Instructions to use nikhil07prakash/float-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nikhil07prakash/float-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nikhil07prakash/float-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nikhil07prakash/float-7b") model = AutoModelForCausalLM.from_pretrained("nikhil07prakash/float-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use nikhil07prakash/float-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nikhil07prakash/float-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nikhil07prakash/float-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nikhil07prakash/float-7b
- SGLang
How to use nikhil07prakash/float-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 "nikhil07prakash/float-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": "nikhil07prakash/float-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 "nikhil07prakash/float-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": "nikhil07prakash/float-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nikhil07prakash/float-7b with Docker Model Runner:
docker model run hf.co/nikhil07prakash/float-7b
Update README.md
Browse files
README.md
CHANGED
|
@@ -44,12 +44,11 @@ model = AutoModel.from_pretrained("nikhil07prakash/float-7b")
|
|
| 44 |
**BibTeX:**
|
| 45 |
|
| 46 |
```python
|
| 47 |
-
@
|
| 48 |
title={Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking},
|
| 49 |
-
author={
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
primaryClass={cs.CL}
|
| 54 |
}
|
| 55 |
```
|
|
|
|
| 44 |
**BibTeX:**
|
| 45 |
|
| 46 |
```python
|
| 47 |
+
@inproceedings{prakash2023fine,
|
| 48 |
title={Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking},
|
| 49 |
+
author={Prakash, Nikhil and Shaham, Tamar Rott and Haklay, Tal and Belinkov, Yonatan and Bau, David},
|
| 50 |
+
booktitle={Proceedings of the 2024 International Conference on Learning Representations},
|
| 51 |
+
note={arXiv:2402.14811},
|
| 52 |
+
year={2024}
|
|
|
|
| 53 |
}
|
| 54 |
```
|