Instructions to use TheBloke/Llama-2-7B-Chat-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Llama-2-7B-Chat-GGML with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Llama-2-7B-Chat-GGML")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/Llama-2-7B-Chat-GGML with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Llama-2-7B-Chat-GGML"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Llama-2-7B-Chat-GGML",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Llama-2-7B-Chat-GGML

SGLang

How to use TheBloke/Llama-2-7B-Chat-GGML 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 "TheBloke/Llama-2-7B-Chat-GGML" \
    --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": "TheBloke/Llama-2-7B-Chat-GGML",
		"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 "TheBloke/Llama-2-7B-Chat-GGML" \
        --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": "TheBloke/Llama-2-7B-Chat-GGML",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Llama-2-7B-Chat-GGML with Docker Model Runner:
```
docker model run hf.co/TheBloke/Llama-2-7B-Chat-GGML
```

Can you fine-tune Llama-2-7B-Chat-GGML and other quantized version of llama?

#28

by obscureagent - opened Sep 7, 2023

Discussion

obscureagent

Sep 7, 2023

Can you fine-tune Llama-2-7B-Chat-GGML and other quantized version of llama?

vpkprasanna

Sep 13, 2023

As per my knowledge we cannot able to quantize the already quantized model but we can quantize the original model uisng GGML or GPTQ Techniques

obscureagent

Sep 13, 2023

•

edited Sep 13, 2023

I know this discussion is for the GGML version, but while I have you, can you point me to a resource regarding a straight-forward process of fine-tuning Llama-2-7b or 7v-chat?

vpkprasanna

Sep 14, 2023

I know this discussion is for the GGML version, but while I have you, can you point me to a resource regarding a straight-forward process of fine-tuning Llama-2-7b or 7v-chat?

you can go through these courses to know how to finetune LLM in general
https://learn.deeplearning.ai/finetuning-large-language-models/lesson/1/introduction

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment