Instructions to use Tony068/wiki-10M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Tony068/wiki-10M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Tony068/wiki-10M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Tony068/wiki-10M") model = AutoModelForCausalLM.from_pretrained("Tony068/wiki-10M") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Tony068/wiki-10M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Tony068/wiki-10M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Tony068/wiki-10M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Tony068/wiki-10M
- SGLang
How to use Tony068/wiki-10M 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 "Tony068/wiki-10M" \ --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": "Tony068/wiki-10M", "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 "Tony068/wiki-10M" \ --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": "Tony068/wiki-10M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Tony068/wiki-10M with Docker Model Runner:
docker model run hf.co/Tony068/wiki-10M
Update config.json
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -12,8 +12,8 @@
|
|
| 12 |
"model_type": "gpt2",
|
| 13 |
"n_ctx": 1024,
|
| 14 |
"n_embd": 768,
|
| 15 |
-
"n_head":
|
| 16 |
-
"n_layer":
|
| 17 |
"n_positions": 1024,
|
| 18 |
"resid_pdrop": 0.1,
|
| 19 |
"summary_activation": null,
|
|
@@ -27,5 +27,5 @@
|
|
| 27 |
"max_length": 50
|
| 28 |
}
|
| 29 |
},
|
| 30 |
-
"vocab_size":
|
| 31 |
}
|
|
|
|
| 12 |
"model_type": "gpt2",
|
| 13 |
"n_ctx": 1024,
|
| 14 |
"n_embd": 768,
|
| 15 |
+
"n_head": 8,
|
| 16 |
+
"n_layer": 4,
|
| 17 |
"n_positions": 1024,
|
| 18 |
"resid_pdrop": 0.1,
|
| 19 |
"summary_activation": null,
|
|
|
|
| 27 |
"max_length": 50
|
| 28 |
}
|
| 29 |
},
|
| 30 |
+
"vocab_size": 2266
|
| 31 |
}
|