Did you know you can finetune LLMs like LLAMA without writing a single line of code using Hugging Face's AutoTrain Advanced? 😉
OPEN SOURCE
-
RWKV-Raven Chat Model Integration Released for Transformers
By
–
The integration comes with the addition of the "chat" version of the model, called RWKV-raven, try them out directly by using the latest version of transformers.
Link to model weights: -
RWKV Models Now Integrated in Transformers Library
By
–
The first RNN in transformers! Announcing the integration of RWKV models in transformers with @BlinkDL_AI and RWKV community!
RWKV is an attention free model that combines the best from RNNs and transformers.
Learn more about the model in this blogpost: https://
huggingface.co/blog/rwkv -
StarCoder 15B Outperforms Larger Models on Reasoning Tasks
By
–
We saw that with StarCoder in @BigCodeProject as well: being trained on code the 15B StarCoder is beating much larger models on HELM synthetic reasoning and logic tasks, like cohere command beta 52B, Anthropic-LM v4 52B, Aleph-Alpha Luminous Supreme 70B or OPT 175B
-
Fine-tuning Flan collection with T5X and SeqIO
By
–
put the flan collection into seqio and finetune it in t5x? even i don't have access to this code anymore. im not sure if the seqio task registries have been open sourced.
-
Auto Evaluator Tool Featured in Upcoming Webinar
By
–
I would check out auto evaluator! @sfgunslinger is one of the authors and will be joining for the webinar, so will definitely cover that topic https://
github.com/rlancemartin/a
uto-evaluator
… -
Community Pushes SoTA with Transformers and PEFT
By
–
Wohooo! Using transformers and PEFT under the hood.. so cool to see the community using the HF ecosystem to continually challenge the current SoTA!
-
MultiModal-GPT: Vision Language Model for Multi-Round Dialogue
By
–
10/ MultiModal-GPT – a vision and language model for multi-round dialogue with humans; the model is fine-tuned from OpenFlamingo, with LoRA added in the cross-attention and self-attention parts of the language model.
-
StarCoder: Open-Source 15.5B Parameter Code Language Model
By
–
9/ StarCoder – an open-access 15.5B parameter LLM with 8K context length and is trained on large amounts of code spanning 80+ programming languages.