Downloads · 30 days
11
13% of all-time downloads
llama-2-13b-hf-sensitivity-sorted
jsyeom/llama-2-13b-hf-sensitivity-sorted
llama-2-13b-hf-sensitivity-sorted is a machine learning model from jsyeom. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model has sensitivity-based channel sorting applied. No quantization has been applied.
All-time downloads
86
Public
Parameters
13B
26 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors26 GB · 100%
At a glance
- Model type
- llama
- Access
- Public
- Created
- Mar 26, 2026
- Updated
- Apr 7, 2026
- SHA
- 9d6d8ee6
Base models
Model card
From the Hugging Face model README
llama-2-13b-hf-sensitivity-sorted
This model has sensitivity-based channel sorting applied. No quantization has been applied.
Configuration
| Parameter | Value |
|---|---|
| Base model | meta-llama/Llama-2-13b-hf |
| Method | Sensitivity-based full channel sorting |
| Sorting order | Ascending (low sensitivity → high) |
| Quantization | None (sorting only) |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("jsyeom/sensitivity_sorted_models/llama-2-13b-hf-sensitivity-sorted")
tokenizer = AutoTokenizer.from_pretrained("jsyeom/sensitivity_sorted_models/llama-2-13b-hf-sensitivity-sorted")
Important Notes
dst_ids.ptcontains the full permutation indices for reference.sort_config.jsoncontains metadata about the sorting configuration.
Reference
- Type
- llama
- Languages
- en
- Created
- Mar 26, 2026
- Updated
- Apr 7, 2026