Join our Discord! https://discord.gg/Nbv9pQ88Xb

2500+ members strong πŸ’ͺ Now with more channels! A hub for users and makers alike!


Endurance 100B v1 🎑

A finetune of Lazarus 2407 100B, a pruned Mistral Large 2407 123B!

image/png

Do not go gentle into that good night. Rage, rage against the dying of the light!


Links

Arsenal (Supported Chat Templates)

  • Metharme (Pygmalion in ST)
    • Creative, unhinged, unique

Favorite RP Format

*action* Dialogue *thoughts* Dialogue *narration* in 1st person PoV

Favorite Card

image/png Audrey by thecooler


Comparisons

Quant Experience 123B 100B 72B
IQ2_XXS Functional 32.43GB 26.61GB 25.49GB
IQ3_XXS Acceptable 47.01GB 38.54GB 31.85GB
IQ4_XS Good 65.43GB 53.64GB 39.71GB

Technical Details

Refer to Lazarus 2407 100B for pruning details.

Endurance used the same hyperparameters as Behemoth. Training loss indicates that they are exactly the same albeit with lower confidence.

image/png

Notes on Lazarus 100B (base model for Endurance):

  • Testers have noted that 100B seemed nearly identical to 123B.
  • One tester said that only one minor mistake was made by the model, requiring a rewrite for failing to pick up on the nuance.
  • Another tester went through a satisfying 32K playthrough without any issues.

Endurance 100B v1.0 has gone through additional RP & Instruct training.

Downloads last month
148
Safetensors
Model size
100B params
Tensor type
BF16
Β·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for TheDrummer/Endurance-100B-v1

Finetuned
(1)
this model
Quantizations
1 model