Instructions to use augmxnt/shisa-base-7b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use augmxnt/shisa-base-7b-v1 with Transformers:

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

pipe = pipeline("text-generation", model="augmxnt/shisa-base-7b-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("augmxnt/shisa-base-7b-v1")
model = AutoModelForCausalLM.from_pretrained("augmxnt/shisa-base-7b-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use augmxnt/shisa-base-7b-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "augmxnt/shisa-base-7b-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "augmxnt/shisa-base-7b-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/augmxnt/shisa-base-7b-v1

SGLang

How to use augmxnt/shisa-base-7b-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 "augmxnt/shisa-base-7b-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": "augmxnt/shisa-base-7b-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 "augmxnt/shisa-base-7b-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": "augmxnt/shisa-base-7b-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use augmxnt/shisa-base-7b-v1 with Docker Model Runner:
```
docker model run hf.co/augmxnt/shisa-base-7b-v1
```

shisa-base-7b-v1

Commit History

added WandB log links

5aa465c

leonardlin commited on Dec 9, 2023

pulled from tokenizer.json for convenience

934a507

leonardlin commited on Dec 7, 2023

Update README.md

3257e9c

leonardlin commited on Dec 6, 2023

Update README.md

46b2d01

leonardlin commited on Dec 5, 2023

Update README.md

bc9268e

leonardlin commited on Dec 5, 2023

Updated plots

60a80d6

leonardlin commited on Dec 4, 2023

Update README.md

98e0992

leonardlin commited on Dec 2, 2023