Instructions to use FPHam/Hemingway_Rewrite_13b_GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FPHam/Hemingway_Rewrite_13b_GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="FPHam/Hemingway_Rewrite_13b_GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FPHam/Hemingway_Rewrite_13b_GPTQ")
model = AutoModelForCausalLM.from_pretrained("FPHam/Hemingway_Rewrite_13b_GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FPHam/Hemingway_Rewrite_13b_GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FPHam/Hemingway_Rewrite_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": "FPHam/Hemingway_Rewrite_13b_GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FPHam/Hemingway_Rewrite_13b_GPTQ

SGLang

How to use FPHam/Hemingway_Rewrite_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 "FPHam/Hemingway_Rewrite_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": "FPHam/Hemingway_Rewrite_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 "FPHam/Hemingway_Rewrite_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": "FPHam/Hemingway_Rewrite_13b_GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FPHam/Hemingway_Rewrite_13b_GPTQ with Docker Model Runner:
```
docker model run hf.co/FPHam/Hemingway_Rewrite_13b_GPTQ
```

Training params

by TeeZee - opened Apr 9, 2024

Discussion

TeeZee

Apr 9, 2024

Hi, I'm experimenting with giving LLM a specific writing style, but so far not so great results. I read your article about parameters, would you be willing to share what rank, alpha, how many epochs or steps did you use to train in the style of Hemingway? Also was it just pure paragraphs used to train or did you append some specific prompt to it?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment