katanemo/Arch-Function-3B
Text Generation
•
Updated
•
556
•
109
t1u1
t1u1
AI & ML interests
None yet
Recent Activity
liked
a model
4 days ago
katanemo/Arch-Function-3B
liked
a model
5 days ago
nomic-ai/nomic-embed-text-v2-moe
liked
a model
7 days ago
bartowski/simplescaling_s1.1-32B-GGUF
Organizations
None yet
t1u1's activity
liked
a
model
4 days ago
liked
a
model
5 days ago
liked
a
model
7 days ago
upvoted
2
papers
7 days ago
reacted to
schuler's
post with 👍
8 days ago
Post
7184
📢 New Research Alert: Making Language Models Smaller & Smarter!
Thrilled to share the latest technical report demonstrating how to reduce language model parameters by 77% while maintaining performance.
The secret? Grouped pointwise convolutions. Yes. We brought a method from computer vision to the transformers arena.
🔑 Key Findings:
• 77% parameter reduction.
• Maintained model capabilities.
• Improved generalization.
Paper: https://www.researchgate.net/publication/388835829_SAVING_77_OF_THE_PARAMETERS_IN_LARGE_LANGUAGE_MODELS_TECHNICAL_REPORT
Code: https://github.com/joaopauloschuler/less-parameters-llm
Thrilled to share the latest technical report demonstrating how to reduce language model parameters by 77% while maintaining performance.
The secret? Grouped pointwise convolutions. Yes. We brought a method from computer vision to the transformers arena.
🔑 Key Findings:
• 77% parameter reduction.
• Maintained model capabilities.
• Improved generalization.
Paper: https://www.researchgate.net/publication/388835829_SAVING_77_OF_THE_PARAMETERS_IN_LARGE_LANGUAGE_MODELS_TECHNICAL_REPORT
Code: https://github.com/joaopauloschuler/less-parameters-llm
- 2 replies
liked
a
model
8 days ago
upvoted
a
collection
10 days ago
upvoted
a
paper
14 days ago
liked
a
model
21 days ago
liked
a
model
22 days ago
reacted to
mitkox's
post with 👍
23 days ago
Post
2322
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.
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
reacted to
lewtun's
post with 🚀
23 days ago
Post
10114
We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open!
🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1.
🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code.
🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training.
Follow along: https://github.com/huggingface/open-r1
🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1.
🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code.
🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training.
Follow along: https://github.com/huggingface/open-r1
- 5 replies
liked
a
model
23 days ago
liked
2
models
24 days ago
upvoted
an
article
26 days ago
Article
FuseO1-Preview: System-II Reasoning Fusion of LLMs
By
and 4 others
•
•
16
upvoted
a
paper
27 days ago
Can you please create weighted/imatrix quant versions?
#1 opened 28 days ago
by
t1u1
liked
a
model
about 1 month ago