metadata
base_model: amazingvince/zephyr-smol_llama-100m-sft-full
inference: false
license: apache-2.0
model-index:
- name: zephyr-smol_llama-100m-sft-full
results: []
model_creator: amazingvince
model_name: zephyr-smol_llama-100m-sft-full
pipeline_tag: text-generation
quantized_by: afrideva
tags:
- generated_from_trainer
- gguf
- ggml
- quantized
- q2_k
- q3_k_m
- q4_k_m
- q5_k_m
- q6_k
- q8_0
amazingvince/zephyr-smol_llama-100m-sft-full-GGUF
Quantized GGUF model files for zephyr-smol_llama-100m-sft-full from amazingvince
| Name | Quant method | Size |
|---|---|---|
| zephyr-smol_llama-100m-sft-full.fp16.gguf | fp16 | 204.25 MB |
| zephyr-smol_llama-100m-sft-full.q2_k.gguf | q2_k | 51.90 MB |
| zephyr-smol_llama-100m-sft-full.q3_k_m.gguf | q3_k_m | 58.04 MB |
| zephyr-smol_llama-100m-sft-full.q4_k_m.gguf | q4_k_m | 66.38 MB |
| zephyr-smol_llama-100m-sft-full.q5_k_m.gguf | q5_k_m | 75.31 MB |
| zephyr-smol_llama-100m-sft-full.q6_k.gguf | q6_k | 84.80 MB |
| zephyr-smol_llama-100m-sft-full.q8_0.gguf | q8_0 | 109.33 MB |
Original Model Card:
zephyr-smol_llama-100m-sft-full
This model is a fine-tuned version of BEE-spoke-data/smol_llama-101M-GQA on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9579
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 |
|---|---|---|---|
| 1.9642 | 0.7 | 1141 | 1.9578 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1