GGUF My Repo
🦙
1.84k
Convert and quantize Hugging Face models to GGUF format quickly
Zixi "Oz" Li
OzTianlu
AI & ML interests
My research focuses on deep reasoning with small language models, Transformer architecture innovation, and knowledge distillation for efficient alignment and transfer.
Recent Activity
liked
a Space
about 20 hours ago
ggml-org/gguf-my-repo
updated
a collection
5 days ago
Geilim Large Language Models
reacted
to
their
post
with 🔥
5 days ago
Geilim-1B-SR-Instruct — Serbian Intelligence for Deep Reasoning 🧠🇷🇸
https://huggingface.co/NoesisLab/Geilim-1B-SR-Instruct
Geilim-1B-SR-Instruct is a lightweight Large Language Model (LLM) designed to bring advanced reasoning capabilities to low-resource languages. It focuses on Serbian understanding and generation while maintaining robust English reasoning. Built on the LLaMA-3 architecture with a proprietary hybrid reasoning mechanism, it delivers deep logic while keeping outputs concise and natural. 🚀
Core Innovations 💡
Implicit Deep Reasoning: Combines standard attention mechanisms with graph-structured reasoning components for rigorous logic and causal inference. 🕸️
ASPP & -flow Hybrid Design: High-efficiency structured propagation + internal probability space optimization for high-quality reasoning without long-winded intermediate steps. ⚡
Bilingual Adaptation: Primarily focused on Serbian while preserving English logic, making it perfect for multilingual chats and cross-lingual tasks. 🌍
Lightweight & Efficient: At ~1.3B parameters, it runs smoothly on consumer-grade GPUs, ideal for edge devices and research. 💻
Use Cases 🛠️
Serbian Chatbots: Intelligent assistants with local linguistic nuance. 🗣️
Educational Tools: Multi-turn interactive tasks and learning support. 📚
Key Advantages ✨
Clean Output: Avoids messy "thinking" tags; reasoning happens internally, delivering clear and direct results. ✅
Open Access: Licensed under Apache-2.0, making it easy for research and engineering integration. 🔓
AI Democratization: Empowering low-resource language ecosystems with cutting-edge intelligence. 🤝
Organizations
liked
a
Space
about 20 hours ago
updated
a
collection
5 days ago
reacted to
their
post with 🔥
5 days ago
Post
2756
Geilim-1B-SR-Instruct — Serbian Intelligence for Deep Reasoning 🧠🇷🇸
NoesisLab/Geilim-1B-SR-Instruct
Geilim-1B-SR-Instruct is a lightweight Large Language Model (LLM) designed to bring advanced reasoning capabilities to low-resource languages. It focuses on Serbian understanding and generation while maintaining robust English reasoning. Built on the LLaMA-3 architecture with a proprietary hybrid reasoning mechanism, it delivers deep logic while keeping outputs concise and natural. 🚀
Core Innovations 💡
Implicit Deep Reasoning: Combines standard attention mechanisms with graph-structured reasoning components for rigorous logic and causal inference. 🕸️
ASPP & -flow Hybrid Design: High-efficiency structured propagation + internal probability space optimization for high-quality reasoning without long-winded intermediate steps. ⚡
Bilingual Adaptation: Primarily focused on Serbian while preserving English logic, making it perfect for multilingual chats and cross-lingual tasks. 🌍
Lightweight & Efficient: At ~1.3B parameters, it runs smoothly on consumer-grade GPUs, ideal for edge devices and research. 💻
Use Cases 🛠️
Serbian Chatbots: Intelligent assistants with local linguistic nuance. 🗣️
Educational Tools: Multi-turn interactive tasks and learning support. 📚
Key Advantages ✨
Clean Output: Avoids messy "thinking" tags; reasoning happens internally, delivering clear and direct results. ✅
Open Access: Licensed under Apache-2.0, making it easy for research and engineering integration. 🔓
AI Democratization: Empowering low-resource language ecosystems with cutting-edge intelligence. 🤝
NoesisLab/Geilim-1B-SR-Instruct
Geilim-1B-SR-Instruct is a lightweight Large Language Model (LLM) designed to bring advanced reasoning capabilities to low-resource languages. It focuses on Serbian understanding and generation while maintaining robust English reasoning. Built on the LLaMA-3 architecture with a proprietary hybrid reasoning mechanism, it delivers deep logic while keeping outputs concise and natural. 🚀
Core Innovations 💡
Implicit Deep Reasoning: Combines standard attention mechanisms with graph-structured reasoning components for rigorous logic and causal inference. 🕸️
ASPP & -flow Hybrid Design: High-efficiency structured propagation + internal probability space optimization for high-quality reasoning without long-winded intermediate steps. ⚡
Bilingual Adaptation: Primarily focused on Serbian while preserving English logic, making it perfect for multilingual chats and cross-lingual tasks. 🌍
Lightweight & Efficient: At ~1.3B parameters, it runs smoothly on consumer-grade GPUs, ideal for edge devices and research. 💻
Use Cases 🛠️
Serbian Chatbots: Intelligent assistants with local linguistic nuance. 🗣️
Educational Tools: Multi-turn interactive tasks and learning support. 📚
Key Advantages ✨
Clean Output: Avoids messy "thinking" tags; reasoning happens internally, delivering clear and direct results. ✅
Open Access: Licensed under Apache-2.0, making it easy for research and engineering integration. 🔓
AI Democratization: Empowering low-resource language ecosystems with cutting-edge intelligence. 🤝
- 1 reply
posted
an
update
5 days ago
Post
2756
Geilim-1B-SR-Instruct — Serbian Intelligence for Deep Reasoning 🧠🇷🇸
NoesisLab/Geilim-1B-SR-Instruct
Geilim-1B-SR-Instruct is a lightweight Large Language Model (LLM) designed to bring advanced reasoning capabilities to low-resource languages. It focuses on Serbian understanding and generation while maintaining robust English reasoning. Built on the LLaMA-3 architecture with a proprietary hybrid reasoning mechanism, it delivers deep logic while keeping outputs concise and natural. 🚀
Core Innovations 💡
Implicit Deep Reasoning: Combines standard attention mechanisms with graph-structured reasoning components for rigorous logic and causal inference. 🕸️
ASPP & -flow Hybrid Design: High-efficiency structured propagation + internal probability space optimization for high-quality reasoning without long-winded intermediate steps. ⚡
Bilingual Adaptation: Primarily focused on Serbian while preserving English logic, making it perfect for multilingual chats and cross-lingual tasks. 🌍
Lightweight & Efficient: At ~1.3B parameters, it runs smoothly on consumer-grade GPUs, ideal for edge devices and research. 💻
Use Cases 🛠️
Serbian Chatbots: Intelligent assistants with local linguistic nuance. 🗣️
Educational Tools: Multi-turn interactive tasks and learning support. 📚
Key Advantages ✨
Clean Output: Avoids messy "thinking" tags; reasoning happens internally, delivering clear and direct results. ✅
Open Access: Licensed under Apache-2.0, making it easy for research and engineering integration. 🔓
AI Democratization: Empowering low-resource language ecosystems with cutting-edge intelligence. 🤝
NoesisLab/Geilim-1B-SR-Instruct
Geilim-1B-SR-Instruct is a lightweight Large Language Model (LLM) designed to bring advanced reasoning capabilities to low-resource languages. It focuses on Serbian understanding and generation while maintaining robust English reasoning. Built on the LLaMA-3 architecture with a proprietary hybrid reasoning mechanism, it delivers deep logic while keeping outputs concise and natural. 🚀
Core Innovations 💡
Implicit Deep Reasoning: Combines standard attention mechanisms with graph-structured reasoning components for rigorous logic and causal inference. 🕸️
ASPP & -flow Hybrid Design: High-efficiency structured propagation + internal probability space optimization for high-quality reasoning without long-winded intermediate steps. ⚡
Bilingual Adaptation: Primarily focused on Serbian while preserving English logic, making it perfect for multilingual chats and cross-lingual tasks. 🌍
Lightweight & Efficient: At ~1.3B parameters, it runs smoothly on consumer-grade GPUs, ideal for edge devices and research. 💻
Use Cases 🛠️
Serbian Chatbots: Intelligent assistants with local linguistic nuance. 🗣️
Educational Tools: Multi-turn interactive tasks and learning support. 📚
Key Advantages ✨
Clean Output: Avoids messy "thinking" tags; reasoning happens internally, delivering clear and direct results. ✅
Open Access: Licensed under Apache-2.0, making it easy for research and engineering integration. 🔓
AI Democratization: Empowering low-resource language ecosystems with cutting-edge intelligence. 🤝
-
- 1 reply
reacted to
yuriyvnv's
post with 👍
5 days ago
Post
2143
🎯 WAVe: 1B Multimodal Embedding Model for Word-Level Speech Quality
Multimodal embeddings for speech + transcript that verify quality at the word level, not just sentence level. Catches mispronunciations, timing errors, and prosody issues that sentence-level filters miss.
📊 Impact on Portuguese ASR:
• 34% reduction in training steps
• 50% better cross-domain generalization
• 30% less synthetic data needed
• Word-aligned attention finds errors other methods miss
🏗️ Architecture:
• Text: XLM-RoBERTa (278M params)
• Audio: Wav2Vec2-BERT 2.0 (581M params)
• Word Alignment: Multi-head attention + GLU (14M params)
• Total: 1B parameters
# Assess speech-transcript alignment
Perfect for filtering synthetic speech datasets before ASR training.
Model: yuriyvnv/WAVe-1B-Multimodal-PT
Code to create WAVe : https://github.com/yuriyvnv/WAVe
#multimodal #speech #embeddings #asr
#syntheticdata #qualityassessment
Multimodal embeddings for speech + transcript that verify quality at the word level, not just sentence level. Catches mispronunciations, timing errors, and prosody issues that sentence-level filters miss.
📊 Impact on Portuguese ASR:
• 34% reduction in training steps
• 50% better cross-domain generalization
• 30% less synthetic data needed
• Word-aligned attention finds errors other methods miss
🏗️ Architecture:
• Text: XLM-RoBERTa (278M params)
• Audio: Wav2Vec2-BERT 2.0 (581M params)
• Word Alignment: Multi-head attention + GLU (14M params)
• Total: 1B parameters
from transformers import AutoModel, AutoProcessor
processor = AutoProcessor.from_pretrained(
"yuriyvnv/WAVe-1B-Multimodal-PT",
trust_remote_code=True
)
model = AutoModel.from_pretrained(
"yuriyvnv/WAVe-1B-Multimodal-PT",
trust_remote_code=True
)# Assess speech-transcript alignment
inputs = processor(text="Olá, como está?", audio=audio_array, sampling_rate=16000, return_tensors="pt")
quality = model(**inputs).quality_score.item()Perfect for filtering synthetic speech datasets before ASR training.
Model: yuriyvnv/WAVe-1B-Multimodal-PT
Code to create WAVe : https://github.com/yuriyvnv/WAVe
#multimodal #speech #embeddings #asr
#syntheticdata #qualityassessment
- 1 reply
liked
a
model
5 days ago
updated
a
model
5 days ago
published
a
model
5 days ago
updated
a
model
5 days ago
updated
a
Space
5 days ago
updated
a
model
6 days ago
liked
a
model
6 days ago
replied to
their
post
6 days ago
Great observation! You nailed it with the comment. 💗To clarify, when I mentioned this as an 'alternative,' I was referring to the implementation method (using a seamless pipeline without enforced tags), not necessarily a breakthrough in arithmetic capability at the 1B scale. What you're seeing here is a classic example of hallucination in small-parameter models. The model is faithfully following the instruction to 'reason step-by-step' (CoT), but due to its limited size (1B), it hallucinates the intermediate calculations while maintaining a confident tone. Maintaining logic while ensuring factual accuracy in such compact models is indeed one of the biggest challenges we are currently facing and working to optimize.
reacted to
their
post with 🚀
8 days ago
Post
2547
🚀 Geilim-1B-Instruct — Implicit Deep Reasoning, Zero Verbosity
NoesisLab/Geilim-1B-Instruct
https://huggingface.co/collections/NoesisLab/geilim-large-language-models
No <think> tags. No long CoT.
Reasoning happens inside the hidden states, not in the output.
What’s different
🧠 Implicit reasoning: deep causal reasoning without exposing chains
🕸️ ASPP (Adjacency-Structured Parallel Propagation): parent-only causal graph, O(n) message passing
🌊 π-flow: internal probability-space refinement instead of token-level deliberation
⚖️ Hybrid gating: learns when to use structure vs attention
Why it matters
Lower latency & token cost
Cleaner, production-ready outputs
CoT-level reasoning depth without verbosity tax
Built on Llama-3.2-1B-Instruct, trained for math, logic, and commonsense.
Designed for small-model reasoning at the edge.
#ImplicitReasoning #SmallLLM #EfficientAI #ReasoningModels #ASPP #PiFlow
NoesisLab/Geilim-1B-Instruct
https://huggingface.co/collections/NoesisLab/geilim-large-language-models
No <think> tags. No long CoT.
Reasoning happens inside the hidden states, not in the output.
What’s different
🧠 Implicit reasoning: deep causal reasoning without exposing chains
🕸️ ASPP (Adjacency-Structured Parallel Propagation): parent-only causal graph, O(n) message passing
🌊 π-flow: internal probability-space refinement instead of token-level deliberation
⚖️ Hybrid gating: learns when to use structure vs attention
Why it matters
Lower latency & token cost
Cleaner, production-ready outputs
CoT-level reasoning depth without verbosity tax
Built on Llama-3.2-1B-Instruct, trained for math, logic, and commonsense.
Designed for small-model reasoning at the edge.
#ImplicitReasoning #SmallLLM #EfficientAI #ReasoningModels #ASPP #PiFlow
-
- 2 replies
posted
an
update
8 days ago
Post
2547
🚀 Geilim-1B-Instruct — Implicit Deep Reasoning, Zero Verbosity
NoesisLab/Geilim-1B-Instruct
https://huggingface.co/collections/NoesisLab/geilim-large-language-models
No <think> tags. No long CoT.
Reasoning happens inside the hidden states, not in the output.
What’s different
🧠 Implicit reasoning: deep causal reasoning without exposing chains
🕸️ ASPP (Adjacency-Structured Parallel Propagation): parent-only causal graph, O(n) message passing
🌊 π-flow: internal probability-space refinement instead of token-level deliberation
⚖️ Hybrid gating: learns when to use structure vs attention
Why it matters
Lower latency & token cost
Cleaner, production-ready outputs
CoT-level reasoning depth without verbosity tax
Built on Llama-3.2-1B-Instruct, trained for math, logic, and commonsense.
Designed for small-model reasoning at the edge.
#ImplicitReasoning #SmallLLM #EfficientAI #ReasoningModels #ASPP #PiFlow
NoesisLab/Geilim-1B-Instruct
https://huggingface.co/collections/NoesisLab/geilim-large-language-models
No <think> tags. No long CoT.
Reasoning happens inside the hidden states, not in the output.
What’s different
🧠 Implicit reasoning: deep causal reasoning without exposing chains
🕸️ ASPP (Adjacency-Structured Parallel Propagation): parent-only causal graph, O(n) message passing
🌊 π-flow: internal probability-space refinement instead of token-level deliberation
⚖️ Hybrid gating: learns when to use structure vs attention
Why it matters
Lower latency & token cost
Cleaner, production-ready outputs
CoT-level reasoning depth without verbosity tax
Built on Llama-3.2-1B-Instruct, trained for math, logic, and commonsense.
Designed for small-model reasoning at the edge.
#ImplicitReasoning #SmallLLM #EfficientAI #ReasoningModels #ASPP #PiFlow
-
- 2 replies
liked
a
model
8 days ago
updated
a
collection
8 days ago
upvoted
a
collection
8 days ago
published
a
model
8 days ago
replied to
sergiopaniego's
post
8 days ago
awesome!