kkkkggg/IMAGHarmony
Updated
β’
1
RalFinger
RalFinger
AI & ML interests
None yet
Recent Activity
liked
a model
8 days ago
kkkkggg/IMAGHarmony
liked
a model
14 days ago
calcuis/bagel-gguf
liked
a model
15 days ago
silveroxides/Chroma-LoRA-Experiments
Organizations
None yet
RalFinger's activity
liked
a
model
8 days ago
liked
a
model
14 days ago
liked
a
model
15 days ago
liked
2
models
about 2 months ago
liked
a
model
3 months ago
Lora training scripts
5
#9 opened 4 months ago
by
sh1ny
liked
a
model
4 months ago
upvoted
a
collection
5 months ago
liked
3
models
7 months ago
liked
2
models
8 months ago
upvoted
an
article
8 months ago
Article
𧨠Diffusers welcomes Stable Diffusion 3.5 Large
β’
52
liked
a
model
8 months ago
reacted to
onekq's
post with π₯
8 months ago
Post
1869
I'm now working on finetuning of coding models. If you are GPU-hungry like me, you will find quantized models very helpful. But quantization for finetuning and inference are different and incompatible. So I made two collections here.
Inference (GGUF, via Ollama, CPU is enough)
onekq-ai/ollama-ready-coding-models-67118c3cfa1af2cf04a926d6
Finetuning (Bitsandbytes, QLora, GPU is needed)
onekq-ai/qlora-ready-coding-models-67118771ce001b8f4cf946b2
For quantization, the inference models are far more popular on HF than finetuning models. I use
QuantFactory
to generate inference models (GGUF), and there are a few other choices.
But there hasn't been such a service for finetuning models. DIY isn't too hard though. I made a few myself and you can find the script in the model cards. If the original model is small enough, you can even do it on a free T4 (available via Google Colab).
If you know a (small) coding model worthy of quantization, please let me know and I'd love to add it to the collections.
Inference (GGUF, via Ollama, CPU is enough)
onekq-ai/ollama-ready-coding-models-67118c3cfa1af2cf04a926d6
Finetuning (Bitsandbytes, QLora, GPU is needed)
onekq-ai/qlora-ready-coding-models-67118771ce001b8f4cf946b2
For quantization, the inference models are far more popular on HF than finetuning models. I use
QuantFactory
to generate inference models (GGUF), and there are a few other choices.But there hasn't been such a service for finetuning models. DIY isn't too hard though. I made a few myself and you can find the script in the model cards. If the original model is small enough, you can even do it on a free T4 (available via Google Colab).
If you know a (small) coding model worthy of quantization, please let me know and I'd love to add it to the collections.
liked
a
model
8 months ago
reacted to
clem's
post with π
8 months ago
Post
3721
Very few people realize that most of the successful AI startups got successful because they were focused on open science and open-source for at least their first few years. To name but a few, OpenAI (GPT, GPT2 was open-source), Runway & Stability (stable diffusion), Cohere, Mistral and of course Hugging Face!
The reasons are not just altruistic, it's also because sharing your science and your models pushes you to build AI faster (which is key in a fast-moving domain like AI), attracts the best scientists & engineers and generates much more visibility, usage and community contributions than if you were 100% closed-source. The same applies to big tech companies as we're seeing with Meta and Google!
More startups and companies should release research & open-source AI, it's not just good for the world but also increases their probability of success!
The reasons are not just altruistic, it's also because sharing your science and your models pushes you to build AI faster (which is key in a fast-moving domain like AI), attracts the best scientists & engineers and generates much more visibility, usage and community contributions than if you were 100% closed-source. The same applies to big tech companies as we're seeing with Meta and Google!
More startups and companies should release research & open-source AI, it's not just good for the world but also increases their probability of success!
- 4 replies