Yes, this is my point: we shouldn't compare different models based on different prompting techniques. We need reflection vs. reflection, CoT vs. CoT, etc.
LLMS
-
Raw LM-Evaluation-Harness Testing Without System Prompt
By
–
It's "raw" lm-evaluation-harness, I didn't add the recommended system prompt.
-
L3.1 70B weights upload issue discussion
By
–
I haven't yet but does it mean they wrongly uploaded L3.1 70B's weights…?
-
Reflection technique between AI models by Fernando Neto
By
–
Example from the great @FernandoNetoAi of reflection with another model.
-
Reflection CoT Evaluation Methods Comparability Issues
By
–
This is super cool but I have a lot of questions. First, reflection = CoT on steroids. It means you can't compare these scores at all. Remember when people made fun of Gemini for providing CoT results for MMLU? This is a lot worse. Secondly, if you don't parse the output and
-
New 70B Model Available on Hugging Face When Main Demo Busy
By
–
if the main demo is busy looks like you can try the new 70B model here on @huggingface : https://
huggingface.co/spaces/feather
less-ai/try-this-model
… -
Link to the Reflection-Llama-3.1-70B model on the Hub
By
–
Check it out on the Hub -> https://
huggingface.co/mattshumer/Ref
lection-Llama-3.1-70B
… -
New 70B LLM Outperforms Claude-3.5-Sonnet and GPT-4o with Innovative Fine-Tuning
By
–
> A new 70B open-source LLM beats Claude-3.5-Sonnet and GPT-4o! Matt Schumer, CEO from Hyperwrite AI, had an idea he wanted to try out: why not fine-tune LLMs to always output their thoughts in specific parts, delineated by tags? Even better: inside of that, you
-
AI Training Progress Requires Years More Data and Compute
By
–
Sadly you will need about 2-4 more years of training data, additional compute, and a bunch of post training before you can expect major improvements.
-
Adding llms.txt support to editor implementation
By
–
Here's a sample of adding llms.txt support to an editor: