Instructions to use molbal/drama-mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use molbal/drama-mistral with PEFT:
```
Task type is invalid.
```

How to use molbal/drama-mistral with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="molbal/drama-mistral",
	filename="drama-mistral-F16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use molbal/drama-mistral with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf molbal/drama-mistral:F16
# Run inference directly in the terminal:
llama-cli -hf molbal/drama-mistral:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf molbal/drama-mistral:F16
# Run inference directly in the terminal:
llama-cli -hf molbal/drama-mistral:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf molbal/drama-mistral:F16
# Run inference directly in the terminal:
./llama-cli -hf molbal/drama-mistral:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf molbal/drama-mistral:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf molbal/drama-mistral:F16

Use Docker

docker model run hf.co/molbal/drama-mistral:F16

LM Studio
Jan

vLLM

How to use molbal/drama-mistral with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/molbal/drama-mistral:F16

Ollama
How to use molbal/drama-mistral with Ollama:
```
ollama run hf.co/molbal/drama-mistral:F16
```

Unsloth Studio new

How to use molbal/drama-mistral with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for molbal/drama-mistral to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for molbal/drama-mistral to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for molbal/drama-mistral to start chatting

Docker Model Runner
How to use molbal/drama-mistral with Docker Model Runner:
```
docker model run hf.co/molbal/drama-mistral:F16
```

Lemonade

How to use molbal/drama-mistral with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull molbal/drama-mistral:F16

Run and chat with the model

lemonade run user.drama-mistral-F16

List all available models

lemonade list

Model Card for molbal/drama-mistral

Text completion model trained on public domain novels.

Model Details

Model Description

This model is trained on a large corpus of novels from various drama categories, including detective fiction, crime nonfiction, mystery fiction, gothic fiction, horror, romantic fiction, short stories, and western. The model is able to generate text that is similar in style and tone to the novels in the dataset.

Developed by: Bálint Molnár-Kaló https://huggingface.co/molbal
Model type: TText completion model
Language(s) (NLP): English only
License: Apache license 2.0
Finetuned from model [optional]: unsloth/mistral-7b-v0.2-bnb-4bit

Model Sources

Repository: https://huggingface.co/datasets/molbal/dramallama-novels
Demo: https://huggingface.co/datasets/molbal/dramallama-novels/viewer/default/train

Training details

Trained for ~19 hours on a RTX 4090 using Unsloth and its wrapper scripts found in https://github.com/molbal/llm-text-completion-finetune uing the cloud provider vast.ai

Downloads last month: 27

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Model tree for molbal/drama-mistral

Base model

unsloth/mistral-7b-v0.2-bnb-4bit

Adapter

(3)

this model

molbal
/

drama-mistral