LLM + Vision, http://
01.AI just launched Yi-VL-34B, now a world-leading open-source VL model for the developers' community. We are exploring more multi-modal possibilities in 2024. Ideas and TALENTS welcome!
OPEN SOURCE
-
01.AI Launches Yi-VL-34B Open-Source Vision-Language Model
By
–
-
01.AI Launches Yi-VL-34B Open-Source Vision Language Model
By
–
We're excited to introduce Yi-VL-34B, newly open-sourced Yi Vision Language Models from http://
01.AI. It now ranks #1 in open-source category per MMMU & CMMMU benchmarks. Now our eyes are wide open to see your fantastic vision projects!! https://
huggingface.co/01-ai/Yi-VL-34B -
Community blogs on autograd engines and language model fine-tuning
By
–
Check out the community blogs of last few days Building autograd engine tinytorch 01: https://
hf.co/blog/joey00072
/building-autograd-engine-tinytorch-01
… Unleashing the Power of Unsloth and QLora: Redefining Language Model Fine-Tuning: https://
hf.co/blog/Andyrasik
a/finetune-unsloth-qlora
… AI Lineage Explorer: https://
hf.co/blog/backnotpr
op/integrity-explorer
… -
UltimateSDupscaler Added to Comfy UI Integration
By
–
I've added all of these: https://
github.com/fofr/cog-comfy
ui/commit/56532c94fb5f0ac2587ba4822b4e55af93a15347
… UltimateSDupscaler should have been a given -
MoE-Mamba: Scaling LLMs with State Space Models and Mixture of Experts
By
–
10/ MoE-Mamba – an approach to efficiently scale LLMs by combining state space models (SSMs) with Mixture of Experts (MoE); MoE-Mamba, outperforms both Mamba and Transformer-MoE.
-
LLM Evaluation Methodologies: Taxonomy and Approaches
By
–
7/ Overview of LLMs for Evaluation – thoroughly surveys the methodologies and explores their strengths and limitations; provides a taxonomy of different approaches involving prompt engineering or calibrating open-source LLMs for evaluation.
-
Proxy-Tuning: Efficient Language Model Adaptation at Decoding
By
–
5/ Tuning Language Models by Proxy – introduces proxy-tuning, a decoding-time algorithm that modifies logits of a target LLM with the logits’ difference between a small base model and a fine-tuned base model.
-
Appreciation for llama2.c project and its helpful contribution
By
–
so cool 😀
(& very happy to see llama2.c referenced as helpful ) -
Stable LM 2 1.6B Multilingual Small Language Model Released
By
–
Today, we’re releasing Stable LM 2 1.6B, a state-of-the-art 1.6 billion parameter small language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch. This model’s size and speed reduce hardware limitations, allowing all to easily
-
Ludwig v0.9.2 Released with New Features and Improvements
By
–
Announcing #Ludwig v0.9.2! This release introduces several capabilities and fixes: Per-step token utilization to tensorboard and progress tracker Default LoRA target modules for #Mixtral Support for exporting models to Carton https://
pbase.ai/3vI8SCW