minipasila's picture

minipasila

mpasila

·

https://minipasila.net/

minipasila

AI & ML interests

None yet

Recent Activity

new activity 4 days ago

tencent/Hunyuan-7B-Instruct:Request for GGUF support through llama.cpp

liked a model 9 days ago

openbmb/MiniCPM-o-2_6

liked a model about 1 month ago

AsmoKoskinen/F5-TTS_Finnish_Model

View all activity

Organizations

None yet

mpasila's activity

New activity in tencent/Hunyuan-7B-Instruct 4 days ago

Request for GGUF support through llama.cpp

#1 opened 5 days ago by

Doctor-Chad-PhD

New activity in mpasila/Llama-3.2-Finnish-Wikipedia-LoRA-1B 4 months ago

Continued pretraining

#1 opened 4 months ago by

New activity in kyutai/moshika-pytorch-bf16 4 months ago

System prompt?

#2 opened 4 months ago by

New activity in mattshumer/Reflection-Llama-3.1-70B 5 months ago

BF16 weights?

#1 opened 5 months ago by

New activity in BeaverAI/mistral-dory-12b 6 months ago

Repetition issue

#1 opened 6 months ago by

New activity in bosonai/Higgs-Llama-3-70B 8 months ago

8B version?

#2 opened 8 months ago by

New activity in NilanE/ParallelFiction-Ja_En-100k 8 months ago

Numbers missing from English translations and a few other issues

#3 opened 10 months ago by

New activity in mpasila/DarkViperAU-Essays 10 months ago

Librarian Bot: Add language metadata for dataset

#1 opened 10 months ago by

New activity in mpasila/JP-EN-Translator-2K-steps-7B 10 months ago

Better performance on short context lengths

#1 opened 10 months ago by

New activity in alpindale/dbrx-instruct 10 months ago

Failing to 4-bit quantize with BitsAndBytes

#1 opened 10 months ago by

New activity in mpasila/Moistral-11B-v1-exl2-4bpw 10 months ago

Model Loader?

#1 opened 10 months ago by

New activity in BeaverLegacy/Moistral-11B-v1 10 months ago

Does this use prompt formatting?

#3 opened 10 months ago by

New activity in TheBloke/Poro-34B-GPTQ 11 months ago

Update to the final version

#1 opened 11 months ago by

New activity in abideen/gemma-7b-openhermes 11 months ago

Retains censorship from the instruct tuned model

#1 opened 11 months ago by

New activity in miqudev/miqu-1-70b about 1 year ago

Please upload the full model first

#1 opened about 1 year ago by

New activity in LumiOpen/Poro-34B about 1 year ago

System requirements for this model?

#4 opened about 1 year ago by

New activity in royallab/Psyfighter-2-13b-exl2 about 1 year ago

8 bpw

#1 opened about 1 year ago by

New activity in TencentARC/LLaMA-Pro-8B-Instruct about 1 year ago

GPTQ or EXL2 quants?

#2 opened about 1 year ago by

New activity in mistralai/Mistral-7B-Instruct-v0.2 about 1 year ago

How is this different from v1?

#2 opened about 1 year ago by

New activity in Finnish-NLP/llama-7b-finnish about 1 year ago

Tokenizer is broken?

#1 opened about 1 year ago by