These are GGUF quantized versions of jondurbin/bagel-dpo-34b-v0.2.
The importance matrix was trained for 1M tokens (2,000 batches of 512 tokens) using wiki.train.raw
.
- Downloads last month
- 276
Model size
34.4B params
Architecture
llama
Unable to determine this model's library. Check the
docs
.