Introducing the Palmyra-mini family: Powerful, lightweight, and ready to reason!
•
58
AI & ML interests
AGI, LLMs, Knowledge Graph, Palmyra, Domain Specific LLM
Recent Activity
Articles
kiranr
published
3
models
11 days ago
tperes
updated
a
model
15 days ago
wassemgtk
updated
a
Space
21 days ago
wassemgtk
published
a
Space
26 days ago
Adding `transformers` tag
#1 opened about 1 month ago
by
ariG23498
Adding `transformers` as the library tag
❤️
1
#1 opened about 1 month ago
by
ariG23498
tperes
updated
2
models
about 1 month ago
Fix pipeline_tag 🤗
❤️
2
1
#1 opened about 1 month ago
by
merve
Post
217
Introducing Palmyra-mini: Compact AI Models for Efficient Inference
The Palmyra-mini family from Writer includes three lightweight models designed for high performance and efficient inference. These models are ideal for developers looking to integrate AI capabilities without excessive computational overhead.
Model Variants
* palmyra-mini: A base model for general-purpose generative tasks, achieving 52.6% on Big Bench Hard (exact match).
* palmyra-mini-thinking-a: Optimized for complex logical reasoning with a Chain of Thought (CoT) approach, scoring 82.87% on GSM8K (strict match).
* palmyra-mini-thinking-b: Specialized for mathematical reasoning, achieving 92.5% on AMC23.
Technical Details
* All models are based on the Qwen architecture, compatible with popular inference frameworks like vLLM, SGLang, and TGI.
* "Thinking" models utilize CoT training for enhanced reasoning capabilities.
* GGUF and MLX quantizations are available for optimized performance.
For more information, including benchmark methodologies and detailed performance metrics, refer to our blog post: (https://huggingface.co/blog/Writer/announcing-palmyra-mini).
Model repos can be found here:
* Writer/palmyra-mini
* Writer/palmyra-mini-thinking-a
* Writer/palmyra-mini-thinking-b
Also check out a mobile implementation of palmyra-mini on iOS here to see a to see a working example of how inference can be incorporated on-device.(https://github.com/tsperes/palmyra-mini-mobile/)
The Palmyra-mini family from Writer includes three lightweight models designed for high performance and efficient inference. These models are ideal for developers looking to integrate AI capabilities without excessive computational overhead.
Model Variants
* palmyra-mini: A base model for general-purpose generative tasks, achieving 52.6% on Big Bench Hard (exact match).
* palmyra-mini-thinking-a: Optimized for complex logical reasoning with a Chain of Thought (CoT) approach, scoring 82.87% on GSM8K (strict match).
* palmyra-mini-thinking-b: Specialized for mathematical reasoning, achieving 92.5% on AMC23.
Technical Details
* All models are based on the Qwen architecture, compatible with popular inference frameworks like vLLM, SGLang, and TGI.
* "Thinking" models utilize CoT training for enhanced reasoning capabilities.
* GGUF and MLX quantizations are available for optimized performance.
For more information, including benchmark methodologies and detailed performance metrics, refer to our blog post: (https://huggingface.co/blog/Writer/announcing-palmyra-mini).
Model repos can be found here:
* Writer/palmyra-mini
* Writer/palmyra-mini-thinking-a
* Writer/palmyra-mini-thinking-b
Also check out a mobile implementation of palmyra-mini on iOS here to see a to see a working example of how inference can be incorporated on-device.(https://github.com/tsperes/palmyra-mini-mobile/)
dmytro-writer
authored
a
paper
5 months ago
wassemgtk
authored
a
paper
5 months ago
Post
3222
I’ve been diving into the iRoPE architecture from Llama 4—a game-changer for long-context models! It interleaves local attention (with RoPE) for short contexts and global attention (with inference-time temp scaling) for long-range reasoning, aiming for infinite context. I’m going to try writing iRoPE—who wants to help?
Code: https://github.com/wassemgtk/iRoPE-try/blob/main/iRoPE.ipynb
Code: https://github.com/wassemgtk/iRoPE-try/blob/main/iRoPE.ipynb
-
- 1 reply
Post
2132
For fun, a new project: SuperTokenizer! A BPE tokenizer trained on C4 to beat GPT-4. Byte-level, A100-powered, and open-source. Messing around with tokens!
https://github.com/wassemgtk/SuperTokenizer
https://github.com/wassemgtk/SuperTokenizer
- 1 reply
Post
1916
# GESAL: Real-Time Adaptation for LLMs
We’re excited to unveil **Graph-Enhanced Singular Adaptive Learning (GESAL)**, a framework that lets LLMs like
🔗 **Code**: [https://github.com/writer/AI-Adaptive-Learning-GESAL](https://github.com/writer/AI-Adaptive-Learning-GESAL)
---
## Why GESAL?
Static LLMs struggle to adapt without heavy retraining. GESAL solves this with:
- **SVF**: Adapts weights via \( W' = U (\Sigma \cdot z) V^T \), using few parameters.
- **Graph Memory**: Stores adaptations in nodes for scalability.
- **RL**: Updates via \( J(z) = \mathbb{E}[\log \pi_z(y|x) r] \) based on feedback.
---
## How It Works
Ask "How many R’s in ‘strawberry’?" If it says "2" and you say "no," GESAL learns to say "3" next time, avoiding repeats.
---
## Try It
Built with Hugging Face’s
Needs a Hugging Face token for Llama-3.2-1B.
---
## Results
GESAL hits 95% accuracy after 5 feedbacks vs. LoRA’s 70%. It’s efficient (~0.5M params) and scalable.
We’re excited to unveil **Graph-Enhanced Singular Adaptive Learning (GESAL)**, a framework that lets LLMs like
meta-llama/Llama-3.2-1B adapt in real time using user feedback. Check out the code and white paper on GitHub!🔗 **Code**: [https://github.com/writer/AI-Adaptive-Learning-GESAL](https://github.com/writer/AI-Adaptive-Learning-GESAL)
---
## Why GESAL?
Static LLMs struggle to adapt without heavy retraining. GESAL solves this with:
- **SVF**: Adapts weights via \( W' = U (\Sigma \cdot z) V^T \), using few parameters.
- **Graph Memory**: Stores adaptations in nodes for scalability.
- **RL**: Updates via \( J(z) = \mathbb{E}[\log \pi_z(y|x) r] \) based on feedback.
---
## How It Works
Ask "How many R’s in ‘strawberry’?" If it says "2" and you say "no," GESAL learns to say "3" next time, avoiding repeats.
---
## Try It
Built with Hugging Face’s
transformers:pip install transformers torch numpy
python Adaptive_Learning_(GESAL).pyNeeds a Hugging Face token for Llama-3.2-1B.
---
## Results
GESAL hits 95% accuracy after 5 feedbacks vs. LoRA’s 70%. It’s efficient (~0.5M params) and scalable.
-
- 15 replies
wassemgtk
authored
a
paper
8 months ago
dmytro-writer
authored
2
papers
9 months ago