Instructions to use Jithendra-k/interACT_LLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jithendra-k/interACT_LLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jithendra-k/interACT_LLM")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Jithendra-k/interACT_LLM") model = AutoModelForCausalLM.from_pretrained("Jithendra-k/interACT_LLM") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Jithendra-k/interACT_LLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jithendra-k/interACT_LLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jithendra-k/interACT_LLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Jithendra-k/interACT_LLM
- SGLang
How to use Jithendra-k/interACT_LLM 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 "Jithendra-k/interACT_LLM" \ --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": "Jithendra-k/interACT_LLM", "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 "Jithendra-k/interACT_LLM" \ --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": "Jithendra-k/interACT_LLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Jithendra-k/interACT_LLM with Docker Model Runner:
docker model run hf.co/Jithendra-k/interACT_LLM
Update README.md
Browse files
README.md
CHANGED
|
@@ -197,7 +197,7 @@ Here are some plots of model performance during training:<br>
|
|
| 197 |
|
| 198 |
|
| 199 |
Here is an Example Input/Output:<br>
|
| 200 |
-
<img src="
|
| 201 |
|
| 202 |
Code to finetune a Llama-2_7B_chat model: [Google_Colab_file](https://colab.research.google.com/drive/169q4hyYZCHgD037AkMowEV7agAcNxdeQ?usp=sharing)
|
| 203 |
|
|
|
|
| 197 |
|
| 198 |
|
| 199 |
Here is an Example Input/Output:<br>
|
| 200 |
+
<img src="example.png"><br>
|
| 201 |
|
| 202 |
Code to finetune a Llama-2_7B_chat model: [Google_Colab_file](https://colab.research.google.com/drive/169q4hyYZCHgD037AkMowEV7agAcNxdeQ?usp=sharing)
|
| 203 |
|