open/ acc

community

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Alanturner2 updated a Space 11 days ago

open-acc/Summarize-Arxiv-Papers-and-ChatBot

Alanturner2 published a Space 11 days ago

open-acc/Summarize-Arxiv-Papers-and-ChatBot

Alanturner2 updated a Space 11 days ago

open-acc/JambaChatbot

View all activity

open-acc's activity

not-lain

posted an update about 12 hours ago

Post

762

I have just released a new blogpost about kv caching and its role in inference speedup 🚀
🔗 https://huggingface.co/blog/not-lain/kv-caching/
some takeaways :

4 replies

csabakecskemeti

posted an update about 24 hours ago

Post

645

I've made an uncensored version of DeepSeek-R1-Distill-Llama-8B with merge. It's passing the "say f***" censor test.
Tested with lm-evaluation-harness on standard open llm leaderboard tests + hellaswag. Scores are improved in most. Details on the model card.

Model:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B
Quants:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B-GGUF

4 replies

cfahlgren1

posted an update 2 days ago

Post

1054

If you haven't seen yet, we just released Inference Providers 🔀

> 4 new serverless inference providers on the Hub 🤯
> Use your HF API key or personal key with all providers 🔑
> Chat with Deepseek R1, V3, and more on HF Hub 🐋
> We support Sambanova, TogetherAI, Replicate, and Fal.ai 💪

Best of all, we don't charge any markup on top of the provider 🫰 Have you tried it out yet? HF Pro accounts get $2 of free usage for the provider inference.

clem

posted an update 3 days ago

Post

6198

AI is not a zero-sum game. Open-source AI is the tide that lifts all boats!

csabakecskemeti

posted an update 4 days ago

Post

2252

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.

7 replies

clem

posted an update 6 days ago

Post

2102

The 🐳 just crossed 10,000 followers on HF

https://huggingface.co/deepseek-ai

mitkox

posted an update 6 days ago

Post

2033

llama.cpp is 26.8% faster than ollama.
I have upgraded both, and using the same settings, I am running the same DeepSeek R1 Distill 1.5B on the same hardware. It's an Apples to Apples comparison.

Total duration:
llama.cpp 6.85 sec <- 26.8% faster
ollama 8.69 sec

Breakdown by phase:
Model loading
llama.cpp 241 ms <- 2x faster
ollama 553 ms

Prompt processing
llama.cpp 416.04 tokens/s with an eval time 45.67 ms <- 10x faster
ollama 42.17 tokens/s with an eval time of 498 ms

Token generation
llama.cpp 137.79 tokens/s with an eval time 6.62 sec <- 13% faster
ollama 122.07 tokens/s with an eval time 7.64 sec

llama.cpp is LLM inference in C/C++; ollama adds abstraction layers and marketing.

Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.

7 replies

mitkox

posted an update 8 days ago

Post

392

Stargate to the west of me
DeepSeek to the east
Here I am
Stuck in the middle with the EU

It will likely be a matter of sparkle to get export control on frontier research and models on both sides, leaving us in a vacuum.

Decentralized training infrastructure and on device inferencing are the future.

suayptalha

posted an update 8 days ago

Post

1604

My last Falcon3-7B merge model, suayptalha/Falcon3-Jessi-v0.4-7B-Slerp, is currently ranked #1 on the open-llm-leaderboard/open_llm_leaderboard among all models with up to 14B parameters.
My Qwen2.5-7B merge model, suayptalha/HomerCreativeAnvita-Mix-Qw7B, is also ranked #7, placing two of my models in the top 10!

2 replies

mitkox

posted an update 10 days ago

Post

491

On device AI reasoning ODA-R using speculative decoding with draft model DeepSeek-R1-Distill-Qwen-1.5B and DeepSeek-R1-Distill-Qwen-32B. DSPy compiler for reasoning prompts in math, engineering, code...

Alanturner2

updated a Space 11 days ago

Sleeping

🐨

Summarize Arxiv Papers And ChatBot

Summarize arixv papers and chatbot using RAG

Alanturner2

published a Space 11 days ago

Sleeping

🐨

Summarize Arxiv Papers And ChatBot

Summarize arixv papers and chatbot using RAG

Alanturner2

updated a Space 11 days ago

Sleeping

📈

JambaChatbot

Chatbot using New model Jamba(mamba+transformer)

Alanturner2

published a Space 11 days ago

Sleeping

📈

JambaChatbot

Chatbot using New model Jamba(mamba+transformer)

csabakecskemeti

posted an update 11 days ago

Post

473

NVIDIA's new AceInstruct and AceMath models quantized here:

DevQuasar/nvidia-aceinstruct-and-acemath-678d716f736603ddc8d7cbd4

(some still uploading please be patient)

ariG23498

posted an update 11 days ago

Post

1883

Tried my hand at simplifying the derivations of Direct Preference Optimization.

I cover how one can reformulate RLHF into DPO. The idea of implicit reward modeling is chef's kiss.

Blog: https://huggingface.co/blog/ariG23498/rlhf-to-dpo

not-lain

posted an update 13 days ago

Post

1148

we now have more than 2000 public AI models using ModelHubMixin🤗

mitkox

posted an update 14 days ago

Post

1392

Training a model to reason in the continuous latent space based on Meta's Coconut.
If it all works will apply it on the MiniCPM-o SVD-LR.
Endgame is a multimodal, adaptive, and efficient foundational on device AI model.