Hugging Face's logo

RichardErkhov
/
scb10x_-_llama-3-typhoon-v1.5x-70b-instruct-gguf

GGUF
conversational
Model card Files
xet
 Community

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

llama-3-typhoon-v1.5x-70b-instruct - GGUF

Name Quant method Size
llama-3-typhoon-v1.5x-70b-instruct.Q2_K.gguf Q2_K 24.56GB
llama-3-typhoon-v1.5x-70b-instruct.IQ3_XS.gguf IQ3_XS 27.29GB
llama-3-typhoon-v1.5x-70b-instruct.IQ3_S.gguf IQ3_S 28.79GB
llama-3-typhoon-v1.5x-70b-instruct.Q3_K_S.gguf Q3_K_S 28.79GB
llama-3-typhoon-v1.5x-70b-instruct.IQ3_M.gguf IQ3_M 29.74GB
llama-3-typhoon-v1.5x-70b-instruct.Q3_K.gguf Q3_K 31.91GB
llama-3-typhoon-v1.5x-70b-instruct.Q3_K_M.gguf Q3_K_M 31.91GB
llama-3-typhoon-v1.5x-70b-instruct.Q3_K_L.gguf Q3_K_L 34.59GB
llama-3-typhoon-v1.5x-70b-instruct.IQ4_XS.gguf IQ4_XS 35.64GB
llama-3-typhoon-v1.5x-70b-instruct.Q4_0.gguf Q4_0 37.22GB
llama-3-typhoon-v1.5x-70b-instruct.IQ4_NL.gguf IQ4_NL 37.58GB
llama-3-typhoon-v1.5x-70b-instruct.Q4_K_S.gguf Q4_K_S 37.58GB
llama-3-typhoon-v1.5x-70b-instruct.Q4_K.gguf Q4_K 39.6GB
llama-3-typhoon-v1.5x-70b-instruct.Q4_K_M.gguf Q4_K_M 39.6GB
llama-3-typhoon-v1.5x-70b-instruct.Q4_1.gguf Q4_1 41.27GB
llama-3-typhoon-v1.5x-70b-instruct.Q5_0.gguf Q5_0 45.32GB
llama-3-typhoon-v1.5x-70b-instruct.Q5_K_S.gguf Q5_K_S 45.32GB
llama-3-typhoon-v1.5x-70b-instruct.Q5_K.gguf Q5_K 46.52GB
llama-3-typhoon-v1.5x-70b-instruct.Q5_K_M.gguf Q5_K_M 46.52GB
llama-3-typhoon-v1.5x-70b-instruct.Q5_1.gguf Q5_1 49.36GB
llama-3-typhoon-v1.5x-70b-instruct.Q6_K.gguf Q6_K 53.91GB
llama-3-typhoon-v1.5x-70b-instruct.Q8_0.gguf Q8_0 69.83GB

Original model description:

language: - th - en pipeline_tag: text-generation license: llama3

Llama-3-Typhoon-1.5X-70B-instruct: Thai Large Language Model (Instruct)

Llama-3-Typhoon-1.5X-70B-instruct is a 70 billion parameter instruct model designed for Thai 🇹🇭 language. It demonstrates competitive performance with GPT-4-0612, and is optimized for application use cases, Retrieval-Augmented Generation (RAG), constrained generation, and reasoning tasks.

Built on Typhoon 1.5 70B (not yet released) and Llama 3 70B Instruct. this model is a result of our experiment on cross-lingual transfer. It utilizes the task-arithmetic model editing technique, combining the Thai understanding capability of Typhoon with the human alignment performance of Llama 3 Instruct.

Remark: To acknowledge Meta's efforts in creating the foundation model and comply with the license, we explicitly include "llama-3" in the model name.

Model Description

  • Model type: A 70B instruct decoder-only model based on the Llama architecture
  • Requirement: Transformers 4.38.0 or newer
  • Primary Language(s): Thai 🇹🇭 and English 🇬🇧
  • License: Llama 3 Community License

Performance

We evaluated the model's performance in Language & Knowledge Capabilities and Instruction Following Capabilities.

  • Language & Knowledge Capabilities:
    • Assessed using multiple-choice question-answering datasets such as ThaiExam and MMLU.
  • Instruction Following Capabilities:
    • Evaluated based on beta users' feedback, focusing on two factors:
      • Human Alignment & Reasoning: Ability to generate responses that are clear and logically structured across multiple steps.
        • Evaluated using MT-Bench — How LLMs can align with human needs.
      • Instruction-following: Ability to adhere to specified constraints in the instructions.
        • Evaluated using IFEval — How LLMs can follow specified constraints, such as formatting and brevity.
  • Agentic Capabilities:

Remark: We developed the Thai (TH) pairs by translating the original datasets into Thai through machine and human methods.

ThaiExam

Model ONET IC TGAT TPAT-1 A-Level Average (ThaiExam) MMLU
Typhoon-1.5X 70B 0.565 0.68 0.778 0.517 0.56 0.620 0.7945
gpt-4-0612 0.493 0.69 0.744 0.509 0.616 0.610 0.864**
--- --- --- --- --- --- --- ---
gpt-4o 0.62 0.63 0.789 0.56 0.623 0.644 0.887**

** We report the MMLU score that is reported in GPT-4o Tech Report.

MT-Bench

Model MT-Bench Thai MT-Bench English
Typhoon-1.5X 70B 8.029 8.797
gpt-4-0612 7.801 8.671
--- --- ---
gpt-4o 8.514 9.184

IFEval

Model IFEval Thai IFEval English
Typhoon-1.5X 70B 0.645 0.810
gpt-4-0612 0.612 0.793*
--- --- ---
gpt-4o 0.737 0.871
  • We report the number from IFEval paper.

Agent

Model GAIA - Thai/English GSM8K - Thai/English HotpotQA - Thai/English
gpt-3.5-turbo-0125 18.42/37.5 70/80 39.56/59
Typhoon-1.5X 70B 17.10/36.25 80/95 52.7/65.83
gpt-4-0612 17.10/38.75 90/100 56.41/76.25
--- --- --- ---
gpt-4o 44.73/57.5 100/100 71.64/76.58

Insight

We utilized model editing techniques and found that the most critical feature for generating accurate Thai answers is located in the backend (the upper layers of the transformer block). Accordingly, we incorporated a high ratio of Typhoon components in these backend layers to enhance our model’s performance.

Usage Example 

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "scb10x/llama-3-typhoon-v1.5x-70b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
) # We don't recommend using BNB 4-bit (load_in_4bit) here. Instead, use AWQ, as detailed here: https://huggingface.co/scb10x/llama-3-typhoon-v1.5x-70b-instruct-awq.

messages = [...] # add message here

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

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=512,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.4,
    top_p=0.95,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Chat Template

We use the Llama 3 chat template.

{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}

Intended Uses & Limitations

This model is experimental and might not be fully evaluated for all use cases. Developers should assess risks in the context of their specific applications.

Follow us

https://twitter.com/opentyphoon

Support

https://discord.gg/CqyBscMFpg

SCB 10X Typhoon Team

  • Kunat Pipatanakul, Potsawee Manakul, Sittipong Sripaisarnmongkol, Natapong Nitarach, Pathomporn Chokchainant, Kasima Tharnpipitchai
  • If you find Typhoon-1.5X 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

Downloads last month
131
GGUF
Model size
71B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

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

Papers for RichardErkhov/scb10x_-_llama-3-typhoon-v1.5x-70b-instruct-gguf