GGUF models by shidowake

36 GGUF models quantized by shidowake on Hugging Face. Sizes run from 2.8B to 13.1B parameters. The longest trained context is 32K tokens.

Most downloadedNewestLargestLongest contextSmallest
SW
240306 swal 13b bnb capybara 6k gpt4 alpaca 6k qlora adaptor fp16merged
Swal · shidowake
Params13.1B
Context4K
Q4_K_M7.9 GB
GGUF
JA
japanese stablelm base gamma 7b base
Japanese · shidowake
Params7.24B
Context4K
Smallest5.1 GB
GGUF
GE
gemma 7b base
Gemma · shidowake
Params8.54B
Context8K
Smallest7.0 GB
GGUF
ME
240404 mergekit MoE chatntq ja 7b v1.0 shisa gamma 7b v1
Mergekit · shidowake
Params12.9B
Context4K
Q4_K_M7.8 GB
GGUF
AU
augmxnt shisa gamma 7b v1
Augmxnt · shidowake
Params7.24B
Context4K
Smallest7.7 GB
GGUF
MI
test 231222 mistral lora adaptor checkpoint 205 merged q8 0
Mistral · shidowake
Params7.24B
Context32K
Smallest7.7 GB
GGUF
ST
stablelm-zephyr-3b
Stablelm · shidowake
Params2.8B
Context4K
Smallest2.0 GB
GGUF
RE
revise 240216 SOL 11B base zephyer template qlora adaptor fp16merged
Revise · shidowake
Params10.7B
Context4K
Smallest11.4 GB
GGUF
MI
test 240102 mistral lora adaptor merged q5 K M
Mistral · shidowake
Params7.24B
Context32K
Smallest5.1 GB
GGUF
SW
SwalMS7b CVec co0.5 mist inst v0.1 co0.5 openchat 3.5 co0.3 Hermes2Pro
Swalms · shidowake
Params7.33B
Context4K
Smallest7.8 GB
Tool use
MI
OpenHermes 2.5 Mistral 7B
Mistral · shidowake
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
TE
test 240110 revised swallow 7B hf qlora adaptor merged
Test · shidowake
Params6.83B
Context4K
Smallest4.9 GB
GGUF
TE
test 240206 cyber2base 7B qlora adaptor pretrained merged 16bit
Test · shidowake
Params7.01B
Context4K
Smallest7.5 GB
GGUF
MI
240308 02 swal 7b plus base bnb 4bit mixtral 5k r64 qlora adaptor fp16merged
Mistral · shidowake
Params6.83B
Context4K
Smallest5.6 GB
GGUF
TE
test 240128 swal 7B hf qlora adaptor qmerged
Test · shidowake
Params6.83B
Context4K
Smallest4.9 GB
GGUF
SO
240216 SOL 11B base zephyer template qlora adaptor fp16merged
Sol · shidowake
Params10.7B
Context4K
Smallest7.6 GB
GGUF
MI
mistral base bnb 4bit alpaca lora adaptor merged
Mistral · shidowake
Params7.24B
Context32K
Smallest5.9 GB
GGUF
SW
240216 swal 13b zephyer template qlora adaptor fp16merged
Swal · shidowake
Params13.1B
Context4K
Q4_K_M7.9 GB
GGUF
TE
test 240202 cyber2 base
Test · shidowake
Params7.01B
Context4K
Smallest7.5 GB
GGUF
TE
test 240202 cyber2 chat
Test · shidowake
Params7.01B
Context32K
Smallest7.5 GB
GGUF
TE
test 240111 defalut template swallow 7B hf qlora adaptor 4bit merged
Test · shidowake
Params6.83B
Context4K
Q4_K_M4.1 GB
GGUF
SA
SakanaAI EvoLLM JP A v1 7B
Sakanaai · shidowake
Params7.24B
Context32K
Smallest7.7 GB
GGUF
CH
240405 chatntq ja 7b v1 co0.8 mist inst v0.1
Chatntq · shidowake
Params7.24B
Context4K
Smallest7.7 GB
GGUF
SW
SwalMS7b CVec co0.5 mist inst v0.1 co0.5 openchat 3.5 co0.5 Hermes2Pro
Swalms · shidowake
Params7.33B
Context4K
Smallest7.8 GB
Tool use
TE
test 240213 lizard
Test · shidowake
Params6.74B
Context4K
Smallest7.2 GB
GGUF
TE
test 240111 defalut template swallow 7B hf qlora adaptor merged
Test · shidowake
Params6.83B
Context4K
Smallest4.9 GB
GGUF
SW
240216 swal 13b chatml qlora adaptor fp16merged
Swal · shidowake
Params13.1B
Context4K
Q4_K_M7.9 GB
GGUF
SW
240311 swal ms 7B base bnb deftok r32 mix ja 9k qlora adaptor fp16merged
Swal · shidowake
Params7.33B
Context4K
Smallest6.0 GB
GGUF
TE
test 240122 shisa base 7b v1
Test · shidowake
Params7.96B
Context32K
Smallest8.5 GB
GGUF
RA
RakutenAI 7B chat
Rakutenai · shidowake
Params7.37B
Context32K
Smallest7.8 GB
GGUF

About shidowake on Hugging Face

shidowake has published 36 GGUF models that ggufmodels.com tracks, across families such as Test, Swal and Mistral. The most downloaded are 240306 swal 13b bnb capybara 6k gpt4 alpaca 6k qlora adaptor fp16merged, japanese stablelm base gamma 7b base and gemma 7b base.

The quants shidowake publishes most often are Q8_0 (21), Q4_K_M (10), Q6_K (8) and Q5_K_M (8). Their Q4_K_M files range from 4.1 to 7.9 GB. Parameter counts run from 2.8B to 13.1B, and the longest trained context window is 32K tokens.

Frequently asked questions

What GGUF models has shidowake published?

36 models are listed here, mainly from the Test, Swal and Mistral families. The most downloaded is 240306 swal 13b bnb capybara 6k gpt4 alpaca 6k qlora adaptor fp16merged.

Which quants does shidowake publish?

The most common are Q8_0 (21 models), Q4_K_M (10 models), Q6_K (8 models) and Q5_K_M (8 models).

Keep browsing