13 1 27

Ivan Stepanov

ivanstepanovftw

https://t.me/ivanstepanovftw

ivanstepanovftw

AI & ML interests

None yet

Recent Activity

reacted to bartowski's post with 👍 5 days ago

Switching to `author_model-name` I posted a poll on twitter, and others have mentioned the interest in me using the convention of including the author name in the model path when I upload. It has a couple advantages, first and foremost of course is ensuring clarity of who uploaded the original model (did Qwen upload Qwen2.6? Or did someone fine tune Qwen2.5 and named it 2.6 for fun?) The second thing is that it avoids collisions, so if multiple people upload the same model and I try to quant them both, I would normally end up colliding and being unable to upload both I'll be implementing the change next week, there are just two final details I'm unsure about: First, should the files also inherit the author's name? Second, what to do in the case that the author name + model name pushes us past the character limit? Haven't yet decided how to handle either case, so feedback is welcome, but also just providing this as a "heads up"

liked a model 8 days ago

bartowski/gemma-2-9b-it-abliterated-GGUF

new activity 3 months ago

ai-sage/Giga-Embeddings-instruct:Exception

View all activity

Organizations

None yet

ivanstepanovftw's activity

New activity in ai-sage/Giga-Embeddings-instruct 3 months ago

Exception

#2 opened 3 months ago by

ivanstepanovftw

New activity in jinaai/jina-embeddings-v3 4 months ago

truncate_dim=N returns non-normalized embeddings

#60 opened 5 months ago by

ivanstepanovftw

New activity in hs-hf/jina-embeddings-v3-distilled 4 months ago

How to specify LoRA?

#1 opened 4 months ago by

ivanstepanovftw

New activity in Lightricks/LTX-Video 4 months ago

Hardware recommendations?

#6 opened 4 months ago by

k-nearest-neighbor

New activity in jinaai/jina-embeddings-v3 4 months ago

Disable tqdm

#66 opened 4 months ago by

ivanstepanovftw

New activity in jinaai/xlm-roberta-flash-implementation 4 months ago

Shouldn't normalization be performed AFTER truncating dimensions?

#49 opened 4 months ago by

ivanstepanovftw

Disable tqdm.

#48 opened 4 months ago by

ivanstepanovftw

New activity in tenyx/Llama3-TenyxChat-70B 10 months ago

Prompt template?

#4 opened 10 months ago by

ivanstepanovftw

New activity in brittlewis12/gemma-7b-it-GGUF 11 months ago

Q8_0 model weights less than Q2_0

#1 opened 11 months ago by

ivanstepanovftw

New activity in ds4sd/DocLayNet-v1.1 over 1 year ago

What is wrong with PDF Cells?

#1 opened over 1 year ago by

ivanstepanovftw

New activity in TheBloke/MPT-7B-Instruct-GGML almost 2 years ago

Corrupted?

#1 opened almost 2 years ago by

BlueAquilae

New activity in chavinlo/alpaca-13b almost 2 years ago

What is the current method to convert these models to work with Llama.cpp?

#1 opened almost 2 years ago by

Derg

New activity in PygmalionAI/pygmalion-7b almost 2 years ago

Reasoning behind bfloat instead of float?

#3 opened almost 2 years ago by

xzuyn

Reasoning behind bfloat instead of float?

#3 opened almost 2 years ago by

xzuyn