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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Llama-2-7B-Chat-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

Does the model response correctly

#24

by mnwato - opened Oct 6, 2023

Discussion

mnwato

Oct 6, 2023

I used sample example:

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name_or_path = 'TheBloke/Llama-2-7B-chat-GPTQ'

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             trust_remote_code=False,
                                             revision="main")

Then generate outpu using:

prompt = "Tell me about AI"
prompt_template=f'''[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>
{prompt}[/INST]

'''

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))

But always getting string like bellow:

strijonasce Socquet fundătquetătритоsceDom Fichescequetscescesceleescescegemeindescesce fundrettoonasceритоsce Intentsceleescesce historiquessce ens Socscescescesceuyonaquetsce Dom Fundsce MortuyDomonascescesce Intent Fichavelsceonaonascesce historiquesscesce Intentритоsce Intentleeритоscesceavelsce DomритоDom IntentscegemeindeătquetscegemeindeprintStackTrace historiques historiques Fichsceритоscesce fund ensscesce Fundscestrijăt enssce fund Societyscesce Fichlee fundsceрито IntentDomsceDomscesceătengoDomscesce SocietyscesceDomscescesce fundscesce rat

McThomas

Oct 12, 2023

•

edited Oct 12, 2023

Hello, you should consider using AutoGPTQForCausalLM. Instead of AutoModelForCausalLM. Indead when quantizing the model entry, and layer are different, information are coded in different number of bit, might explain your problem.
@mnwato

from auto_gptq import AutoGPTQForCausalLM
model = AutoGPTQForCausalLM.from_quantized(
                    semodel_id,
                    use_safetensors=True,
                    trust_remote_code=True,
                    device=device,
                    use_triton=False,
                    quantize_config=None,
                )

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