Instructions to use danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq with Transformers:

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

pipe = pipeline("text-generation", model="danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq")
model = AutoModelForCausalLM.from_pretrained("danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq

SGLang

How to use danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq 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 "danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq" \
    --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": "danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq",
		"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 "danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq" \
        --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": "danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq with Docker Model Runner:
```
docker model run hf.co/danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Sample repository

Development Status :: 2 - Pre-Alpha
Developed by MinWoo Park, 2023, Seoul, South Korea. Contact: parkminwoo1991@gmail.com.

danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq model card

4-bit quantization and 128 group size weight of danielpark/ko-llama-2-jindo-7b-instruct
GPTQ is the state-of-the-art one-shot weight quantization method. This code is built upon GPTQ, GPTQ-for-LLaMa, GPTQ-triton, Auto-GPTQ.

Prompt Template

### System:
{System}

### User:
{User}

### Assistant:
{Assistant}

Inference

Install AutoGPTQ for generating.

$ pip install auto-gptq

from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM

# Set config
MODEL_NAME_OR_PATH = "danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq"
MODEL_BASENAME = "gptq_model-4bit-128g"
USE_TRITON = False
MODEL, TOKENIZER = AutoGPTQForCausalLM.from_quantized(
    MODEL_NAME_OR_PATH,
    model_basename=MODEL_BASENAME,
    use_safetensors=True,
    trust_remote_code=True,
    device="cuda:0",
    use_triton=USE_TRITON,
    quantize_config=None
), AutoTokenizer.from_pretrained(MODEL_NAME_OR_PATH, use_fast=True)


def generate_text_with_model(prompt):
    prompt_template = f"{prompt}\n"
    input_ids = TOKENIZER(prompt_template, return_tensors='pt').input_ids.cuda()
    output = MODEL.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
    generated_text = TOKENIZER.decode(output[0])
    return generated_text

def generate_text_with_pipeline(prompt):
    logging.set_verbosity(logging.CRITICAL)
    pipe = pipeline(
        "text-generation",
        model=MODEL,
        tokenizer=TOKENIZER,
        max_new_tokens=512,
        temperature=0.7,
        top_p=0.95,
        repetition_penalty=1.15
    )
    prompt_template = f"{prompt}\n"
    generated_text = pipe(prompt_template)[0]['generated_text']
    return generated_text

# Example
prompt_text = "What is GPTQ?"
generated_text_model = generate_text_with_model(prompt_text)
print(generated_text_model)

generated_text_pipeline = generate_text_with_pipeline(prompt_text)
print(generated_text_pipeline)

Web Demo

I implement the web demo using several popular tools that allow us to rapidly create web UIs.

model	web ui	quantinized
danielpark/ko-llama-2-jindo-7b-instruct.	using gradio on colab	-
danielpark/ko-llama-2-jindo-7b-instruct-4bit-128g-gptq	using text-generation-webui on colab	gptq
danielpark/ko-llama-2-jindo-7b-instruct-ggml	koboldcpp-v1.38	ggml

Downloads last month: -