Instructions to use tencent/Hunyuan-A13B-Instruct-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/Hunyuan-A13B-Instruct-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="tencent/Hunyuan-A13B-Instruct-FP8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tencent/Hunyuan-A13B-Instruct-FP8", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tencent/Hunyuan-A13B-Instruct-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/Hunyuan-A13B-Instruct-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/Hunyuan-A13B-Instruct-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent/Hunyuan-A13B-Instruct-FP8

SGLang

How to use tencent/Hunyuan-A13B-Instruct-FP8 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 "tencent/Hunyuan-A13B-Instruct-FP8" \
    --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": "tencent/Hunyuan-A13B-Instruct-FP8",
		"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 "tencent/Hunyuan-A13B-Instruct-FP8" \
        --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": "tencent/Hunyuan-A13B-Instruct-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent/Hunyuan-A13B-Instruct-FP8 with Docker Model Runner:
```
docker model run hf.co/tencent/Hunyuan-A13B-Instruct-FP8
```

manaestras commited on Jun 26, 2025

Commit

4a43c81

verified ·

1 Parent(s): e05ca5e

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +4 -5

config.json CHANGED Viewed

@@ -1,19 +1,18 @@
 {
-  "_name_or_path": "/apdcephfs_gy2/share_302508627/darrenhu/llm/model/open_A13B/7b_moe_t1_v53_long_context_stage_daxianwang_fix_renshe_hf",
   "add_classification_head": false,
   "anyres_pooling_size": 2,
   "anyres_vit_max_image_size": null,
   "anyres_vit_two_views": false,
   "architectures": [
-    "HunYuanForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.1,
   "attention_head_dim": 128,
   "auto_map": {
     "AutoConfig": "configuration_hunyuan.HunYuanConfig",
-    "AutoModel": "hunyuan.HunyuanModel",
-    "AutoModelForCausalLM": "hunyuan.HunYuanForCausalLM"
   },
   "bos_token_id": 1,
   "cla_share_factor": 2,
@@ -187,7 +186,7 @@
   "topk_group": null,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": false,
   "use_cla": false,
   "use_mixed_mlp_moe": true,
   "use_mla": false,

 {
   "add_classification_head": false,
   "anyres_pooling_size": 2,
   "anyres_vit_max_image_size": null,
   "anyres_vit_two_views": false,
   "architectures": [
+    "HunYuanMoEV1ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.1,
   "attention_head_dim": 128,
   "auto_map": {
     "AutoConfig": "configuration_hunyuan.HunYuanConfig",
+    "AutoModel": "hunyuan.HunYuanModel",
+    "AutoModelForCausalLM": "hunyuan.HunYuanMoEV1ForCausalLM"
   },
   "bos_token_id": 1,
   "cla_share_factor": 2,
   "topk_group": null,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
+  "use_cache": true,
   "use_cla": false,
   "use_mixed_mlp_moe": true,
   "use_mla": false,