Instructions to use openchat/openchat_3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openchat/openchat_3.5 with Transformers:

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

pipe = pipeline("text-generation", model="openchat/openchat_3.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openchat/openchat_3.5")
model = AutoModelForCausalLM.from_pretrained("openchat/openchat_3.5")
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

vLLM

How to use openchat/openchat_3.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openchat/openchat_3.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openchat/openchat_3.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openchat/openchat_3.5

SGLang

How to use openchat/openchat_3.5 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 "openchat/openchat_3.5" \
    --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": "openchat/openchat_3.5",
		"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 "openchat/openchat_3.5" \
        --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": "openchat/openchat_3.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openchat/openchat_3.5 with Docker Model Runner:
```
docker model run hf.co/openchat/openchat_3.5
```

How did Mixtral make openchat_3.5 worse?

#34

by JJJJJPSYCHIC - opened Dec 12, 2023

Discussion

JJJJJPSYCHIC

Dec 12, 2023

I don't know what happened, I don't know what happened behind the scenes, but openchat has been acting schizophrenic since mixtral was released. It just goes on rambling sentences it didn't used to now, listing adjectives and synonyms for hundreds of tokens for no reason.

Why can't we just have a good working openchat that's unaffected by other development? It worked a couple days ago. Leave it alone.

imone

OpenChat org Dec 13, 2023

Sorry it might be affected by vLLM update. We're confirming the issue.

Alignment-Lab-AI

OpenChat org Dec 13, 2023

•

edited Dec 13, 2023

I don't know what happened, I don't know what happened behind the scenes, but openchat has been acting schizophrenic since mixtral was released. It just goes on rambling sentences it didn't used to now, listing adjectives and synonyms for hundreds of tokens for no reason.

Why can't we just have a good working openchat that's unaffected by other development? It worked a couple days ago. Leave it alone.

i dont believe there have been any major updates in the last few days that would have affected your local build

Alignment-Lab-AI changed discussion status to closed Dec 13, 2023

Alignment-Lab-AI changed discussion status to open Dec 13, 2023

JJJJJPSYCHIC

Dec 14, 2023

i dont believe there have been any major updates in the last few days that would have affected your local build

I just use the huggingface chat.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment