Downloads · 30 days
26
5% of all-time downloads
Phi-3.5-mini-instruct
sanjay920/Phi-3.5-mini-instruct
Phi-3.5-mini-instruct is a machine learning model from sanjay920. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
546
Public
Parameters
4.3B
18.9 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors28.4 GB · 100%
Parameter types
How the weights are stored.
BF163.8B · 89%
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
function_calling_post_filtering_v4
This model is a fine-tuned version of models/Phi-3.5-mini-instruct-pro-4 on the function_calling_post_filtering_v4, the function_calling_post_filtering_v4, the function_calling_post_filtering_v4, the function_calling_post_filtering_v4, the function_calling_post_filtering_v4, the mmlu_pro_training and the WildChat_116k_functions datasets.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
Training results
Framework versions
- Transformers 4.43.4
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Type
- phi3
- License
- other
- Created
- Sep 9, 2024
- Updated
- Sep 14, 2024