From 402c777ecb86565bf4765c5ba051f9e8416c4156 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 4 Jun 2026 05:48:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf Source: Original Platform --- .gitattributes | 57 +++++++ README.md | 164 +++++++++++++++++++ llama-3-typhoon-v1.5-8b-instruct.IQ3_M.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.IQ3_S.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.IQ3_XS.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.IQ4_NL.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.IQ4_XS.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q2_K.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q3_K.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q3_K_L.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q3_K_M.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q3_K_S.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q4_0.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q4_1.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q4_K.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q4_K_S.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q5_0.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q5_1.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q5_K.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q5_K_M.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q5_K_S.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf | 3 + llama-3-typhoon-v1.5-8b-instruct.Q8_0.gguf | 3 + 24 files changed, 287 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 llama-3-typhoon-v1.5-8b-instruct.IQ3_M.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.IQ3_S.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.IQ3_XS.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.IQ4_NL.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.IQ4_XS.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q2_K.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q3_K.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q3_K_L.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q3_K_M.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q3_K_S.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q4_0.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q4_1.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q4_K.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q4_K_S.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q5_0.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q5_1.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q5_K.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q5_K_M.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q5_K_S.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf create mode 100644 llama-3-typhoon-v1.5-8b-instruct.Q8_0.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..efb601d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-typhoon-v1.5-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..24ec6a2 --- /dev/null +++ b/README.md @@ -0,0 +1,164 @@ +Quantization made by Richard Erkhov. + +[Github](https://github.com/RichardErkhov) + +[Discord](https://discord.gg/pvy7H8DZMG) + +[Request more models](https://github.com/RichardErkhov/quant_request) + + +llama-3-typhoon-v1.5-8b-instruct - GGUF +- Model creator: https://huggingface.co/scb10x/ +- Original model: https://huggingface.co/scb10x/llama-3-typhoon-v1.5-8b-instruct/ + + +| Name | Quant method | Size | +| ---- | ---- | ---- | +| [llama-3-typhoon-v1.5-8b-instruct.Q2_K.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q2_K.gguf) | Q2_K | 2.96GB | +| [llama-3-typhoon-v1.5-8b-instruct.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.IQ3_XS.gguf) | IQ3_XS | 3.28GB | +| [llama-3-typhoon-v1.5-8b-instruct.IQ3_S.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.IQ3_S.gguf) | IQ3_S | 3.43GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.41GB | +| [llama-3-typhoon-v1.5-8b-instruct.IQ3_M.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.IQ3_M.gguf) | IQ3_M | 3.52GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q3_K.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q3_K.gguf) | Q3_K | 3.74GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 3.74GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 4.03GB | +| [llama-3-typhoon-v1.5-8b-instruct.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 4.18GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q4_0.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q4_0.gguf) | Q4_0 | 4.34GB | +| [llama-3-typhoon-v1.5-8b-instruct.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.IQ4_NL.gguf) | IQ4_NL | 4.38GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.37GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q4_K.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q4_K.gguf) | Q4_K | 4.58GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 4.58GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q4_1.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q4_1.gguf) | Q4_1 | 4.78GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q5_0.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q5_0.gguf) | Q5_0 | 5.21GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 5.21GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q5_K.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q5_K.gguf) | Q5_K | 5.34GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 5.34GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q5_1.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q5_1.gguf) | Q5_1 | 5.65GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf) | Q6_K | 6.14GB | +| [llama-3-typhoon-v1.5-8b-instruct.Q8_0.gguf](https://huggingface.co/RichardErkhov/scb10x_-_llama-3-typhoon-v1.5-8b-instruct-gguf/blob/main/llama-3-typhoon-v1.5-8b-instruct.Q8_0.gguf) | Q8_0 | 7.95GB | + + + + +Original model description: +--- +license: llama3 +language: +- en +- th +pipeline_tag: text-generation +tags: +- instruct +- chat +--- +**Llama-3-Typhoon-v1.5-8B: Thai Large Language Model (Instruct)** + +**Llama-3-Typhoon-v1.5-8B-instruct** is a *instruct* Thai 🇹🇭 large language model with 8 billion parameters, and it is based on Llama3-8B. + +![Typhoon 1.5 8b benchmark](https://storage.googleapis.com/typhoon-public/assets/1.5-8b-benchmark.png) + +For release post, please see our [blog](https://blog.opentyphoon.ai/typhoon-1-5-release-a9364cb8e8d7). +*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](https://llama.meta.com/llama3/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 + +```python +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. + +```python +{% 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: **[kasima@scb10x.com](mailto:kasima@scb10x.com)**, **[pathomporn@scb10x.com](mailto:pathomporn@scb10x.com)** +- Technical: **[kunat@scb10x.com](mailto:kunat@scb10x.com)** + diff --git a/llama-3-typhoon-v1.5-8b-instruct.IQ3_M.gguf b/llama-3-typhoon-v1.5-8b-instruct.IQ3_M.gguf new file mode 100644 index 0000000..4254a19 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89e2852501fc0087d4c09b50efb2dc655ab6423b3ed617704b73abcf1385f9d4 +size 3784823136 diff --git a/llama-3-typhoon-v1.5-8b-instruct.IQ3_S.gguf b/llama-3-typhoon-v1.5-8b-instruct.IQ3_S.gguf new file mode 100644 index 0000000..6892ffc --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd2525174bc32f093420d0716503931f670735469fec3eea40705bb0e91532f +size 3682324832 diff --git a/llama-3-typhoon-v1.5-8b-instruct.IQ3_XS.gguf b/llama-3-typhoon-v1.5-8b-instruct.IQ3_XS.gguf new file mode 100644 index 0000000..d6e9cc7 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d267d716110da6a0f132444511600bc8c0cfb0ff013f16994bd758ac7ad303ae +size 3518746976 diff --git a/llama-3-typhoon-v1.5-8b-instruct.IQ4_NL.gguf b/llama-3-typhoon-v1.5-8b-instruct.IQ4_NL.gguf new file mode 100644 index 0000000..bdb3455 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c02d714c662670cfb44af6f7049acac7b003fba9424d3b6fa1b33dec6117d3b +size 4707348832 diff --git a/llama-3-typhoon-v1.5-8b-instruct.IQ4_XS.gguf b/llama-3-typhoon-v1.5-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..a6fa628 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38852716df8202a7bf8be6ce35605ea21f19f9f4f11ce0f330017890b6182398 +size 4484362592 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q2_K.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..dc1b1b6 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e11b415f2237977aa1cbb04f99be17c3a42254255a664b959ee87828419f12d6 +size 3179131232 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q3_K.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q3_K.gguf new file mode 100644 index 0000000..b633fa4 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q3_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9792aae47ed88d5a238985288453d9aed4dc77ec1e6a69c977172c7f3243a846 +size 4018917728 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q3_K_L.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..a470e5e --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f76e11f018ba2af2a89d68691d638c506a2a0d57252bbb370fc78b404990878 +size 4321956192 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q3_K_M.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b633fa4 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9792aae47ed88d5a238985288453d9aed4dc77ec1e6a69c977172c7f3243a846 +size 4018917728 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q3_K_S.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..18fc873 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88854332b777237c5a4ba9943e54ca9408c13e2b654260b59ceaefcfa47d4092 +size 3664499040 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q4_0.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q4_0.gguf new file mode 100644 index 0000000..e01c2df --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d6225a067a46557657ca4db77ed289fc676104721d4e0f7a9510e0851ba77a3 +size 4661211488 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q4_1.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q4_1.gguf new file mode 100644 index 0000000..8bb3515 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:099b98182a1aa944945b8ada2570208edee793f2545ab9a92984de1956ef8c08 +size 5130252640 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q4_K.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q4_K.gguf new file mode 100644 index 0000000..419179e --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:573063997782f07d7d0776c44a5438c7bad0511a93e03fabe4ebb8bfe6724954 +size 4920734048 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..419179e --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:573063997782f07d7d0776c44a5438c7bad0511a93e03fabe4ebb8bfe6724954 +size 4920734048 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q4_K_S.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..0f13466 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836977e7a9491950aff7121ca5ded0133eb00e2fa2e26e38d4cafd6f0c63977d +size 4692668768 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q5_0.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q5_0.gguf new file mode 100644 index 0000000..8a2cb6c --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bd8766c2a9d3e13e9aabeb8c41b43161cf69b083d7b67b83cc50f4769e42b75 +size 5599293792 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q5_1.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q5_1.gguf new file mode 100644 index 0000000..ad12ba7 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1851d323e6e24dbc368bd8a3b758d02b1d615c1f48c25fa60d1bd0d4937b34d +size 6068334944 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q5_K.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q5_K.gguf new file mode 100644 index 0000000..4807312 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c9c08eb2a3be85ec98dc5eedc4ba06d8fde2606b4b62ad4af2f4be225d72df +size 5732987232 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q5_K_M.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..4807312 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c9c08eb2a3be85ec98dc5eedc4ba06d8fde2606b4b62ad4af2f4be225d72df +size 5732987232 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q5_K_S.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..9067583 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ead60d404070d0353b65012f9c6d818b6439155b920173d8623b6a38d57985 +size 5599293792 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..04646c7 --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10848a253df4161a03cb5951e421e47ba5b711fad62861ef3e850254c24feeca +size 6596006240 diff --git a/llama-3-typhoon-v1.5-8b-instruct.Q8_0.gguf b/llama-3-typhoon-v1.5-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..de244fa --- /dev/null +++ b/llama-3-typhoon-v1.5-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:716ead1f3a98d4e2dba3a2627bfb957ebb601a68bc648843063fc579efcbed72 +size 8540770656