doing something

You can reduce the translation step right now thanks to this: https://huggingface.co/knowledgator/gliner-x-large-v0.5

115 views15:49

You can reduce the translation step right now thanks to this: https://huggingface.co/knowledgator/gliner-x-large-v0.5

Only one sample was not processed correctly with knowledgator/gliner-x-large-v0.5

But the model is more efficient than previous solution with MamayLM + GLiNER

Colab: https://colab.research.google.com/drive/1tP2gNfvgzscaGKQNkQ0AqBQGSKW6ZUis?usp=sharing

#ai #nlp #pii #security

👍2

399 views16:12

doing something

Only one sample was not processed correctly with knowledgator/gliner-x-large-v0.5 But the model is more efficient than previous solution with MamayLM + GLiNER Colab: https://colab.research.google.com/drive/1tP2gNfvgzscaGKQNkQ0AqBQGSKW6ZUis?usp=sharing #ai…

Also, a test with the translation model. This hybrid solution should give better results.

Colab: https://colab.research.google.com/drive/1fiOSthyg2BI08x4EKNgZOdGC4cD9DQKe?usp=sharing

#ai #pii #security #nlp

111 views16:48

doing something

Photo

Slightly optimized the colab code, now it uses bfloat16 precision

It's more production-ready type of code

🔥1

117 views16:58

doing something

Slightly optimized the colab code, now it uses bfloat16 precision It's more production-ready type of code

And we also can optimize the NER model, just use smaller one

👍3

122 views17:01

doing something

knowledgator/gliner-bi-base-v1.0 + Helsinki-NLP/opus-mt-tc-big-zle-en in float16 precision

All test cases passing, but some entity types incorrectly detected

127 views17:40

doing something

https://arxiv.org/abs/2505.10500

#audio #security

arXiv.org

Quantized Approximate Signal Processing (QASP): Towards...

Audio and speech data are increasingly used in machine learning applications such as speech recognition, speaker identification, and mental health monitoring. However, the passive collection of...

142 views19:29

doing something

https://blog.steelph0enix.dev/posts/llama-cpp-guide/

#nlp

blog.steelph0enix.dev

llama.cpp guide - Running LLMs locally, on any hardware, from scratch

Psst, kid, want some cheap and small LLMs?

134 views23:04

doing something

If you run MamayLM using llama-cpp:


podman run -v ./models:/models --device="nvidia.com/gpu=0" -p 8000:8000 ghcr.io/ggml-org/llama.cpp:server-cuda -m /models/MamayLM-Gemma-2-9B-IT-v0.1.Q4_K_S.gguf --port 8000 --host 0.0.0.0 -n 1024 --n-gpu-layers -1

Then it uses around 1480MiB on GPU

#nlp #llm

150 viewsedited 00:47

doing something

https://github.com/antimatter15/reverse-engineering-gemma-3n

#ml

GitHub

GitHub - antimatter15/reverse-engineering-gemma-3n: Reverse Engineering Gemma 3n: Google's New Edge-Optimized Language Model

Reverse Engineering Gemma 3n: Google's New Edge-Optimized Language Model - antimatter15/reverse-engineering-gemma-3n

152 views09:51

doing something

If you run MamayLM using llama-cpp: podman run -v ./models:/models --device="nvidia.com/gpu=0" -p 8000:8000 ghcr.io/ggml-org/llama.cpp:server-cuda -m /models/MamayLM-Gemma-2-9B-IT-v0.1.Q4_K_S.gguf --port 8000 --host 0.0.0.0 -n 1024 --n-gpu-layers -1 Then…

Experimenting with Gemma 3 and llama-server. gemma-3-1b-it-q4_0.gguf uses around 1350MiB at inference, speed quite high

#llm

154 viewsedited 10:12