Instructions to use poisson-fish/ultralm-13b-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use poisson-fish/ultralm-13b-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="poisson-fish/ultralm-13b-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("poisson-fish/ultralm-13b-GPTQ")
model = AutoModelForCausalLM.from_pretrained("poisson-fish/ultralm-13b-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use poisson-fish/ultralm-13b-GPTQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/poisson-fish/ultralm-13b-GPTQ

SGLang

How to use poisson-fish/ultralm-13b-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 "poisson-fish/ultralm-13b-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": "poisson-fish/ultralm-13b-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 "poisson-fish/ultralm-13b-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": "poisson-fish/ultralm-13b-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use poisson-fish/ultralm-13b-GPTQ with Docker Model Runner:
```
docker model run hf.co/poisson-fish/ultralm-13b-GPTQ
```

This is openbmb/UltraLM-13b recovered with huggyllama/llama-13b and quantized to 4bit GPTQ with the following config:

quantize_config = BaseQuantizeConfig(
    bits=4, 
    group_size=32,  
    desc_act=True,
)

Original Model Card:

UltraLM-13b

This is UltraLM-13b delta weights, a chat language model trained upon UltraChat

Model Details

Model Description

The model is fine-tuned based on LLaMA-13b with a multi-turn chat-format template as below

User: instruction 1<eos_token>
Assistant: response 1<eos_token>
User: instruction 2<eos_token>
Assistant: response 2<eos_token>
...

License: UltraLM is based on LLaMA and should be used under LLaMA's model license.
Finetuned from model: LLaMA-13b
Finetuned on data: UltraChat

Model Sources

Repository: UltraChat
Paper: arxiv
Demo: [More Information Needed]

Uses

To use this model, you need to recover the full model from the delta weights and perform inference following the template below:

[Optional]User: system prompt<eos_token>
User: user input<eos_token>
Assistant:

Downloads last month: 9

Dataset used to train poisson-fish/ultralm-13b-GPTQ

Paper for poisson-fish/ultralm-13b-GPTQ

Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Paper • 2305.14233 • Published May 23, 2023 • 8