license: mit
library_name: transformers
pipeline_tag: text-generation
tags:
- code
- deepseek
- gguf
- bf16
- chinese
- english
metrics:
- accuracy
Deepseek-V2-Chat-GGUF
Quantizised from https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat
Using llama.cpp fork: https://github.com/fairydreaming/llama.cpp/tree/deepseek-v2
Warning: This will not work unless you compile llama.cpp from the repo provided (and set metadata KV overrides)!
How to use:
- Find the relevant directory
- Download all files
- Run merge.py
- Merged GGUF should appear
Quants:
- bf16 [size: 439gb]
- q8_0 (after q2_k) [estimated size: 233.27gb]
- q4_k_m [size: 132gb]
- q2_k (uploading) [size: 80gb]
- q3_k_s (generating, using importance matrix) [estimated size: 96.05gb]
Planned Quants (using importance matrix):
- q5_k_m
- q5_k_s
- q3_k_m
- q6_k
- iq4_nl
- iq4_xs
- iq2_xxs
- iq2_xs
- iq2_s
- iq2_m
- iq1_s
- iq1_m
Note: the model files do not have some DeepSeek v2 specific parameters, will look into adding them
Please use commit 039896407afd40e54321d47c5063c46a52da3e01, otherwise use these metadata KV overrides:
deepseek2.attention.q_lora_rank=int:1536
deepseek2.attention.kv_lora_rank=int:512
deepseek2.expert_shared_count=int:2
deepseek2.expert_feed_forward_length=int:1536
deepseek2.leading_dense_block_count=int:1
A precompiled AVX2 version is avaliable at llama.cpp-039896407afd40e54321d47c5063c46a52da3e01.zip in the root of this repo.
License:
- DeepSeek license for model weights
- MIT license for any repo code
Performance:
~1.5t/s with Ryzen 3 3700x (96gb 3200mhz) [Q2_K]
iMatrix:
Find imatrix.dat in the root of this repo, made with a Q2_K quant (see here for info: https://github.com/ggerganov/llama.cpp/issues/5153#issuecomment-1913185693)
Using groups_merged.txt, find it here: https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384
Censorship:
This model is quite censored, finetuning on toxic DPO might help.