Instructions to use TigerResearch/tigerbot-7b-sft-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TigerResearch/tigerbot-7b-sft-v1 with Transformers:

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

pipe = pipeline("text-generation", model="TigerResearch/tigerbot-7b-sft-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TigerResearch/tigerbot-7b-sft-v1")
model = AutoModelForCausalLM.from_pretrained("TigerResearch/tigerbot-7b-sft-v1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TigerResearch/tigerbot-7b-sft-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TigerResearch/tigerbot-7b-sft-v1"
# 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-sft-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TigerResearch/tigerbot-7b-sft-v1

SGLang

How to use TigerResearch/tigerbot-7b-sft-v1 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-sft-v1" \
    --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-sft-v1",
		"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-sft-v1" \
        --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-sft-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TigerResearch/tigerbot-7b-sft-v1 with Docker Model Runner:
```
docker model run hf.co/TigerResearch/tigerbot-7b-sft-v1
```

tigerbot-7b-sft-v1

Commit History

Update README.md

a630c0e

i4never commited on Jul 8, 2023

delete old file

0ba4d6f

cong.fu commited on Jun 7, 2023

Use bfloat16

d6e771e

cong.fu commited on Jun 7, 2023

Update README.md

3a4a3e6

vivicai commited on Jun 6, 2023

Update README.md

34b19b3

vivicai commited on Jun 6, 2023

Update README.md

94d07d7

vivicai commited on Jun 5, 2023

Update config.json

b5d8e2f

i4never commited on Jun 5, 2023

Create README.md

82adb0f

i4never commited on Jun 2, 2023

Update config.json

b436f40

i4never commited on Jun 1, 2023

Upload tokenizer

a742bfc

i4never commited on May 31, 2023

Upload BloomForCausalLM

de00fe0

i4never commited on May 31, 2023

initial commit

a06f2e6

FC commited on May 31, 2023

Commit History

Update README.md a630c0e

delete old file 0ba4d6f

Use bfloat16 d6e771e

Update README.md 3a4a3e6

Update README.md 34b19b3

Update README.md 94d07d7

Update config.json b5d8e2f

Create README.md 82adb0f

Update config.json b436f40

Upload tokenizer a742bfc

Upload BloomForCausalLM de00fe0

initial commit a06f2e6