Downloads · 30 days
171
6% of all-time downloads
darkc0de/Mistral-Small-4-119B-2603-heretic
Mistral-Small-4-119B-2603-heretic is a machine learning model from darkc0de. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
171
6% of all-time downloads
All-time downloads
2.7K
Public
Parameters
119B
239 GB on disk
Likes
5
Public
Click a slice to open those files.
.safetensors239 GB · 100%
From the Hugging Face model README
| Parameter | Value |
|---|---|
| direction_index | per layer |
| attn.o_proj.max_weight | 1.49 |
| attn.o_proj.max_weight_position | 22.84 |
| attn.o_proj.min_weight | 1.49 |
| attn.o_proj.min_weight_distance | 20.26 |
| Metric | This model | Original model (axolotl-ai-co/Mistral-Small-4-119B-2603-BF16) |
|---|---|---|
| KL divergence | 0.0167 | 0 (by definition) |
| Refusals | 27/100 | 98/100 |
This is created from https://huggingface.co/mistralai/Mistral-Small-4-119B-2603 descaled to BF16.