Instructions to use codewithdark/deepmath-7b-l with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codewithdark/deepmath-7b-l with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="codewithdark/deepmath-7b-l")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("codewithdark/deepmath-7b-l", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use codewithdark/deepmath-7b-l with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "codewithdark/deepmath-7b-l" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codewithdark/deepmath-7b-l", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/codewithdark/deepmath-7b-l
- SGLang
How to use codewithdark/deepmath-7b-l 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 "codewithdark/deepmath-7b-l" \ --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": "codewithdark/deepmath-7b-l", "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 "codewithdark/deepmath-7b-l" \ --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": "codewithdark/deepmath-7b-l", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use codewithdark/deepmath-7b-l with Docker Model Runner:
docker model run hf.co/codewithdark/deepmath-7b-l
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,7 @@ base_model:
|
|
| 13 |
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
| 14 |
pipeline_tag: text-generation
|
| 15 |
---
|
|
|
|
| 16 |
# DeepMath-7B-L
|
| 17 |
|
| 18 |
## Model Overview
|
|
@@ -76,7 +77,7 @@ This model is released under the Apache 2.0 License.
|
|
| 76 |
|
| 77 |
## Citation
|
| 78 |
If you use these models, please cite:
|
| 79 |
-
|
| 80 |
@misc{DeepMath-7B-L,
|
| 81 |
author = {Ahsan},
|
| 82 |
title = {DeepMath-7B-L: LoRA Adapter Enhanced Model for Math Reasoning},
|
|
|
|
| 13 |
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
| 14 |
pipeline_tag: text-generation
|
| 15 |
---
|
| 16 |
+
|
| 17 |
# DeepMath-7B-L
|
| 18 |
|
| 19 |
## Model Overview
|
|
|
|
| 77 |
|
| 78 |
## Citation
|
| 79 |
If you use these models, please cite:
|
| 80 |
+
```
|
| 81 |
@misc{DeepMath-7B-L,
|
| 82 |
author = {Ahsan},
|
| 83 |
title = {DeepMath-7B-L: LoRA Adapter Enhanced Model for Math Reasoning},
|