Instructions to use GritLM/GritLM-7B-KTO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GritLM/GritLM-7B-KTO with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="GritLM/GritLM-7B-KTO", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GritLM/GritLM-7B-KTO", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("GritLM/GritLM-7B-KTO", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GritLM/GritLM-7B-KTO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GritLM/GritLM-7B-KTO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GritLM/GritLM-7B-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GritLM/GritLM-7B-KTO

SGLang

How to use GritLM/GritLM-7B-KTO 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 "GritLM/GritLM-7B-KTO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GritLM/GritLM-7B-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "GritLM/GritLM-7B-KTO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GritLM/GritLM-7B-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GritLM/GritLM-7B-KTO with Docker Model Runner:
```
docker model run hf.co/GritLM/GritLM-7B-KTO
```

CombinHorizon commited on Jun 14, 2024

Commit

2599568

verified ·

1 Parent(s): 108ab54

Create README.md

Browse files

Files changed (1) hide show

README.md +41 -0

README.md ADDED Viewed

	@@ -0,0 +1,41 @@

+---
+pipeline_tag: text-generation
+inference: true
+license: apache-2.0
+datasets:
+- GritLM/tulu2
+---
+# Model Summary
+A [**KTO**](https://arxiv.org/abs/2402.01306) version of https://huggingface.co/GritLM/GritLM-7B
+> GritLM is a generative representational instruction tuned language model. It unifies text representation (embedding) and text generation into a single model achieving state-of-the-art performance on both types of tasks.
+- **Repository:** [ContextualAI/gritlm](https://github.com/ContextualAI/gritlm)
+- **Paper:** https://arxiv.org/abs/2402.09906
+- **Logs:** https://wandb.ai/muennighoff/gritlm/runs/0uui712t/overview
+- **Script:** https://github.com/ContextualAI/gritlm/blob/main/scripts/training/train_gritlm_7b.sh
+| Model | Description |
+|-------|-------------|
+| [GritLM 7B](https://hf.co/GritLM/GritLM-7B) | Mistral 7B finetuned using GRIT |
+| [GritLM 8x7B](https://hf.co/GritLM/GritLM-8x7B) | Mixtral 8x7B finetuned using GRIT |
+# Use
+The model usage is documented [here](https://github.com/ContextualAI/gritlm?tab=readme-ov-file#inference).
+# Citation
+```bibtex
+@misc{muennighoff2024generative,
+      title={Generative Representational Instruction Tuning},
+      author={Niklas Muennighoff and Hongjin Su and Liang Wang and Nan Yang and Furu Wei and Tao Yu and Amanpreet Singh and Douwe Kiela},
+      year={2024},
+      eprint={2402.09906},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```