Downloads · 30 days
11
7% of all-time downloads
Khyatimirani/pcos-fertility-llama3-8b
pcos-fertility-llama3-8b is a text generation model from Khyatimirani. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: Khyatimirani - License: apache-2.0 - Finetuned from model : unsloth/llama-3.2-3b-instruct
Downloads · 30 days
11
7% of all-time downloads
All-time downloads
161
Public
Parameters
3.2B
6.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.4 GB · 100%
From the Hugging Face model README
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
| Parameter | Value |
|---|---|
| Architecture | LlamaForCausalLM |
| Model type | llama |
| Transformers version | 5.0.0 |
| Dtype | float16 |
| Vocab size | 128256 |
| Hidden size | 3072 |
| Intermediate size | 8192 |
| Number of hidden layers | 28 |
| Number of attention heads | 24 |
| Number of key/value heads | 8 |
| Head dimension | 128 |
| Activation function | silu |
| Max position embeddings | 131072 |
| RoPE type | llama3 |
| RoPE theta | 500000.0 |
| RoPE original max positions | 8192 |
| RoPE factor | 32.0 |
| RoPE high freq factor | 4.0 |
| RoPE low freq factor | 1.0 |
| Attention dropout | 0.0 |
| Attention bias | false |
| MLP bias | false |
| RMS norm eps | 1e-05 |
| Initializer range | 0.02 |
| Use cache | true |
| Tie word embeddings | true |
| Pretraining TP | 1 |
| BOS token id | 128000 |
| EOS token id | 128009 |
| PAD token id | 128004 |
| Unsloth fixed | true |
| Unsloth version | 2026.1.4 |