sweatSmile/Phi3-Mini-FinSight-FinancialQA
Text Generation
•
4B
•
Updated
•
6
•
1
amitk17 PRO
sweatSmile
AI & ML interests
Training LLMs • Prompt Engineering • Fine-tuning • Retrieval-Augmented Generation (RAG) • LoRA • NLP • Educational AI • Financial NLP • Chatbot Design • Model Deployment • Transformers • Open-Source Contributions
Recent Activity
updated
a model
about 2 months ago
sweatSmile/Phi3-Mini-FinSight-FinancialQA
liked
a model
about 2 months ago
sweatSmile/Phi3-Mini-FinSight-FinancialQA
published
a model
about 2 months ago
sweatSmile/Phi3-Mini-FinSight-FinancialQA
Organizations
updated
a
model
about 2 months ago
liked
a
model
about 2 months ago
published
a
model
about 2 months ago
published
a
dataset
about 2 months ago
reacted to
anakin87's
post with 👍
about 2 months ago
Post
1088
Haystack can now see 👀
The latest release of the Haystack OSS LLM framework adds a long-requested feature: image support!
📓 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?
🧠 Support for multiple LLM providers: OpenAI, Amazon Bedrock, Google Gemini, Mistral, NVIDIA, OpenRouter, Ollama and more (support for Hugging Face API coming 🔜)
🎛️ Prompt template language to handle structured inputs, including images
📄 PDF and image converters
🔍 Image embedders using CLIP-like models
🧾 LLM-based extractor to pull text from images
🧩 Components to build multimodal RAG pipelines and Agents
I had the chance of leading this effort with @sjrhuschlee (great collab).
📓 Below you can find two notebooks to explore the new features:
• Introduction to Multimodal Text Generation https://haystack.deepset.ai/cookbook/multimodal_intro
• Creating Vision+Text RAG Pipelines https://haystack.deepset.ai/tutorials/46_multimodal_rag
(🖼️ image by @bilgeyucel )
The latest release of the Haystack OSS LLM framework adds a long-requested feature: image support!
📓 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?
🧠 Support for multiple LLM providers: OpenAI, Amazon Bedrock, Google Gemini, Mistral, NVIDIA, OpenRouter, Ollama and more (support for Hugging Face API coming 🔜)
🎛️ Prompt template language to handle structured inputs, including images
📄 PDF and image converters
🔍 Image embedders using CLIP-like models
🧾 LLM-based extractor to pull text from images
🧩 Components to build multimodal RAG pipelines and Agents
I had the chance of leading this effort with @sjrhuschlee (great collab).
📓 Below you can find two notebooks to explore the new features:
• Introduction to Multimodal Text Generation https://haystack.deepset.ai/cookbook/multimodal_intro
• Creating Vision+Text RAG Pipelines https://haystack.deepset.ai/tutorials/46_multimodal_rag
(🖼️ image by @bilgeyucel )
reacted to
their
post with 🔥
about 2 months ago
Post
1124
some of my fav where i run jobs
https://huggingface.co/docs/huggingface_hub/main/en/guides/cli#hf-jobs
https://lightning.ai/
https://colab.research.google.com/
https://www.runpod.io/console/deploy
ps: I ❤️ hf
https://huggingface.co/docs/huggingface_hub/main/en/guides/cli#hf-jobs
https://lightning.ai/
https://colab.research.google.com/
https://www.runpod.io/console/deploy
ps: I ❤️ hf
reacted to
prithivMLmods's
post with 🚀
about 2 months ago
Post
3893
Build something cool with Nano Banana aka Gemini 2.5 Flash Image AIO [All-in-One]. Draw and transform on canvas, edit images, and generate images—all in one place!🍌
✦︎ Constructed with the Gemini API (GCP). Try it here: prithivMLmods/Nano-Banana-AIO (Added the Space recently! - Sep 18 '25)
✦︎ Constructed with the Gemini API (GCP). Try it here: prithivMLmods/Nano-Banana-AIO (Added the Space recently! - Sep 18 '25)
- 4 replies
reacted to
Kseniase's
post with 🚀
about 2 months ago
Post
6160
10 awesome advanced LoRA approaches
Low-Rank Adaptation (LoRA) is the go-to method for efficient model fine-tuning that adds small low-rank matrices instead of retraining full models. The field isn’t standing still – new LoRA variants push the limits of efficiency, generalization, and personalization. So we’re sharing 10 of the latest LoRA approaches you should know about:
1. Mixture-of-LoRA-experts → Mixture of Low-Rank Adapter Experts in Generalizable Audio Deepfake Detection (2509.13878)
Adds multiple low-rank adapters (LoRA) into a model’s layers, and a routing mechanism activates the most suitable ones for each input. This lets the model adapt better to new unseen conditions
2. Amortized Bayesian Meta-Learning for LoRA (ABMLL) → Amortized Bayesian Meta-Learning for Low-Rank Adaptation of Large Language Models (2508.14285)
Balances global and task-specific parameters within a Bayesian framework to improve uncertainty calibration and generalization to new tasks without high memory or compute costs
3. AutoLoRA → AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation (2508.02107)
Automatically retrieves and dynamically aggregates public LoRAs for stronger T2I generation
4. aLoRA (Activated LoRA) → Activated LoRA: Fine-tuned LLMs for Intrinsics (2504.12397)
Only applies LoRA after invocation, letting the model reuse the base model’s KV cache instead of recomputing the full turn’s KV cache. Efficient in multi-turn conversations
5. LiLoRA (LoRA in LoRA) → LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning (2508.06202)
Shares the LoRA matrix A across tasks and additionally low-rank-decomposes matrix B to cut parameters in continual vision-text MLLMs
6. Sensitivity-LoRA → Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models (2509.09119)
Dynamically assigns ranks to weight matrices based on their sensitivity, measured using second-order derivatives
Read further below ↓
Also, subscribe to the Turing Post: https://www.turingpost.com/subscribe
Low-Rank Adaptation (LoRA) is the go-to method for efficient model fine-tuning that adds small low-rank matrices instead of retraining full models. The field isn’t standing still – new LoRA variants push the limits of efficiency, generalization, and personalization. So we’re sharing 10 of the latest LoRA approaches you should know about:
1. Mixture-of-LoRA-experts → Mixture of Low-Rank Adapter Experts in Generalizable Audio Deepfake Detection (2509.13878)
Adds multiple low-rank adapters (LoRA) into a model’s layers, and a routing mechanism activates the most suitable ones for each input. This lets the model adapt better to new unseen conditions
2. Amortized Bayesian Meta-Learning for LoRA (ABMLL) → Amortized Bayesian Meta-Learning for Low-Rank Adaptation of Large Language Models (2508.14285)
Balances global and task-specific parameters within a Bayesian framework to improve uncertainty calibration and generalization to new tasks without high memory or compute costs
3. AutoLoRA → AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation (2508.02107)
Automatically retrieves and dynamically aggregates public LoRAs for stronger T2I generation
4. aLoRA (Activated LoRA) → Activated LoRA: Fine-tuned LLMs for Intrinsics (2504.12397)
Only applies LoRA after invocation, letting the model reuse the base model’s KV cache instead of recomputing the full turn’s KV cache. Efficient in multi-turn conversations
5. LiLoRA (LoRA in LoRA) → LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning (2508.06202)
Shares the LoRA matrix A across tasks and additionally low-rank-decomposes matrix B to cut parameters in continual vision-text MLLMs
6. Sensitivity-LoRA → Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models (2509.09119)
Dynamically assigns ranks to weight matrices based on their sensitivity, measured using second-order derivatives
Read further below ↓
Also, subscribe to the Turing Post: https://www.turingpost.com/subscribe
- 3 replies
upvoted
4
papers
about 2 months ago
LimRank: Less is More for Reasoning-Intensive Information Reranking
Paper
•
2510.23544
•
Published
•
8
E^2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
Paper
•
2510.22733
•
Published
•
31
A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
Paper
•
2510.23587
•
Published
•
65
Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
Paper
•
2510.23607
•
Published
•
177
liked
a
model
2 months ago
updated
a
model
2 months ago
published
a
model
2 months ago
liked
a
model
2 months ago
updated
a
model
2 months ago
published
a
model
2 months ago
reacted to
Kseniase's
post with ❤️👍
3 months ago
Post
6160
10 awesome advanced LoRA approaches
Low-Rank Adaptation (LoRA) is the go-to method for efficient model fine-tuning that adds small low-rank matrices instead of retraining full models. The field isn’t standing still – new LoRA variants push the limits of efficiency, generalization, and personalization. So we’re sharing 10 of the latest LoRA approaches you should know about:
1. Mixture-of-LoRA-experts → Mixture of Low-Rank Adapter Experts in Generalizable Audio Deepfake Detection (2509.13878)
Adds multiple low-rank adapters (LoRA) into a model’s layers, and a routing mechanism activates the most suitable ones for each input. This lets the model adapt better to new unseen conditions
2. Amortized Bayesian Meta-Learning for LoRA (ABMLL) → Amortized Bayesian Meta-Learning for Low-Rank Adaptation of Large Language Models (2508.14285)
Balances global and task-specific parameters within a Bayesian framework to improve uncertainty calibration and generalization to new tasks without high memory or compute costs
3. AutoLoRA → AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation (2508.02107)
Automatically retrieves and dynamically aggregates public LoRAs for stronger T2I generation
4. aLoRA (Activated LoRA) → Activated LoRA: Fine-tuned LLMs for Intrinsics (2504.12397)
Only applies LoRA after invocation, letting the model reuse the base model’s KV cache instead of recomputing the full turn’s KV cache. Efficient in multi-turn conversations
5. LiLoRA (LoRA in LoRA) → LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning (2508.06202)
Shares the LoRA matrix A across tasks and additionally low-rank-decomposes matrix B to cut parameters in continual vision-text MLLMs
6. Sensitivity-LoRA → Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models (2509.09119)
Dynamically assigns ranks to weight matrices based on their sensitivity, measured using second-order derivatives
Read further below ↓
Also, subscribe to the Turing Post: https://www.turingpost.com/subscribe
Low-Rank Adaptation (LoRA) is the go-to method for efficient model fine-tuning that adds small low-rank matrices instead of retraining full models. The field isn’t standing still – new LoRA variants push the limits of efficiency, generalization, and personalization. So we’re sharing 10 of the latest LoRA approaches you should know about:
1. Mixture-of-LoRA-experts → Mixture of Low-Rank Adapter Experts in Generalizable Audio Deepfake Detection (2509.13878)
Adds multiple low-rank adapters (LoRA) into a model’s layers, and a routing mechanism activates the most suitable ones for each input. This lets the model adapt better to new unseen conditions
2. Amortized Bayesian Meta-Learning for LoRA (ABMLL) → Amortized Bayesian Meta-Learning for Low-Rank Adaptation of Large Language Models (2508.14285)
Balances global and task-specific parameters within a Bayesian framework to improve uncertainty calibration and generalization to new tasks without high memory or compute costs
3. AutoLoRA → AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation (2508.02107)
Automatically retrieves and dynamically aggregates public LoRAs for stronger T2I generation
4. aLoRA (Activated LoRA) → Activated LoRA: Fine-tuned LLMs for Intrinsics (2504.12397)
Only applies LoRA after invocation, letting the model reuse the base model’s KV cache instead of recomputing the full turn’s KV cache. Efficient in multi-turn conversations
5. LiLoRA (LoRA in LoRA) → LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning (2508.06202)
Shares the LoRA matrix A across tasks and additionally low-rank-decomposes matrix B to cut parameters in continual vision-text MLLMs
6. Sensitivity-LoRA → Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models (2509.09119)
Dynamically assigns ranks to weight matrices based on their sensitivity, measured using second-order derivatives
Read further below ↓
Also, subscribe to the Turing Post: https://www.turingpost.com/subscribe
-
-
-
- 3 replies