Instructions to use RichardErkhov/scb10x_-_typhoon-7b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/scb10x_-_typhoon-7b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RichardErkhov/scb10x_-_typhoon-7b-gguf",
	filename="typhoon-7b.IQ3_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RichardErkhov/scb10x_-_typhoon-7b-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M

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 RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M

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 RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/scb10x_-_typhoon-7b-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M
```

Unsloth Studio

How to use RichardErkhov/scb10x_-_typhoon-7b-gguf 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 RichardErkhov/scb10x_-_typhoon-7b-gguf 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 RichardErkhov/scb10x_-_typhoon-7b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RichardErkhov/scb10x_-_typhoon-7b-gguf to start chatting

Docker Model Runner
How to use RichardErkhov/scb10x_-_typhoon-7b-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/scb10x_-_typhoon-7b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/scb10x_-_typhoon-7b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.scb10x_-_typhoon-7b-gguf-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

typhoon-7b - GGUF

Model creator: https://huggingface.co/scb10x/
Original model: https://huggingface.co/scb10x/typhoon-7b/

Name	Quant method	Size
typhoon-7b.Q2_K.gguf	Q2_K	2.55GB
typhoon-7b.IQ3_XS.gguf	IQ3_XS	2.83GB
typhoon-7b.IQ3_S.gguf	IQ3_S	2.98GB
typhoon-7b.Q3_K_S.gguf	Q3_K_S	2.96GB
typhoon-7b.IQ3_M.gguf	IQ3_M	3.07GB
typhoon-7b.Q3_K.gguf	Q3_K	3.29GB
typhoon-7b.Q3_K_M.gguf	Q3_K_M	3.29GB
typhoon-7b.Q3_K_L.gguf	Q3_K_L	3.57GB
typhoon-7b.IQ4_XS.gguf	IQ4_XS	3.69GB
typhoon-7b.Q4_0.gguf	Q4_0	3.84GB
typhoon-7b.IQ4_NL.gguf	IQ4_NL	3.89GB
typhoon-7b.Q4_K_S.gguf	Q4_K_S	3.87GB
typhoon-7b.Q4_K.gguf	Q4_K	4.09GB
typhoon-7b.Q4_K_M.gguf	Q4_K_M	4.09GB
typhoon-7b.Q4_1.gguf	Q4_1	4.26GB
typhoon-7b.Q5_0.gguf	Q5_0	4.67GB
typhoon-7b.Q5_K_S.gguf	Q5_K_S	4.67GB
typhoon-7b.Q5_K.gguf	Q5_K	4.8GB
typhoon-7b.Q5_K_M.gguf	Q5_K_M	4.8GB
typhoon-7b.Q5_1.gguf	Q5_1	5.09GB
typhoon-7b.Q6_K.gguf	Q6_K	5.55GB

Original model description:

license: apache-2.0 language: - th library_name: transformers pipeline_tag: text-generation tags: - pretrained

Typhoon-7B: Thai Large Language Model (Pretrained)

Typhoon-7B is a pretrained Thai 🇹🇭 large language model with 7 billion parameters, and it is based on Mistral-7B.

Typhoon-7B outperforms all open-source Thai language models at the time of writing as evaluated on Thai examination benchmarks, and its instruction-tuned variant achieves the best results in instruction-following tasks. Also, its performance in Thai is on par with GPT-3.5 while being 2.62 times more efficient in tokenizing Thai text.

This is not an instruction-tuned model - It may not be able to follow human instructions without using one/few-shot learning or instruction fine-tuning. The model does not have any moderation mechanisms, and may generate harmful or inappropriate responses.

The Instruct model (chat-model) will be released soon. The beta version register is open at https://opentyphoon.ai/ or follow us for future model release https://twitter.com/opentyphoon.

For full details of this model, please read our paper.

Model Description

Model type: A 7B pretrained decoder-only model
Requirement: transformers 4.34.0 or newer.
Primary Language(s): Thai 🇹🇭 and English 🇬🇧
License: Apache-2.0 (Commercial)

Performance on Thai Benchmark

Model	ONET	IC	TGAT	TPAT-1	A-Level
Typhoon-7B	0.379	0.393	0.700	0.414	0.324
SeaLLM-7B	0.342	0.256	0.589	0.336	0.305
OpenThaiGPT-beta-7B	0.180	0.278	0.411	0.319	0.243
WangChanGLM	0.192	0.271	0.167	0.172	0.175
SEA-LION-7B	0.179	0.290	0.244	0.198	0.175
Avg. Human	0.318	-	0.472	0.406	-

Intended Uses & Limitations

This model is a pretrained base model. Thus, it may not be able to follow human instructions without using one/few-shot learning or instruction fine-tuning. The model does not have any moderation mechanisms, and may generate harmful or inappropriate responses.

https://twitter.com/opentyphoon

Support / Ask any question

https://discord.gg/CqyBscMFpg

SCB10X AI Team

Kunat Pipatanakul, Phatrasek Jirabovonvisut, Potsawee Manakul, Sittipong Sripaisarnmongkol, Ruangsak Patomwong, Pathomporn Chokchainant, Kasima Tharnpipitchai
If you find Typhoon-7B useful for your work, please cite it using:

@article{pipatanakul2023typhoon,
    title={Typhoon: Thai Large Language Models}, 
    author={Kunat Pipatanakul and Phatrasek Jirabovonvisut and Potsawee Manakul and Sittipong Sripaisarnmongkol and Ruangsak Patomwong and Pathomporn Chokchainant and Kasima Tharnpipitchai},
    year={2023},
    journal={arXiv preprint arXiv:2312.13951},
    url={https://arxiv.org/abs/2312.13951}
}

Contact Us

General & Collaboration: kasima@scb10x.com, pathomporn@scb10x.com
Technical: kunat@scb10x.com

Downloads last month: 179

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for RichardErkhov/scb10x_-_typhoon-7b-gguf

Typhoon: Thai Large Language Models

Paper • 2312.13951 • Published Dec 21, 2023 • 7

RichardErkhov
/

scb10x_-_typhoon-7b-gguf