Downloads · 30 days
30
25% of all-time downloads
ZhangShenao_-_SELM-Phi-3-mini-4k-instruct-iter-2-4bits
RichardErkhov/ZhangShenao_-_SELM-Phi-3-mini-4k-instruct-iter-2-4bits
ZhangShenao_-_SELM-Phi-3-mini-4k-instruct-iter-2-4bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
122
Public
Parameters
3.9B
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 100%
Parameter types
How the weights are stored.
U83.6B · 93%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
SELM-Phi-3-mini-4k-instruct-iter-2 - bnb 4bits
- Model creator: https://huggingface.co/ZhangShenao/
- Original model: https://huggingface.co/ZhangShenao/SELM-Phi-3-mini-4k-instruct-iter-2/
Original model description:
license: mit base_model: ZhangShenao/SELM-Phi-3-mini-4k-instruct-iter-1 tags:
- alignment-handbook
- dpo
- trl
- selm datasets:
- HuggingFaceH4/ultrafeedback_binarized model-index:
- name: SELM-Phi-3-mini-4k-instruct-iter-2 results: []
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Self-Exploring Language Models: Active Preference Elicitation for Online Alignment.
SELM-Phi-3-mini-4k-instruct-iter-2
This model is a fine-tuned version of ZhangShenao/SELM-Phi-3-mini-4k-instruct-iter-1 using synthetic data based on on the HuggingFaceH4/ultrafeedback_binarized dataset.
Model description
- Model type: A 3.8B parameter Phi3-instruct-based Self-Exploring Language Models (SELM).
- License: MIT
Results
| AlpacaEval 2.0 (LC WR) | MT-Bench (Average) | |
|---|---|---|
| SELM-Phi-3-mini-4k-instruct-iter-3 | 27.98 | 8.32 |
| SELM-Phi-3-mini-4k-instruct-iter-2 | 26.79 | 8.44 |
| SELM-Phi-3-mini-4k-instruct-iter-1 | 27.33 | 8.37 |
| Phi-3-mini-4k-instruct | 23.05 | 8.12 |
Training hyperparameters
The following hyperparameters were used during training:
- alpha: 0.001
- beta: 0.01
- train_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- num_epochs: 1
Framework versions
- Transformers 4.40.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1
- Type
- phi3
- Created
- Jan 24, 2025
- Updated
- Jan 24, 2025