Hugging Face's logo
Tech Meld's picture
9 1 18

Tech Meld

Tech-Meld
sensui3's profile picture Mi6paulino's profile picture Gargaz's profile picture
·

AI & ML interests

I love ML, i have been learning it since summer of 2023, a lot of things have happened since, from basic knowledge to creation of self-made language models and diffusion models, everything is still in early stages, but work is still done.

Recent Activity

replied to mitkox's post about 2 months ago
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.
new activity about 2 months ago
HuggingFaceTB/SmolVLM-256M-Instruct:There is an issue with AutoProcessor
replied to mitkox's post about 2 months ago
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.
View all activity

Organizations

None yet

Tech-Meld's activity

New activity in HuggingFaceTB/SmolVLM-256M-Instruct about 2 months ago

There is an issue with AutoProcessor

3
#6 opened about 2 months ago by
Tech-Meld
New activity in yuntian-deng/o1 2 months ago

update needed

2
#25 opened 2 months ago by
philippemartel1980
New activity in yuntian-deng/o1mini 4 months ago

This space is no longer working
#11 opened 4 months ago by
Tech-Meld
New activity in yuntian-deng/o1 5 months ago

App no longer working

3
#14 opened 5 months ago by
Tech-Meld
New activity in THUDM/LongWriter 7 months ago

Benchmarking concerns

2
#2 opened 7 months ago by
Tech-Meld
New activity in bdsqlsz/Florence-2-SD3-Captioner 8 months ago

Update requirements.txt

1
#1 opened 8 months ago by
Tech-Meld
New activity in DeepFloyd/IF 9 months ago

Update requirements.txt

1
#491 opened 9 months ago by
Tech-Meld
New activity in multimodalart/LoraTheExplorer 9 months ago

Check out my new LoRA Chips & Dies, it is suited for generating images about processors and chips
#193 opened 9 months ago by
Tech-Meld
New activity in yuntian-deng/ChatGPT4Turbo 10 months ago

Fixing Model Output GUI

1
#5 opened 10 months ago by
Tech-Meld