Hugging Face's logo

Zillow
company
Verified
https://www.zillow.com/
zillow
Activity Feed Request to join this org

AI & ML interests

None defined yet.
csabakecskemeti 
posted an update 2 months ago
view post
Post
2880
Has anyone ever backed up a model to a sequential tape drive, or I'm the world first? :D
Just played around with my retro PC that has got a tape drive—did it just because I can.
·
csabakecskemeti 
posted an update 3 months ago
anusha-zg 
in zillow/real_estate_v1 3 months ago

Is this data set relevant for real estate investors?

1
#2 opened 3 months ago by
jhuilar
csabakecskemeti 
posted an update 4 months ago
csabakecskemeti 
posted an update 4 months ago
csabakecskemeti 
posted an update 5 months ago
view post
Post
3388
I'm collecting llama-bench results for inference with a llama 3.1 8B q4 and q8 reference models on varoius GPUs. The results are average of 5 executions.
The system varies (different motherboard and CPU ... but that probably that has little effect on the inference performance).

https://devquasar.com/gpu-gguf-inference-comparison/
the exact models user are in the page

I'd welcome results from other GPUs is you have access do anything else you've need in the post. Hopefully this is useful information everyone.
csabakecskemeti 
posted an update 5 months ago
view post
Post
2401
Managed to get my hands on a 5090FE, it's beefy

| llama 8B Q8_0 | 7.95 GiB | 8.03 B | CUDA | 99 | pp512 | 12207.44 ± 481.67 |
| llama 8B Q8_0 | 7.95 GiB | 8.03 B | CUDA | 99 | tg128 | 143.18 ± 0.18 |

Comparison with others GPUs
http://devquasar.com/gpu-gguf-inference-comparison/
csabakecskemeti 
posted an update 5 months ago
csabakecskemeti 
posted an update 5 months ago
csabakecskemeti 
posted an update 5 months ago
view post
Post
838
Fine tuning on the edge. Pushing the MI100 to it's limits.
QWQ-32B 4bit QLORA fine tuning
VRAM usage 31.498G/31.984G :D

  • 4 replies
·
csabakecskemeti 
posted an update 6 months ago
view post
Post
1987
-UPDATED-
4bit inference is working! The blogpost is updated with code snippet and requirements.txt
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
-UPDATED-
I've played around with an MI100 and ROCm and collected my experience in a blogpost:
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
Unfortunately I've could not make inference or training work with model loaded in 8bit or use BnB, but did everything else and documented my findings.
  • 4 replies
·
csabakecskemeti 
posted an update 6 months ago
view post
Post
2850
Testing Training on AMD/ROCm the first time!

I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s.
For quantized inference it's a beast (MI50 was also surprisingly fast)

For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model.

Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.
·
csabakecskemeti 
posted an update 6 months ago
csabakecskemeti 
posted an update 7 months ago
view post
Post
1894
Check out my idea:
LLmaaS - Local LLM as a Service

With LLmaaS, I propose leveraging locally running LLMs as a service, providing a standardized way for websites to access and utilize them for LLM-powered operations directly on the user’s device.

Demo, code, more detailed description.
https://devquasar.com/llmaas/
https://github.com/csabakecskemeti/LLmaaS
https://youtu.be/OOWGr8jcP5Q

Call for contributors
Join me a develop the LLmaaS proxy to make this a generic purpose tool to leverage local LLMs on web. Build in security measures.
I'm looking for help to make the proxy more generic support multiple local LLM services without any change on the HTML side.
Also looking for ideas how to make the HTML par more modular and easy to use.
  • 4 replies
·
csabakecskemeti 
posted an update 7 months ago
csabakecskemeti 
posted an update 7 months ago
view post
Post
2386
I've run the open llm leaderboard evaluations + hellaswag on deepseek-ai/DeepSeek-R1-Distill-Llama-8B and compared to meta-llama/Llama-3.1-8B-Instruct and at first glance R1 do not beat Llama overall.

If anyone wants to double check the results are posted here:
https://github.com/csabakecskemeti/lm_eval_results

Am I made some mistake, or (at least this distilled version) not as good/better than the competition?

I'll run the same on the Qwen 7B distilled version too.
·
csabakecskemeti 
posted an update 7 months ago
csabakecskemeti 
posted an update 8 months ago
csabakecskemeti 
posted an update 8 months ago
csabakecskemeti 
posted an update 8 months ago
view post
Post
1557
Happy New Year, Huggingface community!
In 2025, I'll continue my quantization (and some fine-tuning) efforts to support the open-source AI and Make knowledge free for everyone.

DevQuasar
https://devquasar.com/
  • 1 reply
·