Ayyylol's picture

Ayyylol

ayyylol

·

AI & ML interests

Ayyy lol

Organizations

New activity in Zyphra/Zamba2-7B-Instruct over 1 year ago

GGUF or EXL2 version?

#2 opened over 1 year ago by

New activity in zai-org/glm-4-9b-chat over 1 year ago

Converting to native Transformers

#81 opened over 1 year ago by

New activity in byroneverson/internlm2_5-7b-chat-abliterated over 1 year ago

Question and a thank you!

#1 opened over 1 year ago by

New activity in jinaai/reader-lm-1.5b over 1 year ago

Temperature and repetition_penalty

#1 opened over 1 year ago by

New activity in upstage/solar-pro-preview-pretrained over 1 year ago

Question about this model

#1 opened over 1 year ago by

New activity in zai-org/LongWriter-glm4-9b over 1 year ago

llama.cpp - Quantize error: KeyError: '<|user|>'

#1 opened over 1 year ago by

New activity in LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct over 1 year ago

llama.cpp support

#8 opened over 1 year ago by

New activity in meta-llama/Llama-3.1-405B-Instruct over 1 year ago

Num KV heads changed from 16 to 8?

#21 opened over 1 year ago by

New activity in huggingchat/chat-ui over 1 year ago

A question about privacy

#523 opened over 1 year ago by

New activity in mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated over 1 year ago

70B when?

#2 opened over 1 year ago by

New activity in failspy/Phi-3-mini-4k-geminified over 1 year ago

The model card unclear xD

#1 opened over 1 year ago by

New activity in MaziyarPanahi/Mistral-7B-Instruct-v0.3-GGUF over 1 year ago

v3 tokenizer

#4 opened over 1 year ago by

New activity in bartowski/Mistral-7B-Instruct-v0.3-GGUF over 1 year ago

v3 tokenizer

#1 opened over 1 year ago by

New activity in mistralai/Mistral-7B-v0.3 over 1 year ago

Remove consolidated weights

#6 opened over 1 year ago by

New activity in failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 over 1 year ago

Possibly missing files

#2 opened over 1 year ago by

New activity in mradermacher/model_requests almost 2 years ago

Orthogonalized models

#49 opened almost 2 years ago by

New activity in failspy/llama-3-70B-Instruct-abliterated almost 2 years ago

Trying to reproduce results

#9 opened almost 2 years ago by

New activity in Artefact2/Mixtral-8x7B-Instruct-v0.1-GGUF almost 2 years ago

Quants appear to be bigger

#1 opened almost 2 years ago by

New activity in mradermacher/model_requests almost 2 years ago

https://huggingface.co/jondurbin/bagel-dpo-20b-v04

#13 opened almost 2 years ago by