497
Gemma 3
🔥
@video-infer @gemma3 @lightningv5 @tts2
Rahim Khan
rahim-xelpmoc
·
AI & ML interests
None yet
Recent Activity
liked
a Space
2 days ago
prithivMLmods/Gemma-3-Multimodal
updated
a model
18 days ago
rahim-xelpmoc/siglip2-base-patch16-384
published
a model
18 days ago
rahim-xelpmoc/siglip2-base-patch16-384
Organizations
None yet
rahim-xelpmoc's activity
liked
a
Space
2 days ago
updated
a
model
18 days ago
published
a
model
18 days ago
reacted to
AdinaY's
post with 😎
24 days ago
Post
2445
The latest paper of DeepSeek is now available on the Daily Papers page 🚀
You can reach out to the authors directly on this page👇
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2502.11089)
You can reach out to the authors directly on this page👇
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2502.11089)
- 1 reply
liked
a
model
29 days ago
reacted to
nicolay-r's
post with 🔥
about 1 month ago
Post
1621
📢 The LLaMA-3.1-8B distilled 8B version of the R1 DeepSeek AI is available besides the one based on Qwen
📙 Notebook for using it in reasoning over series of data 🧠 :
https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_deep_seek_7b_distill_llama3.ipynb
Loading using the pipeline API of the transformers library:
https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_llama.py
🟡 GPU Usage: 12.3 GB (FP16/FP32 mode) which is suitable for T4. (a 1.5 GB less than Qwen-distilled version)
🐌 Perfomance: T4 instance: ~0.19 tokens/sec (FP32 mode) and (FP16 mode) ~0.22-0.30 tokens/sec. Is it should be that slow? 🤔
Model name: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
⭐ Framework: https://github.com/nicolay-r/bulk-chain
🌌 Notebooks and models hub: https://github.com/nicolay-r/nlp-thirdgate
📙 Notebook for using it in reasoning over series of data 🧠 :
https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_deep_seek_7b_distill_llama3.ipynb
Loading using the pipeline API of the transformers library:
https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_llama.py
🟡 GPU Usage: 12.3 GB (FP16/FP32 mode) which is suitable for T4. (a 1.5 GB less than Qwen-distilled version)
🐌 Perfomance: T4 instance: ~0.19 tokens/sec (FP32 mode) and (FP16 mode) ~0.22-0.30 tokens/sec. Is it should be that slow? 🤔
Model name: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
⭐ Framework: https://github.com/nicolay-r/bulk-chain
🌌 Notebooks and models hub: https://github.com/nicolay-r/nlp-thirdgate