Instructions to use ludis/tsukasa-120b-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ludis/tsukasa-120b-qlora with Transformers:

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

pipe = pipeline("text-generation", model="ludis/tsukasa-120b-qlora")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ludis/tsukasa-120b-qlora")
model = AutoModelForCausalLM.from_pretrained("ludis/tsukasa-120b-qlora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ludis/tsukasa-120b-qlora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ludis/tsukasa-120b-qlora"
# 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-120b-qlora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ludis/tsukasa-120b-qlora

SGLang

How to use ludis/tsukasa-120b-qlora 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-120b-qlora" \
    --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-120b-qlora",
		"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-120b-qlora" \
        --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-120b-qlora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ludis/tsukasa-120b-qlora with Docker Model Runner:
```
docker model run hf.co/ludis/tsukasa-120b-qlora
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Gen Settings & Prompting

https://rentry.org/tsukasamodel

Training

axolotl was used for training on a 8x nvidia a100 gpu cluster.

the a100 GPU cluster has been graciously provided by lloorree.

rank 8 qlora (all modules) tune

base model alpindale/goliath-120b tuned on koishi commit 6e675d1 for one epoch

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

then tuned on limarp (without ponyville, lolicit, all the fallen, and eka's portal subsets) Version 2023-10-19 for 2 epochs in metharme completion format

Downloads last month: 10

Model tree for ludis/tsukasa-120b-qlora

Quantizations

2 models

Datasets used to train ludis/tsukasa-120b-qlora

Collection including ludis/tsukasa-120b-qlora

goliath 120b tunes

Collection

2 items • Updated Mar 2