Instructions to use bofenghuang/vigogne-33b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bofenghuang/vigogne-33b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="bofenghuang/vigogne-33b-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bofenghuang/vigogne-33b-instruct")
model = AutoModelForCausalLM.from_pretrained("bofenghuang/vigogne-33b-instruct")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bofenghuang/vigogne-33b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bofenghuang/vigogne-33b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bofenghuang/vigogne-33b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bofenghuang/vigogne-33b-instruct

SGLang

How to use bofenghuang/vigogne-33b-instruct 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 "bofenghuang/vigogne-33b-instruct" \
    --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": "bofenghuang/vigogne-33b-instruct",
		"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 "bofenghuang/vigogne-33b-instruct" \
        --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": "bofenghuang/vigogne-33b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bofenghuang/vigogne-33b-instruct with Docker Model Runner:
```
docker model run hf.co/bofenghuang/vigogne-33b-instruct
```

bofenghuang commited on Jul 19, 2023

Commit

9c2b558

1 Parent(s): c7f02be

up

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -11,12 +11,12 @@ inference: false
 ---
 <p align="center" width="100%">
-<img src="https://huggingface.co/bofenghuang/vigogne-30b-instruct/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
 </p>
-# Vigogne-30B-Instruct: A French Instruction-following LLaMA Model
-Vigogne-30B-Instruct is a LLaMA-30B model fine-tuned to follow the French instructions.
 For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
@@ -36,7 +36,7 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 from vigogne.preprocess import generate_instruct_prompt
-model_name_or_path = "bofenghuang/vigogne-30b-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False)
 model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, device_map="auto")

 ---
 <p align="center" width="100%">
+<img src="https://huggingface.co/bofenghuang/vigogne-33b-instruct/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
 </p>
+# Vigogne-33B-Instruct: A French Instruction-following LLaMA Model
+Vigogne-33B-Instruct is a LLaMA-33B model fine-tuned to follow the French instructions.
 For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 from vigogne.preprocess import generate_instruct_prompt
+model_name_or_path = "bofenghuang/vigogne-33b-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False)
 model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, device_map="auto")