legraphista's picture
Upload README.md with huggingface_hub
f2d9f77 verified
|
raw
history blame
10.5 kB
metadata
base_model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
inference: false
library_name: gguf
license: other
license_link: LICENSE
license_name: deepseek-license
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - quantized
  - GGUF
  - quantization
  - imat
  - imatrix
  - static
  - 16bit
  - 8bit
  - 6bit
  - 5bit
  - 4bit
  - 3bit
  - 2bit
  - 1bit

DeepSeek-Coder-V2-Lite-Instruct-IMat-GGUF

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

Original Model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp b3166
IMatrix dataset: here


Files

IMatrix

Status: ✅ Available
Link: here

Common Quants

Filename Quant type File Size Status Uses IMatrix Is Split
DeepSeek-Coder-V2-Lite-Instruct.Q8_0.gguf Q8_0 16.70GB ✅ Available ⚪ Static 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q6_K.gguf Q6_K 14.07GB ✅ Available ⚪ Static 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q4_K.gguf Q4_K 10.36GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q3_K.gguf Q3_K 8.13GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q2_K.gguf Q2_K 6.43GB ✅ Available 🟢 IMatrix 📦 No

All Quants

Filename Quant type File Size Status Uses IMatrix Is Split
DeepSeek-Coder-V2-Lite-Instruct.BF16.gguf BF16 31.42GB ✅ Available ⚪ Static 📦 No
DeepSeek-Coder-V2-Lite-Instruct.FP16.gguf F16 31.42GB ✅ Available ⚪ Static 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q8_0.gguf Q8_0 16.70GB ✅ Available ⚪ Static 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q6_K.gguf Q6_K 14.07GB ✅ Available ⚪ Static 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q5_K.gguf Q5_K 11.85GB ✅ Available ⚪ Static 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q5_K_S.gguf Q5_K_S 11.14GB ✅ Available ⚪ Static 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q4_K.gguf Q4_K 10.36GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q4_K_S.gguf Q4_K_S 9.53GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.IQ4_NL.gguf IQ4_NL 8.91GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.IQ4_XS.gguf IQ4_XS 8.57GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q3_K.gguf Q3_K 8.13GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q3_K_L.gguf Q3_K_L 8.46GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q3_K_S.gguf Q3_K_S 7.49GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.IQ3_M.gguf IQ3_M 7.55GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.IQ3_S.gguf IQ3_S 7.49GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.IQ3_XS.gguf IQ3_XS 7.12GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.IQ3_XXS.gguf IQ3_XXS 6.96GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q2_K.gguf Q2_K 6.43GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.Q2_K_S.gguf Q2_K_S 6.46GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.IQ2_M.gguf IQ2_M 6.33GB ✅ Available 🟢 IMatrix 📦 No
DeepSeek-Coder-V2-Lite-Instruct.IQ2_S IQ2_S - ⏳ Processing 🟢 IMatrix -
DeepSeek-Coder-V2-Lite-Instruct.IQ2_XS IQ2_XS - ⏳ Processing 🟢 IMatrix -
DeepSeek-Coder-V2-Lite-Instruct.IQ2_XXS IQ2_XXS - ⏳ Processing 🟢 IMatrix -
DeepSeek-Coder-V2-Lite-Instruct.IQ1_M IQ1_M - ⏳ Processing 🟢 IMatrix -
DeepSeek-Coder-V2-Lite-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/DeepSeek-Coder-V2-Lite-Instruct-IMat-GGUF --include "DeepSeek-Coder-V2-Lite-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/DeepSeek-Coder-V2-Lite-Instruct-IMat-GGUF --include "DeepSeek-Coder-V2-Lite-Instruct.Q8_0/*" --local-dir ./
# see FAQ for merging GGUF's

Inference

Simple chat template

<|begin▁of▁sentence|>User: {user_prompt}

Assistant: {assistant_response}<|end▁of▁sentence|>User: {next_user_prompt}

Chat template with system prompt

<|begin▁of▁sentence|>{system_prompt}

User: {user_prompt}

Assistant: {assistant_response}<|end▁of▁sentence|>User: {next_user_prompt}

Llama.cpp

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

Got a suggestion? Ping me @legraphista!