Instructions to use TheBloke/CodeLlama-34B-Instruct-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/CodeLlama-34B-Instruct-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/CodeLlama-34B-Instruct-GPTQ", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/CodeLlama-34B-Instruct-GPTQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TheBloke/CodeLlama-34B-Instruct-GPTQ", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/CodeLlama-34B-Instruct-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/CodeLlama-34B-Instruct-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/CodeLlama-34B-Instruct-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/CodeLlama-34B-Instruct-GPTQ

SGLang

How to use TheBloke/CodeLlama-34B-Instruct-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/CodeLlama-34B-Instruct-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/CodeLlama-34B-Instruct-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/CodeLlama-34B-Instruct-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/CodeLlama-34B-Instruct-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/CodeLlama-34B-Instruct-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/CodeLlama-34B-Instruct-GPTQ
```

Is the 34B llama2 actually GPTQ working?

by mzbac - opened Aug 26, 2023

Discussion

mzbac

Aug 26, 2023

Somehow I keep getting an error for the fused llama attention.

/auto_gptq/nn_modules/fused_llama_attn.py", line 59, in forward
    query_states, key_states, value_states = torch.split(qkv_states, self.hidden_size, dim=2)
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

It seems that qkv_states doesn't match

Shape of qkv_states: torch.Size([1, 62, 10240])
Expected third dimension size: 24576
Actual third dimension size: 10240
Value of self.hidden_size: 8192

kajuberdut

Aug 26, 2023

Works for me on the 1a642c12b582330a4780047461905787cc3f18c5 commit of ooga_booga with ExLlama_HF.

mzbac

Aug 27, 2023

@giblesnot, thanks mate, I was using AutoGPTQ to load the model. I will try the Exllama.

yachty66

Aug 29, 2023

same here when running not in oogabooga. i am using the code for running it with AutoGPTQForCausalLM from huggingface and it's failing with the same error. please help.

TheBloke

Owner Aug 29, 2023

•

edited Aug 29, 2023

If using AutoGPTQ, please pass inject_fused_attention=False.

The issue is that Llama 2 70B and 34B introduced a new optimisation called GQA (Ghost Query Attention) which is not supported by AutoGPTQ's Fused Attention optimisation.

This issue will be fixed in AutoGPTQ fairly soon, hopefully: https://github.com/PanQiWei/AutoGPTQ/pull/237

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