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
zhangir-azerbayev commited on
Commit ·
84c323e
1
Parent(s): 21a6f14
update readme
Browse files
README.md
CHANGED
|
@@ -53,7 +53,7 @@ Further performance can be extracted by using majority voting:
|
|
| 53 |
| Minerva | 540B | 78.5% | 30.8% | 75.0% | - | 50.3% |
|
| 54 |
|
| 55 |
### Tool Use and Theorem Proving
|
| 56 |
-
In addition to chain-of-thought reasoning, Llemma has strong capabilities in computational mathematics tasks. For tool use and formal theorem proving evaluations, see [our paper](
|
| 57 |
|
| 58 |
### Citation
|
| 59 |
```
|
|
|
|
| 53 |
| Minerva | 540B | 78.5% | 30.8% | 75.0% | - | 50.3% |
|
| 54 |
|
| 55 |
### Tool Use and Theorem Proving
|
| 56 |
+
In addition to chain-of-thought reasoning, Llemma has strong capabilities in computational mathematics tasks. For tool use and formal theorem proving evaluations, see [our paper](http://arxiv.org/abs/2310.10631).
|
| 57 |
|
| 58 |
### Citation
|
| 59 |
```
|