legraphista's picture
Upload README.md with huggingface_hub
a458d06 verified
|
raw
history blame
9.9 kB
metadata
base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
inference: false
language:
  - en
library_name: gguf
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - chat
  - quantized
  - GGUF
  - quantization
  - imat
  - imatrix
  - static
  - 16bit
  - 8bit
  - 6bit
  - 5bit
  - 4bit
  - 3bit
  - 2bit
  - 1bit

Qwen2.5-Math-1.5B-Instruct-IMat-GGUF

Llama.cpp imatrix quantization of Qwen/Qwen2.5-Math-1.5B-Instruct

Original Model: Qwen/Qwen2.5-Math-1.5B-Instruct
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3787
IMatrix dataset: here


Files

IMatrix

Status: βœ… Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Qwen2.5-Math-1.5B-Instruct.Q8_0.gguf Q8_0 1.65GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q6_K.gguf Q6_K 1.27GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q4_K.gguf Q4_K 986.05MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q3_K.gguf Q3_K 824.18MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q2_K.gguf Q2_K 676.31MB βœ… Available 🟒 IMatrix πŸ“¦ No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
Qwen2.5-Math-1.5B-Instruct.BF16.gguf BF16 3.09GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.FP16.gguf F16 3.09GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q8_0.gguf Q8_0 1.65GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q6_K.gguf Q6_K 1.27GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q5_K.gguf Q5_K 1.13GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q5_K_S.gguf Q5_K_S 1.10GB βœ… Available βšͺ Static πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q4_K.gguf Q4_K 986.05MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q4_K_S.gguf Q4_K_S 940.31MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.IQ4_NL.gguf IQ4_NL 936.33MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.IQ4_XS.gguf IQ4_XS 895.73MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q3_K.gguf Q3_K 824.18MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q3_K_L.gguf Q3_K_L 880.16MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q3_K_S.gguf Q3_K_S 760.94MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.IQ3_M.gguf IQ3_M 776.66MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.IQ3_S.gguf IQ3_S 762.41MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.IQ3_XS.gguf IQ3_XS 731.70MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.IQ3_XXS IQ3_XXS - ⏳ Processing 🟒 IMatrix -
Qwen2.5-Math-1.5B-Instruct.Q2_K.gguf Q2_K 676.31MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.Q2_K_S.gguf Q2_K_S 640.14MB βœ… Available 🟒 IMatrix πŸ“¦ No
Qwen2.5-Math-1.5B-Instruct.IQ2_M IQ2_M - ⏳ Processing 🟒 IMatrix -
Qwen2.5-Math-1.5B-Instruct.IQ2_S IQ2_S - ⏳ Processing 🟒 IMatrix -
Qwen2.5-Math-1.5B-Instruct.IQ2_XS IQ2_XS - ⏳ Processing 🟒 IMatrix -
Qwen2.5-Math-1.5B-Instruct.IQ2_XXS IQ2_XXS - ⏳ Processing 🟒 IMatrix -
Qwen2.5-Math-1.5B-Instruct.IQ1_M IQ1_M - ⏳ Processing 🟒 IMatrix -
Qwen2.5-Math-1.5B-Instruct.IQ1_S IQ1_S - ⏳ Processing 🟒 IMatrix -

Downloading using huggingface-cli

If you do not have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Download the specific file you want:

huggingface-cli download legraphista/Qwen2.5-Math-1.5B-Instruct-IMat-GGUF --include "Qwen2.5-Math-1.5B-Instruct.Q8_0.gguf" --local-dir ./

If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download legraphista/Qwen2.5-Math-1.5B-Instruct-IMat-GGUF --include "Qwen2.5-Math-1.5B-Instruct.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's

Inference

Simple chat template

<|im_start|>system
Please reason step by step, and put your final answer within \boxed{}.<|im_end|>
<|im_start|>user
{user_prompt}<|im_end|>
<|im_start|>assistant
{assistant_response}<|im_end|>
<|im_start|>user
{next_user_prompt}<|im_end|>

Chat template with system prompt

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{user_prompt}<|im_end|>
<|im_start|>assistant
{assistant_response}<|im_end|>
<|im_start|>user
{next_user_prompt}<|im_end|>

Llama.cpp

llama.cpp/main -m Qwen2.5-Math-1.5B-Instruct.Q8_0.gguf --color -i -p "prompt here (according to the chat template)"

FAQ

Why is the IMatrix not applied everywhere?

According to this investigation, it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results).

How do I merge a split GGUF?

  1. Make sure you have gguf-split available
  2. Locate your GGUF chunks folder (ex: Qwen2.5-Math-1.5B-Instruct.Q8_0)
  3. Run gguf-split --merge Qwen2.5-Math-1.5B-Instruct.Q8_0/Qwen2.5-Math-1.5B-Instruct.Q8_0-00001-of-XXXXX.gguf Qwen2.5-Math-1.5B-Instruct.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!