pek111/llama-3-typhoon-v1.5-8b-instruct-GGUF

Llama 3 Typhoon v1.5 8B Instruct - GGUF

Description

This repo contains GGUF format model files for SCB 10X's Llama 3 Typhoon v1.5 8B Instruct.

You can jump to downloads.

About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st, 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenization, and support for special tokens. It also supports metadata and is designed to be extensible.

Here is an incomplete list of clients and libraries that are known to support GGUF:

• llama.cpp. The source project for GGUF. Offers a CLI and a server option.
• text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
• KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for storytelling.
• LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
• LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
• Faraday.dev, an attractive and easy-to-use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
• llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
• candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.

Prompt template

Llama 3 chat template

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

You are a helpful assistant who're always speak Thai.<|eot_id|><|start_header_id|>user<|end_header_id|>

1+1 เท่ากับเท่าไหร่<|eot_id|><|start_header_id|>assistant<|end_header_id|>

1+1 เท่ากับ 2 ครับ<|eot_id|>

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d36d5be95a0d9088b674dbb27354107221

They are also compatible with many third-party UIs and libraries - please see the list at the top of this README.

Explanation of quantization methods

Click to see details

The new methods available are:

• GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
• GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This ends up using 3.4375 bpw.
• GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
• GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
• GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw

Refer to the Provided Files table below to see what files use which methods, and how.

Provided files

Name	Quant method	Bits	Size	Use case
llama-3-typhoon-v1.5-8b-instruct.Q2_K.gguf	Q2_K	2	2.95 GB	smallest, significant quality loss - not recommended for most purposes
llama-3-typhoon-v1.5-8b-instruct.Q3_K_S.gguf	Q3_K_S	3	3.41 GB	very small, high quality loss
llama-3-typhoon-v1.5-8b-instruct.Q3_K_M.gguf	Q3_K_M	3	3.74 GB	very small, high quality loss
llama-3-typhoon-v1.5-8b-instruct.Q3_K_L.gguf	Q3_K_L	3	4.02 GB	small, substantial quality loss
llama-3-typhoon-v1.5-8b-instruct.Q4_0.gguf	Q4_0	4	4.34 GB	legacy; small, very high quality loss - prefer using Q3_K_M
llama-3-typhoon-v1.5-8b-instruct.Q4_K_S.gguf	Q4_K_S	4	4.37 GB	small, greater quality loss
llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf	Q4_K_M	4	4.58 GB	medium, balanced quality - recommended
llama-3-typhoon-v1.5-8b-instruct.Q5_0.gguf	Q5_0	5	5.21 GB	legacy; medium, balanced quality - prefer using Q4_K_M
llama-3-typhoon-v1.5-8b-instruct.Q5_K_S.gguf	Q5_K_S	5	5.21 GB	large, low quality loss - recommended
llama-3-typhoon-v1.5-8b-instruct.Q5_K_M.gguf	Q5_K_M	5	5.33 GB	large, very low quality loss - recommended
llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf	Q6_K	6	6.14 GB	very large, extremely low quality loss
llama-3-typhoon-v1.5-8b-instruct.Q8_0.gguf	Q8_0	8	7.95 GB	very large, extremely low quality loss - not recommended
llama-3-typhoon-v1.5-8b-instruct.BF16.gguf	BF16	16	14.97 GB	largest, original quality - not recommended

How to download GGUF files

Note for manual downloaders: You rarely want to clone the entire repo! Multiple different quantization formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

• LM Studio
• LoLLMS Web UI
• Faraday.dev

In text-generation-webui

Under Download Model, you can enter the model repo: pek111/llama-3-typhoon-v1.5-8b-instruct-GGUF, and below it, a specific filename to download, such as tc-instruct-dpo.Q4_K_M.gguf.

Then click Download.

On the command line, including multiple files at once

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub>=0.17.1

Then you can download any individual model file to the current directory, at high speed, with a command like this:

huggingface-cli download pek111/llama-3-typhoon-v1.5-8b-instruct-GGUF llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

More advanced huggingface-cli download usage

You can also download multiple files at once with a pattern:

huggingface-cli download pek111/llama-3-typhoon-v1.5-8b-instruct-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'

For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download pek111/llama-3-typhoon-v1.5-8b-instruct-GGUF llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

Windows CLI users: Use set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 or $env:HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 before running the download command.

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d36d5be95a0d9088b674dbb27354107221 or later.

./main -ngl 32 -m tc-instruct-dpo.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change -c 4096 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

For other parameters and how to use them, please refer to the llama.cpp documentation

How to run in text-generation-webui

Further instructions here: text-generation-webui/docs/llama.cpp.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.

How to load this model from Python using ctransformers

First install the package

# Base llama-cpp-python with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python

# In Windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for Nvidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_CUDA=on"
pip install llama_cpp_python --verbose
# If BLAS = 0 try installing with these commands instead (Windows + CUDA)
set CMAKE_ARGS="-DLLAMA_CUDA=on"
set FORCE_CMAKE=1
$env:CMAKE_ARGS = "-DLLAMA_CUDA=on"
$env:FORCE_CMAKE = 1
python -m pip install llama_cpp_python>=0.2.26 --verbose --force-reinstall --no-cache-dir

Simple example code to load one of these GGUF models

import llama_cpp

llm_cpp = llama_cpp.Llama(
    model_path="models/llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf",  # Path to the model
    n_threads=10,  # CPU cores
    n_batch=512,  # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
    n_gpu_layers=33,  # Change this value based on your model and your GPU VRAM pool.
    n_ctx=2048,  # Max context length
)

prompt = """
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

You are a helpful assistant who're always speak Thai.<|eot_id|><|start_header_id|>user<|end_header_id|>

1+1 เท่ากับเท่าไหร่<|eot_id|><|start_header_id|>assistant<|end_header_id|>

"""

response = llm_cpp(
    prompt=prompt,
    max_tokens=256,
    temperature=0.5,
    top_k=1,
    repeat_penalty=1.1,
    echo=True
)

print(response)

Output

{
    "id": "cmpl-b0971ce1-1607-42b3-b6dd-8bf8e324307a",
    "object": "text_completion",
    "created": 1721478196,
    "model": "models/llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf",
    "choices": [
        {
            "text": "\n<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant who're always speak Thai.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n1+1 เท่ากับเท่าไหร่<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n2",
            "index": 0,
            "logprobs": None,
            "finish_reason": "stop",
        }
    ],
    "usage": {"prompt_tokens": 41, "completion_tokens": 2, "total_tokens": 43},
}

How to use with LangChain

Here are guides on using llama-cpp-python or ctransformers with LangChain:

• LangChain + llama-cpp-python
• LangChain + ctransformers

Original model card: SCB 10X's Llama 3 Typhoon v1.5 8B Instruct

Llama-3-Typhoon-1.5-8B: Thai Large Language Model (Instruct)

Llama-3-Typhoon-1.5-8B-instruct is a instruct Thai 🇹🇭 large language model with 8 billion parameters, and it is based on Llama3-8B.

For release post, please see our blog. *To acknowledge Meta's effort in creating the foundation model and to comply with the license, we explicitly include "llama-3" in the model name.

Model Description

• Model type: A 8B instruct decoder-only model based on Llama architecture.
• Requirement: transformers 4.38.0 or newer.
• Primary Language(s): Thai 🇹🇭 and English 🇬🇧
• License: Llama 3 Community License

Performance

Model	ONET	IC	TGAT	TPAT-1	A-Level	Average (ThaiExam)	M3Exam	MMLU
Typhoon-1.0 (Mistral)	0.379	0.393	0.700	0.414	0.324	0.442	0.391	0.547
Typhoon-1.5 8B (Llama3)	0.446	0.431	0.722	0.526	0.407	0.506	0.460	0.614
Sailor 7B	0.372	0.379	0.678	0.405	0.396	0.446	0.411	0.553
SeaLLM 2.0 7B	0.327	0.311	0.656	0.414	0.321	0.406	0.354	0.579
OpenThaiGPT 1.0.0 7B	0.238	0.249	0.444	0.319	0.289	0.308	0.268	0.369
SambaLingo-Thai-Chat 7B	0.251	0.241	0.522	0.302	0.262	0.316	0.309	0.388

Usage Example

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "scb10x/llama-3-typhoon-v1.5-8b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a helpful assistant who're always speak Thai."},
    {"role": "user", "content": "ขอสูตรไก่ย่าง"},
]

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=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Chat Template

We use llama3 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 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

https://discord.gg/CqyBscMFpg

SCB10X AI Team

• Kunat Pipatanakul, Potsawee Manakul, Sittipong Sripaisarnmongkol, Natapong Nitarach, Pathomporn Chokchainant, Kasima Tharnpipitchai
• If you find Typhoon-8B 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: [email protected], [email protected]
• Technical: [email protected]