Delta-Vector/MS3.2-Austral-24B-SFT

Wot is this

Just another checkpoint, better to use the -Winton model but this is released to keep in line with being an actual OSS Finetuner. (Unlike some others who don't release datasets or checkpoints!)

This is the SFT part of the MS3.2 train ontop of Codex

Wandb: https://wandb.ai/gum1h0x/austral/artifacts/axolotl-config/config-4hspge7d/v0/files/axolotl_config_ept225f_.yml

Datasets:

datasets:
  - path: Delta-Vector/Hydrus-Claude-Instruct-2.7K
    type: dan-chat-advanced
  - path: Delta-Vector/Hydrus-Claude-Instruct-5K
    type: dan-chat-advanced
  - path: Delta-Vector/Orion-Shoujo-AI-Filtered-ShareGPT
    type: dan-chat-advanced
  - path: PocketDoc/Dans-Personamaxx-VN
    type: dan-chat-advanced
  - path: NewEden/LIMARP-Complexity
    type: dan-chat-advanced
  - path: NewEden/PIPPA-Mega-Filtered
    type: dan-chat-advanced
  - path: NewEden/OpenCAI-ShareGPT
    type: dan-chat-advanced
  - path: NewEden/Creative_Writing-Complexity
    type: dan-chat-advanced
  - path: NewEden/Light-Novels-Roleplay-Logs-Books-Oh-My-duplicate-turns-removed
    type: dan-chat-advanced
  - path: PocketDoc/Dans-Failuremaxx-Adventure-3
    type: dan-chat-advanced
  - path: NewEden/Books-V2-ShareGPT
    type: dan-chat-advanced
  - path: NewEden/Deepseek-V3-RP-Filtered
    type: dan-chat-advanced
  - path: NewEden/Final-Alpindale-LNs-ShareGPT
    type: dan-chat-advanced
  - path: NewEden/DeepseekRP-Filtered
    type: dan-chat-advanced
  - path: NewEden/RP-logs-V2-Experimental
    type: dan-chat-advanced
  - path: anthracite-org/kalo_opus_misc_240827
    type: dan-chat-advanced
  - path: anthracite-org/kalo_misc_part2
    type: dan-chat-advanced
  - path: NewEden/Storium-Prefixed-Clean
    type: dan-chat-advanced
  - path: Delta-Vector/Hydrus-AM-Thinking-IF
    type: dan-chat-advanced

TYSM to Gum1hox for sponsering the run, Trained on 1xB200 for 30 hours

https://x.com/gum1h0x