legraphista's picture
Upload README.md with huggingface_hub
0e04a6f verified
|
raw
history blame
5.41 kB
metadata
base_model: deepseek-ai/DeepSeek-V2-Lite
inference: false
library_name: gguf
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - quantized
  - GGUF
  - imatrix
  - quantization
  - imat
  - imatrix
  - static

DeepSeek-V2-Lite-IMat-GGUF

Llama.cpp imatrix quantization of deepseek-ai/DeepSeek-V2-Lite

Original Model: deepseek-ai/DeepSeek-V2-Lite
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp https://github.com/ggerganov/llama.cpp/pull/7519
IMatrix dataset: here

Files

IMatrix

Status: βœ… Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
DeepSeek-V2-Lite.Q8_0.gguf Q8_0 16.70GB βœ… Available βšͺ No πŸ“¦ No
DeepSeek-V2-Lite.Q6_K.gguf Q6_K 14.07GB βœ… Available βšͺ No πŸ“¦ No
DeepSeek-V2-Lite.Q4_K Q4_K - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.Q3_K.gguf Q3_K 8.13GB βœ… Available 🟒 Yes πŸ“¦ No
DeepSeek-V2-Lite.Q2_K Q2_K - ⏳ Processing 🟒 Yes -

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
DeepSeek-V2-Lite.FP16.gguf F16 31.42GB βœ… Available βšͺ No πŸ“¦ No
DeepSeek-V2-Lite.BF16.gguf BF16 31.42GB βœ… Available βšͺ No πŸ“¦ No
DeepSeek-V2-Lite.Q5_K.gguf Q5_K 11.85GB βœ… Available βšͺ No πŸ“¦ No
DeepSeek-V2-Lite.Q5_K_S.gguf Q5_K_S 11.14GB βœ… Available βšͺ No πŸ“¦ No
DeepSeek-V2-Lite.Q4_K_S Q4_K_S - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.Q3_K_L Q3_K_L - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.Q3_K_S Q3_K_S - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.Q2_K_S Q2_K_S - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ4_NL IQ4_NL - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ4_XS IQ4_XS - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ3_M IQ3_M - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ3_S IQ3_S - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ3_XS IQ3_XS - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ3_XXS IQ3_XXS - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ2_M IQ2_M - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ2_S IQ2_S - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ2_XS IQ2_XS - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ2_XXS IQ2_XXS - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ1_M IQ1_M - ⏳ Processing 🟒 Yes -
DeepSeek-V2-Lite.IQ1_S IQ1_S - ⏳ Processing 🟒 Yes -

Downloading using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download legraphista/DeepSeek-V2-Lite-IMat-GGUF --include "DeepSeek-V2-Lite.Q8_0.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download legraphista/DeepSeek-V2-Lite-IMat-GGUF --include "DeepSeek-V2-Lite.Q8_0/*" --local-dir DeepSeek-V2-Lite.Q8_0
# see FAQ for merging GGUF's

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: DeepSeek-V2-Lite.Q8_0)
  3. Run gguf-split --merge DeepSeek-V2-Lite.Q8_0/DeepSeek-V2-Lite.Q8_0-00001-of-XXXXX.gguf DeepSeek-V2-Lite.Q8_0.gguf
    • Make sure to point gguf-split to the first chunk of the split.

Got a suggestion? Ping me @legraphista!