If you'd like to quickly check out SOLAR-10.7B-Instruct-v1.0, try using @togethercompute playaround and endpoint. They're really good! https://
api.together.xyz/playground/cha
t/upstage/SOLAR-10.7B-Instruct-v1.0
…
@hunkims
-
SOLAR-10.7B-Instruct Model Available via Together Compute
By
–
-
Solar LLM Ranks Second in Financial Document Q&A Benchmark
By
–
#solarllm Solar performs well in LLM benchmark for financial document question answering, ranking second only after GPT-4. https://
medium.com/@kunal_79217/a
n-llm-benchmark-for-financial-document-question-answering-e63e9d2bda25
… -
Merged and Stacked LLMs: Technical Excellence Guide
By
–
#solarllm This is an excellent read for 𝗠𝗲𝗿𝗴𝗲𝗱/𝗦𝘁𝗮𝗰𝗸𝗲𝗱 𝗟𝗟𝗠.
-
Evaluating Solar LLM with 1.6 Million Users Feedback
By
–
#solarllm #askup #kakao #thumbsup One of the best ways to evaluate LLM models is by getting feedback from many users. There are 1.6 million AskUp users of Solar LLM on @Kakao messenger in Korea. AskUp also uses GPT 3.5 and GPT 4, where an LLM model is randomly selected when a
-
Solar LM Newsletter Delivers Daily AI Paper Summaries
By
–
#solarlm #solarinaction delivers paper summaries to your inbox. Solar llm summarizes carefully selected daily papers from @Huggingface Just join at https://
groups.google.com/g/hf-daily-pap
er-newsletter
… thanks to @algo_diver -
Solar LLM Local Deployment Tutorial by Upstage
By
–
#solarllm Great tutorial on utilizing @upstageai
's Solar LLM for local deployment. Excellent example of its use case! https://
youtu.be/3l4m8N0_UJo?si
=IE6A6xnwiU41jRKb
… -
SOLAR-10.7B Model Enhanced with Direct Preference Optimization
By
–
#solarllm SOLAR-10.7B + Direct Preference Optimization (DPO)
-
Self-Extend LLM: Extending Context Window Without Fine-tuning
By
–
#solarllm #16K Very interesting work, Self-Extend LLM! "The proposed method does not require any training. With only four lines of code modification, it can effortlessly extend existing LLMs’ context window without any fine-tuning. We conducted comprehensive experiments, and the
-
Open Ko-LLM Leaderboard Launches with 500+ Models
By
–
We’re thrilled to announce that our Open Ko-LLM leaderboard, (GPU/CPU sponsored by KT and @huggingface
), now features over 500 models! If you’re developing a Large Language Model (LLM), come test its Korean language abilities at our leaderboard, https://
huggingface.co/spaces/upstage
/open-ko-llm-leaderboard
…