It looks like your config set temperature to 0 , it should be 0.6
according to Usage Recommendations
SB
shb777
AI & ML interests
LLM's , Speech 2 Speech and Synthetic Data
Recent Activity
replied to
csabakecskemeti's
post
about 2 hours ago
I've run the open llm leaderboard evaluations + hellaswag on https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B and compared to https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct and at first glance R1 do not beat Llama overall.
If anyone wants to double check the results are posted here:
https://github.com/csabakecskemeti/lm_eval_results
Am I made some mistake, or (at least this distilled version) not as good/better than the competition?
I'll run the same on the Qwen 7B distilled version too.
updated
a dataset
4 days ago
shb777/gemini-flash-2.0-speech
liked
a Space
8 days ago
black-forest-labs/FLUX.1-dev
Organizations
shb777's activity
replied to
csabakecskemeti's
post
about 2 hours ago
upvoted
an
article
9 days ago
Article
Train 400x faster Static Embedding Models with Sentence Transformers
•
121
[bot] Conversion to Parquet
#1 opened 9 days ago
by
parquet-converter