Quantization made by Richard Erkhov.

Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16 - GGUF

Model creator: https://huggingface.co/alexredna/
Original model: https://huggingface.co/alexredna/Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16/

Name	Quant method	Size
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q2_K.gguf	Q2_K	0.4GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q3_K_S.gguf	Q3_K_S	0.47GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q3_K.gguf	Q3_K	0.51GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q3_K_M.gguf	Q3_K_M	0.51GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q3_K_L.gguf	Q3_K_L	0.55GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.IQ4_XS.gguf	IQ4_XS	0.57GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q4_0.gguf	Q4_0	0.59GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.IQ4_NL.gguf	IQ4_NL	0.6GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q4_K_S.gguf	Q4_K_S	0.6GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q4_K.gguf	Q4_K	0.62GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q4_K_M.gguf	Q4_K_M	0.62GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q4_1.gguf	Q4_1	0.65GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q5_0.gguf	Q5_0	0.71GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q5_K_S.gguf	Q5_K_S	0.71GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q5_K.gguf	Q5_K	0.73GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q5_K_M.gguf	Q5_K_M	0.73GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q5_1.gguf	Q5_1	0.77GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q6_K.gguf	Q6_K	0.84GB
Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16.Q8_0.gguf	Q8_0	1.09GB

Original model description:

license: apache-2.0 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 tags: - trl - sft - generated_from_trainer datasets: - generator model-index: - name: Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16 results: []

Tukan-1.1B-Chat-reasoning-sft-COLA-2.5epr-R8-A16

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the generator dataset. It achieves the following results on the evaluation set:

Loss: 1.0216

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: 5e-05
train_batch_size: 6
eval_batch_size: 3
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 20
total_train_batch_size: 120
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
num_epochs: 2.5

Training results

Training Loss	Epoch	Step	Validation Loss
1.1073	0.24	10	1.1011
1.1024	0.47	20	1.0842
1.0961	0.71	30	1.0675
1.066	0.94	40	1.0529
1.0598	1.18	50	1.0413
1.0384	1.42	60	1.0326
1.0356	1.65	70	1.0268
1.0378	1.89	80	1.0235
1.0376	2.12	90	1.0220
1.0309	2.36	100	1.0215

Framework versions

Transformers 4.36.2
Pytorch 2.2.0a0+gitd925d94
Datasets 2.14.6
Tokenizers 0.15.0