Instructions to use statelesshz/test_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use statelesshz/test_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="statelesshz/test_model")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("statelesshz/test_model", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use statelesshz/test_model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "statelesshz/test_model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "statelesshz/test_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/statelesshz/test_model
- SGLang
How to use statelesshz/test_model 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 "statelesshz/test_model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "statelesshz/test_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "statelesshz/test_model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "statelesshz/test_model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use statelesshz/test_model with Docker Model Runner:
docker model run hf.co/statelesshz/test_model
Update config.json
Browse files- config.json +1 -25
config.json
CHANGED
|
@@ -1,29 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
-
"auto_map": {
|
| 6 |
-
"AutoConfig": "configuration_baichuan.BaichuanConfig",
|
| 7 |
-
"AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM"
|
| 8 |
-
},
|
| 9 |
-
"tokenizer_class": "BaichuanTokenizer",
|
| 10 |
-
"bos_token_id": 1,
|
| 11 |
-
"eos_token_id": 2,
|
| 12 |
-
"hidden_act": "silu",
|
| 13 |
-
"hidden_size": 4096,
|
| 14 |
-
"initializer_range": 0.02,
|
| 15 |
-
"intermediate_size": 11008,
|
| 16 |
-
"max_position_embeddings": 4096,
|
| 17 |
-
"model_max_length": 4096,
|
| 18 |
-
"model_type": "baichuan",
|
| 19 |
-
"num_attention_heads": 32,
|
| 20 |
-
"num_hidden_layers": 32,
|
| 21 |
-
"pad_token_id": 0,
|
| 22 |
-
"rms_norm_eps": 1e-06,
|
| 23 |
-
"_from_model_config": true,
|
| 24 |
-
"tie_word_embeddings": false,
|
| 25 |
-
"torch_dtype": "bfloat16",
|
| 26 |
-
"transformers_version": "4.29.2",
|
| 27 |
-
"use_cache": true,
|
| 28 |
-
"vocab_size": 125696
|
| 29 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"ViTMSNModel"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|