Text Generation
Transformers
Safetensors
text generation
Deci AI
DeciCoder
custom_code
Eval Results (legacy)
Instructions to use Deci/DeciCoder-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Deci/DeciCoder-1b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Deci/DeciCoder-1b", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Deci/DeciCoder-1b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Deci/DeciCoder-1b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Deci/DeciCoder-1b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Deci/DeciCoder-1b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Deci/DeciCoder-1b
- SGLang
How to use Deci/DeciCoder-1b 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 "Deci/DeciCoder-1b" \ --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": "Deci/DeciCoder-1b", "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 "Deci/DeciCoder-1b" \ --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": "Deci/DeciCoder-1b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Deci/DeciCoder-1b with Docker Model Runner:
docker model run hf.co/Deci/DeciCoder-1b
Adding Evaluation Results
#13
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -177,4 +177,17 @@ author = {DeciAI Research Team},
|
|
| 177 |
year = {2023}
|
| 178 |
url={[https://huggingface.co/deci/decicoder-1b](https://huggingface.co/deci/decicoder-1b)},
|
| 179 |
}
|
| 180 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 177 |
year = {2023}
|
| 178 |
url={[https://huggingface.co/deci/decicoder-1b](https://huggingface.co/deci/decicoder-1b)},
|
| 179 |
}
|
| 180 |
+
```
|
| 181 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 182 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Deci__DeciCoder-1b)
|
| 183 |
+
|
| 184 |
+
| Metric | Value |
|
| 185 |
+
|-----------------------|---------------------------|
|
| 186 |
+
| Avg. | 25.6 |
|
| 187 |
+
| ARC (25-shot) | 21.16 |
|
| 188 |
+
| HellaSwag (10-shot) | 31.09 |
|
| 189 |
+
| MMLU (5-shot) | 24.34 |
|
| 190 |
+
| TruthfulQA (0-shot) | 47.05 |
|
| 191 |
+
| Winogrande (5-shot) | 50.83 |
|
| 192 |
+
| GSM8K (5-shot) | 1.74 |
|
| 193 |
+
| DROP (3-shot) | 2.98 |
|