Train a SLM to create a schedule from a list of events and priorities - Article: https://t.ly/-Dejx - Code: https://t.ly/1J_VG
Stefano Fiorucci PRO
anakin87
AI & ML interests
Contributing to Haystack LLM framework ๐๏ธ. Language Models: orchestration, post-training, synthetic data...
Recent Activity
updated
a Space
1 day ago
anakin87/fact-checking-rocks
posted
an
update
4 days ago
Haystack can now see ๐
The latest release of the Haystack OSS LLM framework adds a long-requested feature: image support!
๐ Notebooks below
This isn't just about passing images to an LLM. We built several features to enable practical multimodal use cases.
What's new?
๐ง Support for multiple LLM providers: OpenAI, Amazon Bedrock, Google Gemini, Mistral, NVIDIA, OpenRouter, Ollama and more (support for Hugging Face API coming ๐)
๐๏ธ Prompt template language to handle structured inputs, including images
๐ PDF and image converters
๐ Image embedders using CLIP-like models
๐งพ LLM-based extractor to pull text from images
๐งฉ Components to build multimodal RAG pipelines and Agents
I had the chance of leading this effort with @sjrhuschlee (great collab).
๐ Below you can find two notebooks to explore the new features:
๓ ฏโข๓ ๓ Introduction to Multimodal Text Generation https://haystack.deepset.ai/cookbook/multimodal_intro
๓ ฏโข๓ ๓ Creating Vision+Text RAG Pipelines https://haystack.deepset.ai/tutorials/46_multimodal_rag
(๐ผ๏ธ image by @bilgeyucel )
liked
a model
6 days ago
Pramodith/topN_sigma_generation
Organizations
Starting from 2024-11-15
-
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper โข 2504.13837 โข Published โข 134 -
Understanding R1-Zero-Like Training: A Critical Perspective
Paper โข 2503.20783 โข Published โข 57 -
Inference-Time Scaling for Generalist Reward Modeling
Paper โข 2504.02495 โข Published โข 57 -
Large Language Diffusion Models
Paper โข 2502.09992 โข Published โข 122
Datasets and models for Neogenesis: Post-training recipe for improving Gemma 2 for a specific language. Notebook: https://t.ly/iuKdy
-
anakin87/gemma-2-9b-neogenesis-ita
Text Generation โข 9B โข Updated โข 2.04k โข โข 10 -
anakin87/gemma-2-2b-neogenesis-ita
Text Generation โข 3B โข Updated โข 2.05k โข โข 6 -
Gemma 2 9B Neogenesis ITA
๐9B Italian strong model ๐ช
-
3
Gemma 2 2B Neogenesis ITA
๐Chat with an Italian Small Model
I tried to merge two of the best Italian LLMs using Mergekit. The results are acceptable, but I could not improve on the best existing model.
-
anakin87/Llama-3-8b-ita-ties-pro
Text Generation โข 8B โข Updated โข 3.58k โข โข 1 -
anakin87/Llama-3-8b-ita-slerp
Text Generation โข 8B โข Updated โข 3.58k โข โข 1 -
anakin87/Llama-3-8b-ita-ties
Text Generation โข 8B โข Updated โข 2.24k โข โข 3 -
NikolayKozloff/Llama-3-8b-ita-ties-Q8_0-GGUF
8B โข Updated โข 1
Train a SLM to create a schedule from a list of events and priorities - Article: https://t.ly/-Dejx - Code: https://t.ly/1J_VG
Datasets and models for Neogenesis: Post-training recipe for improving Gemma 2 for a specific language. Notebook: https://t.ly/iuKdy
-
anakin87/gemma-2-9b-neogenesis-ita
Text Generation โข 9B โข Updated โข 2.04k โข โข 10 -
anakin87/gemma-2-2b-neogenesis-ita
Text Generation โข 3B โข Updated โข 2.05k โข โข 6 -
Gemma 2 9B Neogenesis ITA
๐9B Italian strong model ๐ช
-
3
Gemma 2 2B Neogenesis ITA
๐Chat with an Italian Small Model
Starting from 2024-11-15
-
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper โข 2504.13837 โข Published โข 134 -
Understanding R1-Zero-Like Training: A Critical Perspective
Paper โข 2503.20783 โข Published โข 57 -
Inference-Time Scaling for Generalist Reward Modeling
Paper โข 2504.02495 โข Published โข 57 -
Large Language Diffusion Models
Paper โข 2502.09992 โข Published โข 122
I tried to merge two of the best Italian LLMs using Mergekit. The results are acceptable, but I could not improve on the best existing model.
-
anakin87/Llama-3-8b-ita-ties-pro
Text Generation โข 8B โข Updated โข 3.58k โข โข 1 -
anakin87/Llama-3-8b-ita-slerp
Text Generation โข 8B โข Updated โข 3.58k โข โข 1 -
anakin87/Llama-3-8b-ita-ties
Text Generation โข 8B โข Updated โข 2.24k โข โข 3 -
NikolayKozloff/Llama-3-8b-ita-ties-Q8_0-GGUF
8B โข Updated โข 1