BEE-spoke-data/TinyLlama-3T-1.1bee-GGUF

Quantized GGUF model files for TinyLlama-3T-1.1bee from BEE-spoke-data

Name	Quant method	Size
tinyllama-3t-1.1bee.fp16.gguf	fp16	2.20 GB
tinyllama-3t-1.1bee.q2_k.gguf	q2_k	432.13 MB
tinyllama-3t-1.1bee.q3_k_m.gguf	q3_k_m	548.40 MB
tinyllama-3t-1.1bee.q4_k_m.gguf	q4_k_m	667.81 MB
tinyllama-3t-1.1bee.q5_k_m.gguf	q5_k_m	782.04 MB
tinyllama-3t-1.1bee.q6_k.gguf	q6_k	903.41 MB
tinyllama-3t-1.1bee.q8_0.gguf	q8_0	1.17 GB

Original Model Card:

TinyLlama-3T-1.1bee

A grand successor to the original. This one has the following improvements:

• start from finished 3T TinyLlama
• vastly improved and expanded SoTA beekeeping dataset

Model description

This model is a fine-tuned version of TinyLlama-1.1b-3T on the BEE-spoke-data/bees-internal dataset.

It achieves the following results on the evaluation set:

• Loss: 2.1640
• Accuracy: 0.5406

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 4
• eval_batch_size: 2
• seed: 13707
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.4432	0.19	50	2.3850	0.5033
2.3655	0.39	100	2.3124	0.5129
2.374	0.58	150	2.2588	0.5215
2.3558	0.78	200	2.2132	0.5291
2.2677	0.97	250	2.1828	0.5348
2.0701	1.17	300	2.1788	0.5373
2.0766	1.36	350	2.1673	0.5398
2.0669	1.56	400	2.1651	0.5402
2.0314	1.75	450	2.1641	0.5406
2.0281	1.95	500	2.1639	0.5407

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0
• Datasets 2.16.1
• Tokenizers 0.15.0