Iambe-20b-DARE / README.md
athirdpath's picture
Update README.md
bf37f73
|
raw
history blame
1.99 kB
metadata
license: cc-by-nc-4.0

Iambe-20b-DARE

Description and Role

Named after a charming daughter of Echo and Pan in Greek myth, Iambe-20b-DARE is a DARE merge building on my recent experiments. Iambe is intended to be a model that has the best realisticly possible understanding of the scene state remains personable and "human-like" in RP scenarios,

Prompting and Context

Iambe-20b-DARE uses Alpaca formatting, and has an effective context size of 4096 tokens. This model is uncensored, and the output/deployment of this model is the responsibility of the user.

Method and Hypothesis

Based on my extended vanilla model BigLlama, this adds elements of:

  • NeverSleep/Noromaid-20b-v0.1.1 - Addded to adapt the excellent writing and "soul" that come from the datasets backing this model.

  • athirdpath/Eileithyia-20b - Added at low weight and density to capture anatomical data and its relation to fiction without the model's other... quirks.

  • athirdpath/CleverGirl-20b-Blended - Added to capture CleverGirl's problem-solving abilities.

Examples

Coming soon.

Testing and Conclusions

VERY Impressed so far, concrete data coming soonish.

Does still have some confusion (at q5_k_m), but has instantly become my daily driver.

Recipe

merge_method: dare_ties

  • base_model: athirdpath/BigLlama-20B

  • model: NeverSleep/Noromaid-20b-v0.1.1

    weight: 0.41 / density: 0.50

  • model: athirdpath/Eileithyia-20b

    weight: 0.18 / density: 0.30

  • model: athirdpath/CleverGirl-20b-Blended

    weight: 0.41 / density: 0.50

int8_mask: true

dtype: bfloat16

Gratitude

Thanks to brucethemoose for the recipe. Thanks to Undi95 and IkariDev at NeverSleep for Noromaid, as well as lots of inspiration. Thanks to Sao10K for half of CleverGirl.