Instructions to use ludis/tsukasa-7b-qlora-gptq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ludis/tsukasa-7b-qlora-gptq with Transformers:

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

pipe = pipeline("text-generation", model="ludis/tsukasa-7b-qlora-gptq")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ludis/tsukasa-7b-qlora-gptq")
model = AutoModelForCausalLM.from_pretrained("ludis/tsukasa-7b-qlora-gptq", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ludis/tsukasa-7b-qlora-gptq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ludis/tsukasa-7b-qlora-gptq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ludis/tsukasa-7b-qlora-gptq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ludis/tsukasa-7b-qlora-gptq

SGLang

How to use ludis/tsukasa-7b-qlora-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 "ludis/tsukasa-7b-qlora-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": "ludis/tsukasa-7b-qlora-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 "ludis/tsukasa-7b-qlora-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": "ludis/tsukasa-7b-qlora-gptq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ludis/tsukasa-7b-qlora-gptq with Docker Model Runner:
```
docker model run hf.co/ludis/tsukasa-7b-qlora-gptq
```

Gen Settings & Prompting

https://rentry.org/tsukasamodel

GPTQ

2048 sequence length

VMware/open-instruct dataset

Training

axolotl was used for training on a 8x nvidia a40 gpu cluster.

the a40 GPU cluster has been graciously provided by Arc Compute.

rank 16 qlora (all modules) tune

base model mistralai/Mistral-7B-v0.1 tuned on koishi commit 6e675d1 for one epoch

then tuned on pippa 6412b0c for one epoch (metharme completion)

then tuned on limarp Version 2023-10-19 for 2 epochs in metharme completion format

Downloads last month: 9

Datasets used to train ludis/tsukasa-7b-qlora-gptq

Collection including ludis/tsukasa-7b-qlora-gptq

mistral 0.2 7b tunes

Collection

5 items • Updated Mar 2