Instructions to use TigerResearch/tigerbot-70b-chat-v3-4bit-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TigerResearch/tigerbot-70b-chat-v3-4bit-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="TigerResearch/tigerbot-70b-chat-v3-4bit-exl2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TigerResearch/tigerbot-70b-chat-v3-4bit-exl2")
model = AutoModelForCausalLM.from_pretrained("TigerResearch/tigerbot-70b-chat-v3-4bit-exl2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TigerResearch/tigerbot-70b-chat-v3-4bit-exl2 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-v3-4bit-exl2"
# 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-v3-4bit-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TigerResearch/tigerbot-70b-chat-v3-4bit-exl2

SGLang

How to use TigerResearch/tigerbot-70b-chat-v3-4bit-exl2 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-v3-4bit-exl2" \
    --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-v3-4bit-exl2",
		"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-v3-4bit-exl2" \
        --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-v3-4bit-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TigerResearch/tigerbot-70b-chat-v3-4bit-exl2 with Docker Model Runner:
```
docker model run hf.co/TigerResearch/tigerbot-70b-chat-v3-4bit-exl2
```

A cutting-edge foundation for your very own LLM.

🌐 TigerBot • 🤗 Hugging Face

This is a 4-bit EXL2 version of the Tigerbot 70b chat.

It was quantized to 4bit using: https://github.com/turboderp/exllamav2

How to download and use this model in github: https://github.com/TigerResearch/TigerBot

Here are commands to clone the TigerBot and install.

conda create --name tigerbot python=3.8
conda activate tigerbot
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia

git clone https://github.com/TigerResearch/TigerBot
cd TigerBot
pip install -r requirements.txt

Inference with command line interface

infer with exllamav2

# install exllamav2
git clone https://github.com/turboderp/exllamav2
cd exllamav2
pip install -r requirements.txt

# infer command
CUDA_VISIBLE_DEVICES=0 python other_infer/exllamav2_hf_infer.py --model_path TigerResearch/tigerbot-70b-chat-4bit-exl2

Downloads last month: 10