Instructions to use roleplaiapp/AceInstruct-72B-Q2_K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use roleplaiapp/AceInstruct-72B-Q2_K-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="roleplaiapp/AceInstruct-72B-Q2_K-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("roleplaiapp/AceInstruct-72B-Q2_K-GGUF", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use roleplaiapp/AceInstruct-72B-Q2_K-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "roleplaiapp/AceInstruct-72B-Q2_K-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "roleplaiapp/AceInstruct-72B-Q2_K-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/roleplaiapp/AceInstruct-72B-Q2_K-GGUF

SGLang

How to use roleplaiapp/AceInstruct-72B-Q2_K-GGUF 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 "roleplaiapp/AceInstruct-72B-Q2_K-GGUF" \
    --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": "roleplaiapp/AceInstruct-72B-Q2_K-GGUF",
		"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 "roleplaiapp/AceInstruct-72B-Q2_K-GGUF" \
        --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": "roleplaiapp/AceInstruct-72B-Q2_K-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use roleplaiapp/AceInstruct-72B-Q2_K-GGUF with Docker Model Runner:
```
docker model run hf.co/roleplaiapp/AceInstruct-72B-Q2_K-GGUF
```

roleplaiapp/AceInstruct-72B-Q2_K-GGUF

Repo: roleplaiapp/AceInstruct-72B-Q2_K-GGUF
Original Model: AceInstruct-72B Organization: nvidia Quantized File: aceinstruct-72b-q2_k.gguf Quantization: GGUF Quantization Method: Q2_K
Use Imatrix: False
Split Model: False

Overview

This is an GGUF Q2_K quantized version of AceInstruct-72B.

Quantization By

I often have idle A100 GPUs while building/testing and training the RP app, so I put them to use quantizing models. I hope the community finds these quantizations useful.

Andrew Webby @ RolePlai

Downloads last month: 3

GGUF

Hardware compatibility

2-bit

Model tree for roleplaiapp/AceInstruct-72B-Q2_K-GGUF

Base model

nvidia/AceInstruct-72B

Quantized

(19)

this model