mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-23 17:01:04 +02:00
* separate bias + head weight init * smaller bias init + sum with 1/sqrt(combined_r) scaling + better lora merge logic * ok init * chunked ctx magic num working * configs * no transpose + only sum aggregation * fix cli * cli * 32-256 data * example cli + smaller dataset * toy ctx magic num ds size + quantize + remove head bias * configs removed * require lora_bias * Merge remote-tracking branch 'origin/main' into new-arch |
||
|---|---|---|
| .. | ||
| gemma-3-1b-it/toy_exp | ||
| medium_exp | ||
| small_exp | ||
| toy_exp | ||
| context_numbers_10.yaml | ||
| context_numbers_10_self_gen.yaml | ||
| fw_qa_v2_level_0.yaml | ||
| fw_qa_v2_level_1.yaml | ||
| fw_qa_v2_level_2.yaml | ||
| fw_qa_v2_level_3.yaml | ||
| pwc_tiny.yaml | ||
| qa_short_ctx.yaml | ||
| qa_short_ctx_compact.yaml | ||
| qa_short_ctx_self_gen.yaml | ||
| qa_short_ctx_self_gen_no_fw_qa.yaml | ||
| qa_short_ctx_self_gen_squad.yaml | ||
| squad.yaml | ||
| squad_compact.yaml | ||
| squad_fw_qa_v2_level_3.yaml | ||
| squad_hotpot_qa.yaml | ||