RichardErkhov/scb10x_-_typhoon-v1.5-72b-instruct-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

typhoon-v1.5-72b-instruct - GGUF

• Model creator: https://huggingface.co/scb10x/
• Original model: https://huggingface.co/scb10x/typhoon-v1.5-72b-instruct/

Name	Quant method	Size
typhoon-v1.5-72b-instruct.Q2_K.gguf	Q2_K	26.51GB
typhoon-v1.5-72b-instruct.IQ3_XS.gguf	IQ3_XS	27.87GB
typhoon-v1.5-72b-instruct.IQ3_S.gguf	IQ3_S	29.4GB
typhoon-v1.5-72b-instruct.Q3_K_S.gguf	Q3_K_S	30.69GB
typhoon-v1.5-72b-instruct.IQ3_M.gguf	IQ3_M	31.6GB
typhoon-v1.5-72b-instruct.Q3_K.gguf	Q3_K	33.46GB
typhoon-v1.5-72b-instruct.Q3_K_M.gguf	Q3_K_M	14.94GB
typhoon-v1.5-72b-instruct.Q3_K_L.gguf	Q3_K_L	35.84GB
typhoon-v1.5-72b-instruct.IQ4_XS.gguf	IQ4_XS	36.41GB
typhoon-v1.5-72b-instruct.Q4_0.gguf	Q4_0	38.18GB
typhoon-v1.5-72b-instruct.IQ4_NL.gguf	IQ4_NL	38.42GB
typhoon-v1.5-72b-instruct.Q4_K_S.gguf	Q4_K_S	39.04GB
typhoon-v1.5-72b-instruct.Q4_K.gguf	Q4_K	41.08GB
typhoon-v1.5-72b-instruct.Q4_K_M.gguf	Q4_K_M	41.08GB
typhoon-v1.5-72b-instruct.Q4_1.gguf	Q4_1	42.32GB
typhoon-v1.5-72b-instruct.Q5_0.gguf	Q5_0	46.45GB
typhoon-v1.5-72b-instruct.Q5_K_S.gguf	Q5_K_S	46.45GB
typhoon-v1.5-72b-instruct.Q5_K.gguf	Q5_K	47.78GB
typhoon-v1.5-72b-instruct.Q5_K_M.gguf	Q5_K_M	47.78GB
typhoon-v1.5-72b-instruct.Q5_1.gguf	Q5_1	50.59GB
typhoon-v1.5-72b-instruct.Q6_K.gguf	Q6_K	55.24GB
typhoon-v1.5-72b-instruct.Q8_0.gguf	Q8_0	71.55GB

Original model description:

license: other license_name: tongyi-qianwen license_link: https://huggingface.co/Qwen/Qwen1.5-72B/blob/main/LICENSE language: - th - en pipeline_tag: text-generation

Typhoon-1.5-72B-instruct: Thai Large Language Model (Instruct)

Typhoon-1.5-72B-instruct is a instruct Thai 🇹🇭 large language model with 72 billion parameters, and it is based on Qwen1.5-72B.

We also have a newer release of 1.5x 70B, which is better for application use cases. here

For release post, please see our blog.

Model Description

• Model type: A 72B instruct decoder-only model based on Qwen1.5 archtecture.
• Requirement: transformers 4.38.0 or newer.
• Primary Language(s): Thai 🇹🇭 and English 🇬🇧
• License: Qwen License

Performance

Model	ONET	IC	TGAT	TPAT-1	A-Level	Average (ThaiExam)	M3Exam	MMLU
Typhoon-1.5 72B	0.562	0.716	0.778	0.5	0.528	0.6168	0.587	0.7271
OpenThaiGPT 1.0.0 70B	0.447	0.492	0.778	0.5	0.319	0.5072	0.493	0.6167
GPT-3.5-turbo(01-2024)	0.358	0.279	0.678	0.345	0.318	0.3956	0.316	0.700**
GPT-4(04-2024)	0.589	0.594	0.756	0.517	0.616	0.6144	0.626	0.864**
** We report the MMLU score that is reported in GPT-4 Tech Report.

Usage Example

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "scb10x/typhoon-v1.5-72b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
) # We do not recommend loading the model using 4-bit and 8-bit BNB as it may produce inaccurate results.

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "ขอสูตรไก่ย่าง"},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=1024,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
    repetition_penalty=1.15
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Chat Template

We use chatml chat-template.

{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}
{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}

Intended Uses & Limitations

This model is an instructional model. However, it’s still undergoing development. It incorporates some level of guardrails, but it still may produce answers that are inaccurate, biased, or otherwise objectionable in response to user prompts. We recommend that developers assess these risks in the context of their use case.

Follow us

https://twitter.com/opentyphoon

Support / Ask any question

https://discord.gg/CqyBscMFpg

SCB10X AI Team

• Kunat Pipatanakul, Potsawee Manakul, Sittipong Sripaisarnmongkol, Natapong Nitarach, Pathomporn Chokchainant, Kasima Tharnpipitchai
• If you find Typhoon v1.5 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