momonga PRO

mmnga's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in mmnga-o/miotts-cpp-gguf 18 days ago

remove files

#1 opened 18 days ago by

mmnga

New activity in elyza/ELYZA-Thinking-1.0-Qwen-32B 10 months ago

eos_token becomes <|im_end|> after GGUF conversion with llama.cpp, and generation never terminates

#1 opened 10 months ago by

mmnga

New activity in mmnga/Ninja-v1-NSFW-128k-gguf 11 months ago

Update README.md

❤️ 1

1

#1 opened 11 months ago by

kamone373

New activity in mmnga/Moonlight-16B-A3B-Instruct-gguf about 1 year ago

It seems completely broken

1

#1 opened about 1 year ago by

aguspiza

New activity in mmnga/Llama-3.3-70B-Instruct-gguf about 1 year ago

Can we hire you for quantization and fine tuning?

1

#1 opened about 1 year ago by

rafa9

New activity in mmnga/DeepSeek-V3-slice-jp64 about 1 year ago

Fix

1

#1 opened about 1 year ago by

STATIKwitak

New activity in mmnga/rinna-llama-3-youko-70b-instruct-gguf over 1 year ago

Would it be possible to have an 8bit gguf?

❤️ 1

2

#1 opened over 1 year ago by

PurityWolf

New activity in mmnga/Llama-3.1-70B-Japanese-Instruct-2407-gguf over 1 year ago

Please use split ggufs instead of splitting files manually

❤️ 1

1

#1 opened over 1 year ago by

lmg-anon

New activity in mmnga/Mistral-Large-Instruct-2407-gguf over 1 year ago

Usage in the model card seems to be ChatML format.

❤️ 1

1

#1 opened over 1 year ago by

yamikumods

New activity in mmnga/Phi-3-medium-128k-instruct-gguf almost 2 years ago

LM Studioでのエラー

3

#1 opened almost 2 years ago by

alfredplpl

New activity in mmnga/Llama-3-70B-japanese-suzume-vector-v0.1 almost 2 years ago

An idea

👍 1

1

#1 opened almost 2 years ago by

Cran-May

New activity in mmnga/ELYZA-japanese-Llama-2-7b-fast-instruct-gguf almost 2 years ago

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

7

#1 opened almost 2 years ago by

wattai

New activity in mmnga/Superswallow-7b-v0.1-gguf about 2 years ago

Differences in output from the original model

2

#1 opened about 2 years ago by

nitky

New activity in mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1 about 2 years ago

Librarian Bot: Add moe tag to model

#3 opened about 2 years ago by

librarian-bot

New activity in mmnga/Mixtral-Extraction-4x7B-Instruct-v0.1 about 2 years ago

Librarian Bot: Add moe tag to model

#1 opened about 2 years ago by

librarian-bot

New activity in mmnga/TinyMixtral-x8-Clonebase-7b about 2 years ago

Librarian Bot: Add moe tag to model

#1 opened about 2 years ago by

librarian-bot

New activity in mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1 about 2 years ago

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

❤️ 1

3

#2 opened about 2 years ago by

BlueNipples

Responses somewhat related to the prompt but still gibberish

2

#1 opened about 2 years ago by

JeroenAdam

New activity in mmnga/cyberagent-calm2-7b-chat-GPTQ-calib-ja-1k over 2 years ago

Tritonのサポート切れによるColab A100への移行

2

#2 opened over 2 years ago by

alfredplpl

bfloat16でなくfloat16による量子化

2

#1 opened over 2 years ago by

alfredplpl