README.md

metadata

base_model: deepseek-ai/DeepSeek-V2-Lite-Chat
inference: false
library_name: gguf
pipeline_tag: text-generation
quantized_by: legraphista
tags:
  - quantized
  - GGUF
  - imatrix
  - quantization
  - imat
  - imatrix
  - static

DeepSeek-V2-Lite-Chat-IMat-GGUF

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

Original Model: deepseek-ai/DeepSeek-V2-Lite-Chat
Original dtype: BF16 (bfloat16)
Quantized by: llama.cpp https://github.com/fairydreaming/llama.cpp/tree/deepseek-v2
IMatrix dataset: here

Files

IMatrix

Status: ⏳ Processing
Link: here

Common Quants

Filename	Quant type	File Size	Status	Uses IMatrix	Is Split
DeepSeek-V2-Lite-Chat.Q8_0.gguf	Q8_0	16.70GB	✅ Available	⚪ No	📦 No
DeepSeek-V2-Lite-Chat.Q6_K.gguf	Q6_K	14.07GB	✅ Available	⚪ No	📦 No
DeepSeek-V2-Lite-Chat.Q4_K	Q4_K	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.Q3_K	Q3_K	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.Q2_K	Q2_K	-	⏳ Processing	🟢 Yes	-

All Quants

Filename	Quant type	File Size	Status	Uses IMatrix	Is Split
DeepSeek-V2-Lite-Chat.FP16.gguf	F16	31.42GB	✅ Available	⚪ No	📦 No
DeepSeek-V2-Lite-Chat.BF16	BF16	-	⏳ Processing	⚪ No	-
DeepSeek-V2-Lite-Chat.Q5_K.gguf	Q5_K	11.85GB	✅ Available	⚪ No	📦 No
DeepSeek-V2-Lite-Chat.Q5_K_S.gguf	Q5_K_S	11.14GB	✅ Available	⚪ No	📦 No
DeepSeek-V2-Lite-Chat.Q4_K_S	Q4_K_S	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.Q3_K_L	Q3_K_L	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.Q3_K_S	Q3_K_S	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.Q2_K_S	Q2_K_S	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ4_NL	IQ4_NL	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ4_XS	IQ4_XS	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ3_M	IQ3_M	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ3_S	IQ3_S	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ3_XS	IQ3_XS	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ3_XXS	IQ3_XXS	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ2_M	IQ2_M	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ2_S	IQ2_S	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ2_XS	IQ2_XS	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ2_XXS	IQ2_XXS	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.IQ1_M	IQ1_M	-	⏳ Processing	🟢 Yes	-
DeepSeek-V2-Lite-Chat.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-Chat-IMat-GGUF --include "DeepSeek-V2-Lite-Chat.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-Chat-IMat-GGUF --include "DeepSeek-V2-Lite-Chat.Q8_0/*" --local-dir DeepSeek-V2-Lite-Chat.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
   • To get hold of gguf-split, navigate to https://github.com/ggerganov/llama.cpp/releases
   • Download the appropriate zip for your system from the latest release
   • Unzip the archive and you should be able to find gguf-split
2. Locate your GGUF chunks folder (ex: DeepSeek-V2-Lite-Chat.Q8_0)
3. Run gguf-split --merge DeepSeek-V2-Lite-Chat.Q8_0/DeepSeek-V2-Lite-Chat.Q8_0-00001-of-XXXXX.gguf DeepSeek-V2-Lite-Chat.Q8_0.gguf
   • Make sure to point gguf-split to the first chunk of the split.

---

Got a suggestion? Ping me @legraphista!