Upload DeepSeek-V2-Chat.q8_0.gguf/DeepSeek-V2-Chat.Q8_0-00004-of-00012.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.q8_0.gguf/DeepSeek-V2-Chat.Q8_0-00003-of-00012.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.q8_0.gguf/DeepSeek-V2-Chat.Q8_0-00002-of-00012.gguf with huggingface_hub

license: add DeepSeek license

readme: update quant info; minor changes to hyperlinks and terms

Upload DeepSeek-V2-Chat.q8_0.gguf/DeepSeek-V2-Chat.Q8_0-00001-of-00012.gguf with huggingface_hub

readme: fix kv overrides

Upload DeepSeek-V2-Chat.iq3_xs.gguf/DeepSeek-V2-Chat.IQ3_XS-00008-of-00008.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.iq3_xs.gguf/DeepSeek-V2-Chat.IQ3_XS-00007-of-00008.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.iq3_xs.gguf/DeepSeek-V2-Chat.IQ3_XS-00006-of-00008.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.iq3_xs.gguf/DeepSeek-V2-Chat.IQ3_XS-00005-of-00008.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.iq3_xs.gguf/DeepSeek-V2-Chat.IQ3_XS-00004-of-00008.gguf with huggingface_hub

readme: add new llama.cpp release info

Upload DeepSeek-V2-Chat.iq3_xs.gguf/DeepSeek-V2-Chat.IQ3_XS-00003-of-00008.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.iq3_xs.gguf/DeepSeek-V2-Chat.IQ3_XS-00002-of-00008.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.iq3_xs.gguf/DeepSeek-V2-Chat.IQ3_XS-00001-of-00008.gguf with huggingface_hub

model: remove iq1_m, faulty upload

readme: add extra params

model: correct name capitalization

Upload Deepseek-V2-Chat.IQ1_M.gguf with huggingface_hub

readme: update quants

Upload DeepSeek-V2-Chat.iq2_xxs.gguf/DeepSeek-V2-Chat.IQ2_XXS-00003-of-00003.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.iq2_xxs.gguf/DeepSeek-V2-Chat.IQ2_XXS-00002-of-00003.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.iq2_xxs.gguf/DeepSeek-V2-Chat.IQ2_XXS-00001-of-00003.gguf with huggingface_hub

tool: add kv overrides to start command (win)

tool: add linux autorun (no CUDA, ubuntu)

tool: automatically download llama.cpp and model files; run chat completions server (win, cuda)

readme: TODO implement llamafile

readme: add quants update

Upload DeepSeek-V2-Chat.q2_k.gguf/DeepSeek-V2-Chat.Q2_K-00005-of-00005.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.q2_k.gguf/DeepSeek-V2-Chat.Q2_K-00004-of-00005.gguf with huggingface_hub

Upload DeepSeek-V2-Chat.q2_k.gguf/DeepSeek-V2-Chat.Q2_K-00003-of-00005.gguf with huggingface_hub

imatrix: add chunk 63 (final)

Upload DeepSeek-V2-Chat.q2_k.gguf/DeepSeek-V2-Chat.Q2_K-00002-of-00005.gguf with huggingface_hub

imatrix: add chunk 13

Upload DeepSeek-V2-Chat.q2_k.gguf/DeepSeek-V2-Chat.Q2_K-00001-of-00005.gguf with huggingface_hub

imatrix: update after 6 chunks

imatrix: update after 4 chunks

readme: add detailed instructions

imatrix: upload 3 chunks

build: add precompiled llama.cpp

Upload imatrix.dat

Update README.md

delete: Use gguf-split instead of Python script

Create readme.md

Create DeepSeek-V2-Chat.q6_k.gguf/readme.md

Create DeepSeek-V2-Chat.q5_k_m.gguf/readme.md

Add readme for q3_k_m

Update README.md

Upload DeepSeek-V2-Chat.bf16.gguf/DeepSeek-V2-Chat.bf16.part-22-of-22.gguf with huggingface_hub