---
base_model:
- TheDrummer/Lazarus-2407-100B
---
# Join our Discord! https://discord.gg/Nbv9pQ88Xb
## 2500+ members strong 💪 Now with more channels! A hub for users and makers alike!
---
# Endurance 100B v1 🎡

*A finetune of [Lazarus 2407 100B](https://huggingface.co/TheDrummer/Lazarus-2407-100B), a pruned Mistral Large 2407 123B!*

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/R2dDPDShY2VEhRzbJr-Go.png)

> [Do not go gentle into that good night. Rage, rage against the dying of the light!](https://www.youtube.com/watch?v=ESWzPhZWYeI)

---

## Links
- Original: https://huggingface.co/TheDrummer/Endurance-100B-v1
- GGUF: https://huggingface.co/TheDrummer/Endurance-100B-v1-GGUF
- iMatrix: https://huggingface.co/bartowski/Endurance-100B-v1-GGUF (recommended for smaller quants)

## 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](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/Ebi-X8DEw5LclXCFuL_H7.png)
[Audrey by thecooler](https://characterhub.org/characters/thecooler/audrey-5f995ef8)

---

## 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](https://huggingface.co/TheDrummer/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](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/s0uELhSkSSwseyBrFzw7q.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.