Text Generation
Transformers
Safetensors
llama
chess
ChessLlama
chess-engines
text-generation-inference
Instructions to use Q-bert/ChessLlama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Q-bert/ChessLlama with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Q-bert/ChessLlama", device_map="auto")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Q-bert/ChessLlama") model = AutoModelForCausalLM.from_pretrained("Q-bert/ChessLlama", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Q-bert/ChessLlama with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Q-bert/ChessLlama" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Q-bert/ChessLlama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Q-bert/ChessLlama
- SGLang
How to use Q-bert/ChessLlama 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 "Q-bert/ChessLlama" \ --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": "Q-bert/ChessLlama", "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 "Q-bert/ChessLlama" \ --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": "Q-bert/ChessLlama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Q-bert/ChessLlama with Docker Model Runner:
docker model run hf.co/Q-bert/ChessLlama
Update README.md
Browse files
README.md
CHANGED
|
@@ -40,14 +40,19 @@ This notebook is created to test the model's capabilities. You can use it to eva
|
|
| 40 |
|
| 41 |
You can use this model or dataset to train your own models as well, and challenge me in this new field.
|
| 42 |
|
| 43 |
-
#
|
| 44 |
|
| 45 |
### Training Data
|
| 46 |
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
[More Information Needed]
|
| 50 |
|
| 51 |
### Training Procedure
|
| 52 |
|
| 53 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
You can use this model or dataset to train your own models as well, and challenge me in this new field.
|
| 42 |
|
| 43 |
+
# Training Details
|
| 44 |
|
| 45 |
### Training Data
|
| 46 |
|
| 47 |
+
[Q-bert/Elite-Chess-Games](https://huggingface.co/datasets/Q-bert/Elite-Chess-Games)
|
|
|
|
|
|
|
| 48 |
|
| 49 |
### Training Procedure
|
| 50 |
|
| 51 |
+
This model was fully trained from scratch with random weights. It was created from the ground up with a new configuration and model, and trained using the Hugging Face Trainer for 1200 steps. There is still potential for further training. You can see the training code below.
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
**Training Loss Graph:**
|
| 55 |
+

|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
|