Text Generation
Transformers
PyTorch
English
llama
math
reasoning
Eval Results
text-generation-inference
Instructions to use EleutherAI/llemma_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EleutherAI/llemma_7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="EleutherAI/llemma_7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("EleutherAI/llemma_7b") model = AutoModelForCausalLM.from_pretrained("EleutherAI/llemma_7b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use EleutherAI/llemma_7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "EleutherAI/llemma_7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EleutherAI/llemma_7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/EleutherAI/llemma_7b
- SGLang
How to use EleutherAI/llemma_7b 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 "EleutherAI/llemma_7b" \ --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": "EleutherAI/llemma_7b", "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 "EleutherAI/llemma_7b" \ --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": "EleutherAI/llemma_7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use EleutherAI/llemma_7b with Docker Model Runner:
docker model run hf.co/EleutherAI/llemma_7b
Commit ·
acc26c5
1
Parent(s): 84c323e
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: llama2
|
| 3 |
datasets:
|
| 4 |
- EleutherAI/proof-pile-2
|
|
|
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
tags:
|
|
@@ -65,6 +66,4 @@ In addition to chain-of-thought reasoning, Llemma has strong capabilities in com
|
|
| 65 |
archivePrefix={arXiv},
|
| 66 |
primaryClass={cs.CL}
|
| 67 |
}
|
| 68 |
-
```
|
| 69 |
-
|
| 70 |
-
|
|
|
|
| 2 |
license: llama2
|
| 3 |
datasets:
|
| 4 |
- EleutherAI/proof-pile-2
|
| 5 |
+
- open-web-math/open-web-math
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
tags:
|
|
|
|
| 66 |
archivePrefix={arXiv},
|
| 67 |
primaryClass={cs.CL}
|
| 68 |
}
|
| 69 |
+
```
|
|
|
|
|
|