BEE-spoke-data/zephyr-220m-sft-full-GGUF
Quantized GGUF model files for zephyr-220m-sft-full from BEE-spoke-data
| Name | Quant method | Size |
|---|---|---|
| zephyr-220m-sft-full.fp16.gguf | fp16 | 436.50 MB |
| zephyr-220m-sft-full.q2_k.gguf | q2_k | 94.43 MB |
| zephyr-220m-sft-full.q3_k_m.gguf | q3_k_m | 114.65 MB |
| zephyr-220m-sft-full.q4_k_m.gguf | q4_k_m | 137.58 MB |
| zephyr-220m-sft-full.q5_k_m.gguf | q5_k_m | 157.91 MB |
| zephyr-220m-sft-full.q6_k.gguf | q6_k | 179.52 MB |
| zephyr-220m-sft-full.q8_0.gguf | q8_0 | 232.28 MB |
Original Model Card:
zephyr-220m-sft-full
This model is a fine-tuned version of BEE-spoke-data/smol_llama-220M-openhermes on the Ultrachat_200k dataset. It achieves the following results on the evaluation set:
- Loss: 1.6579
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: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6447 | 1.0 | 1624 | 1.6579 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
https://wandb.ai/amazingvince/huggingface/runs/5rffzk3x/workspace?workspace=user-amazingvince