Instructions to use pavelslab-nyu/Chess-SFT-Models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pavelslab-nyu/Chess-SFT-Models with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="pavelslab-nyu/Chess-SFT-Models")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("pavelslab-nyu/Chess-SFT-Models", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use pavelslab-nyu/Chess-SFT-Models with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "pavelslab-nyu/Chess-SFT-Models" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pavelslab-nyu/Chess-SFT-Models", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/pavelslab-nyu/Chess-SFT-Models
- SGLang
How to use pavelslab-nyu/Chess-SFT-Models 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 "pavelslab-nyu/Chess-SFT-Models" \ --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": "pavelslab-nyu/Chess-SFT-Models", "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 "pavelslab-nyu/Chess-SFT-Models" \ --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": "pavelslab-nyu/Chess-SFT-Models", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use pavelslab-nyu/Chess-SFT-Models with Docker Model Runner:
docker model run hf.co/pavelslab-nyu/Chess-SFT-Models
model_50m_2.3B model card
Browse files- model_50m_2.3B/README.md +0 -3
model_50m_2.3B/README.md
CHANGED
|
@@ -15,9 +15,6 @@ SFT (**thinking**) chess model from the compute-allocation study.
|
|
| 15 |
| property | value |
|
| 16 |
|---|---|
|
| 17 |
| base size | 50m |
|
| 18 |
-
| total compute C | 6.5e+18 FLOPs |
|
| 19 |
-
| α (pretrain fraction) | 0.1 |
|
| 20 |
-
| β (SFT fraction) | 0.023 |
|
| 21 |
| **pretraining tokens** | **2.3B** (2,295,571,127) |
|
| 22 |
|
| 23 |
## Evaluation (multi-turn chess benchmark, test_B0 family)
|
|
|
|
| 15 |
| property | value |
|
| 16 |
|---|---|
|
| 17 |
| base size | 50m |
|
|
|
|
|
|
|
|
|
|
| 18 |
| **pretraining tokens** | **2.3B** (2,295,571,127) |
|
| 19 |
|
| 20 |
## Evaluation (multi-turn chess benchmark, test_B0 family)
|