base_model, inference, license, model-index, model_creator, model_name, pipeline_tag, quantized_by, tags

base_model	inference	license	model-index	model_creator	model_name	pipeline_tag	quantized_by	tags
amazingvince/zephyr-smol_llama-100m-sft-full	false	apache-2.0	name results zephyr-smol_llama-100m-sft-full	amazingvince	zephyr-smol_llama-100m-sft-full	text-generation	afrideva	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