Post
590
everywhere i go i see his face
alkinun
AtAndDev
AI & ML interests
LLMs, Alignment, Merging, Unsloth, DPO, SFT, ORPO, SPIN..
Recent Activity
posted
an
update
about 13 hours ago
everywhere i go i see his face
reacted
to
prithivMLmods's
post
with π
about 13 hours ago
Deepswipe by
.
.
.
. Deepseekπ¬πΏ
Everything is now in recovery. ππ
reacted
to
prithivMLmods's
post
with π₯
about 13 hours ago
Deepswipe by
.
.
.
. Deepseekπ¬πΏ
Everything is now in recovery. ππ
Organizations
AtAndDev's activity
posted
an
update
about 13 hours ago
reacted to
prithivMLmods's
post with ππ₯
about 13 hours ago
Post
1162
Deepswipe by
.
.
.
. Deepseekπ¬πΏ
Everything is now in recovery. ππ
.
.
.
. Deepseekπ¬πΏ
Everything is now in recovery. ππ
- 2 replies
liked
a
model
4 days ago
reacted to
onekq's
post with π
5 days ago
Post
2224
So πDeepSeekπ hits the mainstream media. But it has been a star in our little cult for at least 6 months. Its meteoric success is not overnight, but two years in the making.
To learn their history, just look at their π€ repo https://huggingface.co/deepseek-ai
* End of 2023, they launched the first model (pretrained by themselves) following Llama 2 architecture
* June 2024, v2 (MoE architecture) surpassed Gemini 1.5, but behind Mistral
* September, v2.5 surpassed GPT 4o mini
* December, v3 surpassed GPT 4o
* Now R1 surpassed o1
Most importantly, if you think DeepSeek success is singular and unrivaled, that's WRONG. The following models are also near or equal the o1 bar.
* Minimax-01
* Kimi k1.5
* Doubao 1.5 pro
To learn their history, just look at their π€ repo https://huggingface.co/deepseek-ai
* End of 2023, they launched the first model (pretrained by themselves) following Llama 2 architecture
* June 2024, v2 (MoE architecture) surpassed Gemini 1.5, but behind Mistral
* September, v2.5 surpassed GPT 4o mini
* December, v3 surpassed GPT 4o
* Now R1 surpassed o1
Most importantly, if you think DeepSeek success is singular and unrivaled, that's WRONG. The following models are also near or equal the o1 bar.
* Minimax-01
* Kimi k1.5
* Doubao 1.5 pro
- 1 reply
i believe sglang would be even faster but not sure if it supports non-nvidia devices
upvoted
a
collection
6 days ago
liked
2
models
6 days ago
reacted to
chansung's
post with π₯
6 days ago
Post
1973
Simple Summarization on DeepSeek-R1 from DeepSeek AI
The RL stage is very important.
β³ However, it is difficult to create a truly helpful AI for people solely through RL.
β³ So, we applied a learning pipeline consisting of four stages: providing a good starting point, reasoning RL, SFT, and safety RL, and achieved performance comparable to o1.
β³ Simply fine-tuning other open models with the data generated by R1-Zero (distillation) resulted in performance comparable to o1-mini.
Of course, this is just a brief overview and may not be of much help. All models are accessible on Hugging Face, and the paper can be read through the GitHub repository.
Model: https://huggingface.co/deepseek-ai
Paper: https://github.com/deepseek-ai/DeepSeek-R1
The RL stage is very important.
β³ However, it is difficult to create a truly helpful AI for people solely through RL.
β³ So, we applied a learning pipeline consisting of four stages: providing a good starting point, reasoning RL, SFT, and safety RL, and achieved performance comparable to o1.
β³ Simply fine-tuning other open models with the data generated by R1-Zero (distillation) resulted in performance comparable to o1-mini.
Of course, this is just a brief overview and may not be of much help. All models are accessible on Hugging Face, and the paper can be read through the GitHub repository.
Model: https://huggingface.co/deepseek-ai
Paper: https://github.com/deepseek-ai/DeepSeek-R1
- 1 reply
replied to
nroggendorff's
post
6 days ago
some ppl cant just get enough
updated
a
dataset
6 days ago
reacted to
ezgikorkmaz's
post with ππ
7 days ago
Post
1639
If you are interested in reinforcement learning, a recent paper I wrote introduces foundational analysis on deep reinforcement learning decision making and representations learnt by it.
Link: https://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lfpgsrn6sc2m
Link: https://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lfpgsrn6sc2m
- 1 reply
reacted to
sharpenb's
post with π
7 days ago
Post
1840
We compressed SmolLMs to make 135 variations of them (see https://huggingface.co/PrunaAI?search_models=smolLM) with different quantization configurations with
We made a blog to summarize our findings (see https://www.pruna.ai/blog/smollm2-smaller-faster) and small LM can be made smaller! :)
pruna (https://docs.pruna.ai/en/latest/). We made a blog to summarize our findings (see https://www.pruna.ai/blog/smollm2-smaller-faster) and small LM can be made smaller! :)
-
- 3 replies
That non centered emoji...
But cool blog
published
a
dataset
7 days ago
upvoted
a
collection
7 days ago
reacted to
sometimesanotion's
post with ππ₯
7 days ago
Post
2582
I've managed a #1 score of 41.22% average for 14B parameter models on the Open LLM Leaderboard. As of this writing, sometimesanotion/Lamarck-14B-v0.7 is #8 for all models up to 70B parameters.
It took a custom toolchain around Arcee AI's mergekit to manage the complex merges, gradients, and LoRAs required to make this happen. I really like seeing features of many quality finetunes in one solid generalist model.
It took a custom toolchain around Arcee AI's mergekit to manage the complex merges, gradients, and LoRAs required to make this happen. I really like seeing features of many quality finetunes in one solid generalist model.
- 5 replies