Instructions to use anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g with Transformers:

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

pipe = pipeline("text-generation", model="anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g")
model = AutoModelForCausalLM.from_pretrained("anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g

SGLang

How to use anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g 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 "anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g" \
    --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": "anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g",
		"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 "anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g" \
        --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": "anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g with Docker Model Runner:
```
docker model run hf.co/anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g
```

anon8231489123 commited on Apr 1, 2023

Commit

14d6f0a

1 Parent(s): 7fc3159

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -1

README.md CHANGED Viewed

@@ -1,4 +1,14 @@
-(untested)
 GPTQ 4bit quantization of: https://huggingface.co/chavinlo/gpt4-x-alpaca
 Note: This was quantized with this branch of GPTQ-for-LLaMA: https://github.com/qwopqwop200/GPTQ-for-LLaMa/tree/triton
 Because of this, it appears to be incompatible with Oobabooga at the moment. Stay tuned?

+Update: Okay... Two different models now. One generated in the Triton branch, one generated in Cuda. Use the Cuda one for now unless the Triton branch becomes widely used.
+Cuda info (use this one):
+Command:
+CUDA_VISIBLE_DEVICES=0 python llama.py ./models/chavinlo-gpt4-x-alpaca
+--wbits 4
+--true-sequential
+--groupsize 128
+--save gpt-x-alpaca-13b-native-4bit-128g-cuda.pt
+Prev. info
 GPTQ 4bit quantization of: https://huggingface.co/chavinlo/gpt4-x-alpaca
 Note: This was quantized with this branch of GPTQ-for-LLaMA: https://github.com/qwopqwop200/GPTQ-for-LLaMa/tree/triton
 Because of this, it appears to be incompatible with Oobabooga at the moment. Stay tuned?