post_attention_layernorm",
+      "model.layers.74.self_attn.indexers_proj",
+      "model.layers.55.input_layernorm",
+      "model.layers.49.input_layernorm",
+      "model.layers.40.mlp.gate.e_score_correction_bias",
+      "model.layers.25.mlp.gate",
+      "model.layers.2.self_attn.indexer.k_norm.bias",
+      "model.layers.68.self_attn.kv_a_layernorm",
+      "model.layers.51.input_layernorm",
+      "model.layers.22.self_attn.indexers_proj",
+      "model.layers.10.input_layernorm",
+      "model.layers.42.self_attn.indexer.k_norm",
+      "model.layers.56.self_attn.kv_a_layernorm",
+      "model.layers.17.self_attn.q_a_layernorm",
+      "model.layers.59.self_attn.kv_a_layernorm",
+      "model.layers.3.input_layernorm",
+      "model.layers.57.input_layernorm",
+      "model.layers.38.input_layernorm",
+      "model.layers.62.self_attn.indexer.k_norm",
+      "model.layers.20.mlp.gate",
+      "model.layers.64.mlp.gate",
+      "model.layers.28.self_attn.q_a_layernorm",
+      "model.layers.32.self_attn.kv_a_layernorm",
+      "model.layers.10.mlp.gate.e_score_correction_bias",
+      "model.layers.5.self_attn.q_a_layernorm",
+      "model.layers.37.self_attn.kv_a_layernorm"
+    ],
+    "quant_method": "fp8",
+    "scale_fmt": "float",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "rope_theta": 8000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.13.0.dev0",
+  "use_cache": true,
+  "v_head_dim": 256,
+  "vocab_size": 154880
+}