Model Repository #87
Replies: 8 comments
-
|
Cerebras 111M (GPT2) - https://huggingface.co/concedo/cerebras-111M-ggml/ RWKV-v4-169M - https://huggingface.co/concedo/rwkv-v4-169m-ggml/tree/main |
Beta Was this translation helpful? Give feedback.
-
|
Alpaca 7B: https://huggingface.co/Sosaka/Alpaca-native-4bit-ggml Alpaca 13B: https://huggingface.co/Pi3141/alpaca-native-13B-ggml GPT-X-Alpaca 13B: https://huggingface.co/anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g Alpaca 30B: https://huggingface.co/Pi3141/alpaca-lora-30B-ggml I have tested then. Some must run the convert script to maximum performance. |
Beta Was this translation helpful? Give feedback.
-
|
I will edit the first post to keep all models organized by categories. Thanks for the contributions. |
Beta Was this translation helpful? Give feedback.
-
|
This one works well (worked as of a few days ago): https://huggingface.co/camelids/llama-13b-ggml-q4_0 |
Beta Was this translation helpful? Give feedback.
-
|
Added 3 more models converted and tested by me, Adventure, Adventien and Pygway. |
Beta Was this translation helpful? Give feedback.
-
|
gpt4all: https://huggingface.co/eachadea/ggml-gpt4all-7b-4bit |
Beta Was this translation helpful? Give feedback.
-
|
Added wizardLM 7B, great model, better than alpaca, give it a try. |
Beta Was this translation helpful? Give feedback.
-
|
Baize_lora_13b_q4: https://huggingface.co/couchpotato888/baize_lora_q4_ggml |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Models for use with koboldcpp
CHAT MODELS
Pygmalion 6B: - https://huggingface.co/concedo/pygmalion-6bv3-ggml-ggjt
ADVENTURE MODELS
Skein 6B: - https://huggingface.co/Kastor/GPT-J-6b-Skein-ggml-q4_1
Adventure 6B: - https://huggingface.co/Kastor/GPT-J-6B-Adventure-ggml-q4_1
Adventien 6B (Adventure+Skein): - https://huggingface.co/Kastor/GPT-J-6B-Adventien-ggml-q4_1
NOVEL MODELS
Janeway 6B: - https://huggingface.co/concedo/janeway-6b-ggml
Shinen 6B: - https://huggingface.co/xzuyn/GPT-J-6B-Shinen-ggml-q4_0
MIXED MODELS
Pygway 6B: - https://huggingface.co/Kastor/GPT-J-6B-Pygway-ggml-q4_1
Javalion R: - https://huggingface.co/xzuyn/Javalion-R-ggml-q4_0
Alpacino 13B: - https://huggingface.co/verymuchawful/Alpacino-13b-ggml
GENERIC MODELS
WizardLM 7B: - https://huggingface.co/TheBloke/wizardLM-7B-GGML
(Posted by LostRuins)
Cerebras 111M (GPT2): - https://huggingface.co/concedo/cerebras-111M-ggml/
RWKV-v4-169M: - https://huggingface.co/concedo/rwkv-v4-169m-ggml/tree/main
(Posted by gustrd)
Alpaca 7B: - https://huggingface.co/Sosaka/Alpaca-native-4bit-ggml
Alpaca 13B: - https://huggingface.co/Pi3141/alpaca-native-13B-ggml
GPT-X-Alpaca 13B: - https://huggingface.co/anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g
Alpaca 30B: - https://huggingface.co/Pi3141/alpaca-lora-30B-ggml
(Posted by noprotocolunit)
Llama 13B: - https://huggingface.co/camelids/llama-13b-ggml-q4_0
(Posted by Myrminki)
gpt4all: - https://huggingface.co/eachadea/ggml-gpt4all-7b-4bit
Beta Was this translation helpful? Give feedback.
All reactions