Instructions to use TigerResearch/tigerbot-70b-chat-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TigerResearch/tigerbot-70b-chat-v2 with Transformers:

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

pipe = pipeline("text-generation", model="TigerResearch/tigerbot-70b-chat-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TigerResearch/tigerbot-70b-chat-v2")
model = AutoModelForCausalLM.from_pretrained("TigerResearch/tigerbot-70b-chat-v2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TigerResearch/tigerbot-70b-chat-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TigerResearch/tigerbot-70b-chat-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TigerResearch/tigerbot-70b-chat-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TigerResearch/tigerbot-70b-chat-v2

SGLang

How to use TigerResearch/tigerbot-70b-chat-v2 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 "TigerResearch/tigerbot-70b-chat-v2" \
    --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": "TigerResearch/tigerbot-70b-chat-v2",
		"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 "TigerResearch/tigerbot-70b-chat-v2" \
        --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": "TigerResearch/tigerbot-70b-chat-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TigerResearch/tigerbot-70b-chat-v2 with Docker Model Runner:
```
docker model run hf.co/TigerResearch/tigerbot-70b-chat-v2
```

WHY "max_position_embeddings": 2048

by chenxi118 - opened Dec 2, 2023

Discussion

chenxi118

Dec 2, 2023

Typically, models based on LLaMA-2 have a parameter size of 4K, but why is it 2K here? Will this lead to a shorter effective understanding of the context by the model?

yechen

Tiger Research org Dec 3, 2023

this is because we fine tuned this version of model using 2048 max length to group data, we found almost all demonstration data within this length. However, the model should work fine with 4k length or even longer, RoPE can extrapolate well due to its functional form.

chenxi118

Dec 3, 2023

Thanks！

chenxi118 changed discussion status to closed Dec 3, 2023

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