Instructions to use TigerResearch/tigerbot-7b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TigerResearch/tigerbot-7b-base with Transformers:

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

pipe = pipeline("text-generation", model="TigerResearch/tigerbot-7b-base")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TigerResearch/tigerbot-7b-base")
model = AutoModelForCausalLM.from_pretrained("TigerResearch/tigerbot-7b-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TigerResearch/tigerbot-7b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TigerResearch/tigerbot-7b-base"
# 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-7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TigerResearch/tigerbot-7b-base

SGLang

How to use TigerResearch/tigerbot-7b-base 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-7b-base" \
    --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-7b-base",
		"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-7b-base" \
        --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-7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TigerResearch/tigerbot-7b-base with Docker Model Runner:
```
docker model run hf.co/TigerResearch/tigerbot-7b-base
```

tigerbot-7b-base

Commit History

Dec 20, 2024

00:52
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
c0d4b0a

Sep 20, 2023

06:16
Update README.md

i4never

6b804ee

Aug 21, 2023

07:46
Update tokenizer_config.json

i4never

3008314
07:28
update tigerbot-7b-base-v3-tokenizer

i4never

d2b2f67

Aug 19, 2023

07:00
Create README.md

i4never

3e674be
06:59
upload tigerbot-7b-base-v3-tokenizer

i4never

b4516a6
06:56
upload tigerbot-7b-base-v3

i4never

9c85880
06:21
initial commit

i4never

c5ec0ef

Commit History

Dec 20, 2024

Adding `safetensors` variant of this model⁠

Sep 20, 2023

Update README.md

Aug 21, 2023

Update tokenizer_config.json

update tigerbot-7b-base-v3-tokenizer

Aug 19, 2023

Create README.md

upload tigerbot-7b-base-v3-tokenizer

upload tigerbot-7b-base-v3

initial commit