deepseek-ai/DeepSeek-V3
Text Generation
•
Updated
•
248k
•
2.33k
Paraskevi Kivroglou
KvrParaskevi
AI & ML interests
I am looking forward into a world full of AI innovation. By having small ideas in new projects, I want to take the next step and give them life.
Recent Activity
liked
a model
9 days ago
deepseek-ai/DeepSeek-V3
liked
a dataset
16 days ago
semeru/code-text-python
liked
a dataset
19 days ago
CodeEval-Pro/mbpp-pro
Organizations
KvrParaskevi's activity
liked
a
model
9 days ago
liked
a
dataset
16 days ago
liked
a
dataset
19 days ago
liked
2
datasets
20 days ago
liked
a
dataset
22 days ago
liked
a
model
23 days ago
liked
2
datasets
about 1 month ago
upvoted
a
paper
2 months ago
liked
a
model
2 months ago
liked
a
dataset
2 months ago
liked
a
dataset
3 months ago
liked
a
model
3 months ago
reacted to
reach-vb's
post with 🚀
3 months ago
Post
3010
Smol models ftw! AMD released AMD OLMo 1B - beats OpenELM, tiny llama on MT Bench, Alpaca Eval - Apache 2.0 licensed 🔥
> Trained with 1.3 trillion (dolma 1.7) tokens on 16 nodes, each with 4 MI250 GPUs
> Three checkpoints:
- AMD OLMo 1B: Pre-trained model
- AMD OLMo 1B SFT: Supervised fine-tuned on Tulu V2, OpenHermes-2.5, WebInstructSub, and Code-Feedback datasets
- AMD OLMo 1B SFT DPO: Aligned with human preferences using Direct Preference Optimization (DPO) on UltraFeedback dataset
Key Insights:
> Pre-trained with less than half the tokens of OLMo-1B
> Post-training steps include two-phase SFT and DPO alignment
> Data for SFT:
- Phase 1: Tulu V2
- Phase 2: OpenHermes-2.5, WebInstructSub, and Code-Feedback
> Model checkpoints on the Hub & Integrated with Transformers ⚡️
Congratulations & kudos to AMD on a brilliant smol model release! 🤗
amd/amd-olmo-6723e7d04a49116d8ec95070
> Trained with 1.3 trillion (dolma 1.7) tokens on 16 nodes, each with 4 MI250 GPUs
> Three checkpoints:
- AMD OLMo 1B: Pre-trained model
- AMD OLMo 1B SFT: Supervised fine-tuned on Tulu V2, OpenHermes-2.5, WebInstructSub, and Code-Feedback datasets
- AMD OLMo 1B SFT DPO: Aligned with human preferences using Direct Preference Optimization (DPO) on UltraFeedback dataset
Key Insights:
> Pre-trained with less than half the tokens of OLMo-1B
> Post-training steps include two-phase SFT and DPO alignment
> Data for SFT:
- Phase 1: Tulu V2
- Phase 2: OpenHermes-2.5, WebInstructSub, and Code-Feedback
> Model checkpoints on the Hub & Integrated with Transformers ⚡️
Congratulations & kudos to AMD on a brilliant smol model release! 🤗
amd/amd-olmo-6723e7d04a49116d8ec95070
replied to
di-zhang-fdu's
post
3 months ago
Awesome work. Can we finetune further this reasoning model?
reacted to
di-zhang-fdu's
post with 👍
3 months ago
Post
6399
LLaMA-O1: Open Large Reasoning Model Frameworks For Training, Inference and Evaluation With PyTorch and HuggingFace
Large Reasoning Models powered by Monte Carlo Tree Search (MCTS), Self-Play Reinforcement Learning, PPO, AlphaGo Zero's dua policy paradigm and Large Language Models!
https://github.com/SimpleBerry/LLaMA-O1/
What will happen when you compound MCTS ❤ LLM ❤ Self-Play ❤RLHF?
Just a little bite of strawberry!🍓
Past related works:
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning (2410.02884)
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B (2406.07394)
Large Reasoning Models powered by Monte Carlo Tree Search (MCTS), Self-Play Reinforcement Learning, PPO, AlphaGo Zero's dua policy paradigm and Large Language Models!
https://github.com/SimpleBerry/LLaMA-O1/
What will happen when you compound MCTS ❤ LLM ❤ Self-Play ❤RLHF?
Just a little bite of strawberry!🍓
Past related works:
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning (2410.02884)
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B (2406.07394)
-
- 2 replies
upvoted
a
paper
3 months ago
liked
a
model
3 months ago
reacted to
nroggendorff's
post with 👀
3 months ago
Post
2657
When huggingface patches this, I'm going to be really sad, but in the meantime, here you go:
When AutoTrain creates a new space to train your model, it does so via the huggingface API. If you modify the code so that it includes a premade README.md file, you can add these two lines:
This will tell huggingface to listen for the iframe on your port, instead of the one autotrain is actually hosting on, and because startup time isn't charged, you get the product for free. (you can take this even further by switching compute type to A100 or something)
When AutoTrain creates a new space to train your model, it does so via the huggingface API. If you modify the code so that it includes a premade README.md file, you can add these two lines:
---
app_port: 8080 # or any integer besides 7860 that's greater than 2 ** 10
startup_duration_timeout: 350m
---This will tell huggingface to listen for the iframe on your port, instead of the one autotrain is actually hosting on, and because startup time isn't charged, you get the product for free. (you can take this even further by switching compute type to A100 or something)
- 1 reply