Instructions to use Neko-Institute-of-Science/LLaMA-65B-4bit-32g with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neko-Institute-of-Science/LLaMA-65B-4bit-32g with Transformers:

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

pipe = pipeline("text-generation", model="Neko-Institute-of-Science/LLaMA-65B-4bit-32g")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Neko-Institute-of-Science/LLaMA-65B-4bit-32g")
model = AutoModelForCausalLM.from_pretrained("Neko-Institute-of-Science/LLaMA-65B-4bit-32g", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Neko-Institute-of-Science/LLaMA-65B-4bit-32g with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Neko-Institute-of-Science/LLaMA-65B-4bit-32g"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neko-Institute-of-Science/LLaMA-65B-4bit-32g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Neko-Institute-of-Science/LLaMA-65B-4bit-32g

SGLang

How to use Neko-Institute-of-Science/LLaMA-65B-4bit-32g 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 "Neko-Institute-of-Science/LLaMA-65B-4bit-32g" \
    --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": "Neko-Institute-of-Science/LLaMA-65B-4bit-32g",
		"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 "Neko-Institute-of-Science/LLaMA-65B-4bit-32g" \
        --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": "Neko-Institute-of-Science/LLaMA-65B-4bit-32g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Neko-Institute-of-Science/LLaMA-65B-4bit-32g with Docker Model Runner:
```
docker model run hf.co/Neko-Institute-of-Science/LLaMA-65B-4bit-32g
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

I tried making groupsize 16 but that did not end well so I went with 32g. FYI I can run this with full context on my A6000.

65B  (act-order true-sequential groupsize)
wikitext2 3.5319948196411133 (stock 16bit)
wikitext2 3.610668182373047 (32g)
wikitext2 3.650667667388916 (16g)
wikitext2 3.6660284996032715 (128)
ptb-new 7.66942024230957 (stock 16bit)
ptb-new 7.71506929397583 (32g)
ptb-new 7.762592792510986 (128)
ptb-new 7.829207897186279 (16g)
c4-new 5.8114824295043945 (stock 16bit)
c4-new 5.859227657318115 (32g)
c4-new 5.893154144287109 (128)
c4-new 5.929086208343506 (16g)

Downloads last month: 12