Hugging Face's logo
momonga's picture
18 91

momonga PRO

mmnga
thr3a's profile picture jinen's profile picture DrHakase's profile picture
·

AI & ML interests

None yet

Recent Activity

updated a model 2 days ago
mmnga/DeepSeek-V3-slice-jp64
updated a model 4 days ago
mmnga/tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-gguf
updated a model 4 days ago
mmnga/tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-gguf
View all activity

Organizations

Algomatic Inc's profile picture MLX Community's profile picture

mmnga's activity

New activity in mmnga/rinna-llama-3-youko-70b-instruct-gguf 5 months ago

Would it be possible to have an 8bit gguf?

2
#1 opened 5 months ago by
PurityWolf
New activity in mmnga/Llama-3.1-70B-Japanese-Instruct-2407-gguf 5 months ago

Please use split ggufs instead of splitting files manually

1
#1 opened 5 months ago by
lmg-anon
New activity in mmnga/Mistral-Large-Instruct-2407-gguf 5 months ago

Usage in the model card seems to be ChatML format.

1
#1 opened 5 months ago by
yamikumods
New activity in mmnga/Phi-3-medium-128k-instruct-gguf 8 months ago

LM Studioでのエラー

3
#1 opened 8 months ago by
alfredplpl
New activity in stabilityai/japanese-stablelm-2-instruct-1_6b 8 months ago

Update tokenization_arcade100k.py
#1 opened 8 months ago by
mmnga
New activity in mmnga/Llama-3-70B-japanese-suzume-vector-v0.1 8 months ago

An idea

1
#1 opened 8 months ago by
Cran-May
New activity in mmnga/ELYZA-japanese-Llama-2-7b-fast-instruct-gguf 9 months ago

Please tell me how did you convert this FAST model into gguf file.

7
#1 opened 9 months ago by
wattai
New activity in Vezora/Mistral-22B-v0.1 9 months ago

Update config.json

1
#3 opened 9 months ago by
mmnga
New activity in mmnga/Superswallow-7b-v0.1-gguf 12 months ago

Differences in output from the original model

2
#1 opened 12 months ago by
nitky
New activity in mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1 12 months ago

Librarian Bot: Add moe tag to model
#3 opened 12 months ago by
librarian-bot
New activity in mmnga/Mixtral-Extraction-4x7B-Instruct-v0.1 12 months ago

Librarian Bot: Add moe tag to model
#1 opened 12 months ago by
librarian-bot
New activity in mmnga/TinyMixtral-x8-Clonebase-7b 12 months ago

Librarian Bot: Add moe tag to model
#1 opened 12 months ago by
librarian-bot
New activity in mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1 about 1 year ago

Maybe a slerp or some other merge method will preserve the component experts better?

3
#2 opened about 1 year ago by
BlueNipples

Responses somewhat related to the prompt but still gibberish

2
#1 opened about 1 year ago by
JeroenAdam
New activity in mmnga/cyberagent-calm2-7b-chat-GPTQ-calib-ja-1k about 1 year ago

Tritonのサポート切れによるColab A100への移行

2
#2 opened about 1 year ago by
alfredplpl

bfloat16でなくfloat16による量子化

2
#1 opened about 1 year ago by
alfredplpl
New activity in elyza/ELYZA-japanese-Llama-2-7b-fast-instruct over 1 year ago

Missing tokenizer.model

4
#1 opened over 1 year ago by
mmnga
New activity in mmnga/rinna-bilingual-gpt-neox-4b-ggml over 1 year ago

is this related with GPT-Neo-2.7B-AID ?

1
#1 opened over 1 year ago by
adriey