Cosmos
Collection
The collection of Cosmos models
•
31 items
•
Updated
•
245
RalFinger
RalFinger
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
16 days ago
Cosmos
new activity
about 2 months ago
mit-han-lab/svdquant-models:How Do I Use It in ComfyUI?
liked
a model
2 months ago
Kijai/SUPIR_pruned
Organizations
None yet
RalFinger's activity
upvoted
a
collection
16 days ago
How Do I Use It in ComfyUI?
7
#1 opened 3 months ago
by
youknownothing
liked
2
models
2 months ago
liked
3
models
3 months ago
upvoted
an
article
3 months ago
Article
🧨 Diffusers welcomes Stable Diffusion 3.5 Large
•
50
liked
a
model
3 months ago
reacted to
onekq's
post with 🔥
3 months ago
Post
1857
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 https://huggingface.co/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 https://huggingface.co/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
3 months ago
reacted to
clem's
post with 👍
4 months ago
Post
3714
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
liked
a
model
4 months ago
reacted to
davidberenstein1957's
post with 🔥
4 months ago
Post
1651
🦀 Is your SQL a bit rusty? I just created theText To SQL Hub dataset explorer. To write SQL queries based on natural text input. Uses DuckDB, Llama 3.1 70B and the Hugging Face dataset-server API.
davidberenstein1957/text-to-sql-hub-datasets
davidberenstein1957/text-to-sql-hub-datasets
reacted to
cbensimon's
post with ❤️
4 months ago
Post
4403
Hello everybody,
We've rolled out a major update to ZeroGPU! All the Spaces are now running on it.
Major improvements:
1. GPU cold starts about twice as fast!
2. RAM usage reduced by two-thirds, allowing more effective resource usage, meaning more GPUs for the community!
3. ZeroGPU initializations (coldstarts) can now be tracked and displayed (use
4. Improved compatibility and PyTorch integration, increasing ZeroGPU compatible spaces without requiring any modifications!
Feel free to answer in the post if you have any questions
🤗 Best regards,
Charles
We've rolled out a major update to ZeroGPU! All the Spaces are now running on it.
Major improvements:
1. GPU cold starts about twice as fast!
2. RAM usage reduced by two-thirds, allowing more effective resource usage, meaning more GPUs for the community!
3. ZeroGPU initializations (coldstarts) can now be tracked and displayed (use
progress=gr.Progress(track_tqdm=True))4. Improved compatibility and PyTorch integration, increasing ZeroGPU compatible spaces without requiring any modifications!
Feel free to answer in the post if you have any questions
🤗 Best regards,
Charles
liked
3
models
5 months ago
reacted to
macadeliccc's
post with 👍
5 months ago
Post
1755
Automated web scraping with playwright is becoming easier by the day. Now, using ollama tool calling, its possible to perform very high accuracy web scraping (in some cases 100% accurate) through just asking an LLM to scrape the content for you.
This can be completed in a multistep process similar to cohere's platform. If you have tried the cohere playground with web scraping, this will feel very similar. In my experience, the Llama 3.1 version is much better due to the larger context window. Both tools are great, but the difference is the ollama + playwright version is completely controlled by you.
All you need to do is wrap your scraper in a function:
and then make your request:
To learn more:
Github w/ Playground: https://github.com/tdolan21/tool-calling-playground/blob/main/notebooks/ollama-playwright-web-scraping.ipynb
Complete Guide: https://medium.com/@tdolan21/building-an-llm-powered-web-scraper-with-ollama-and-playwright-6274d5d938b5
This can be completed in a multistep process similar to cohere's platform. If you have tried the cohere playground with web scraping, this will feel very similar. In my experience, the Llama 3.1 version is much better due to the larger context window. Both tools are great, but the difference is the ollama + playwright version is completely controlled by you.
All you need to do is wrap your scraper in a function:
async def query_web_scraper(url: str) -> dict:
scraper = WebScraper(headless=False)
return await scraper.query_page_content(url)and then make your request:
# First API call: Send the query and function description to the model
response = ollama.chat(
model=model,
messages=messages,
tools=[
{
'type': 'function',
'function': {
'name': 'query_web_scraper',
'description': 'Scrapes the content of a web page and returns the structured JSON object with titles, articles, and associated links.',
'parameters': {
'type': 'object',
'properties': {
'url': {
'type': 'string',
'description': 'The URL of the web page to scrape.',
},
},
'required': ['url'],
},
},
},
]
)To learn more:
Github w/ Playground: https://github.com/tdolan21/tool-calling-playground/blob/main/notebooks/ollama-playwright-web-scraping.ipynb
Complete Guide: https://medium.com/@tdolan21/building-an-llm-powered-web-scraper-with-ollama-and-playwright-6274d5d938b5
liked
a
Space
5 months ago