RichardErkhov/Tensoic_-_Tiny-Llama-openhermes-1.1B-step-715k-1.5T-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Tiny-Llama-openhermes-1.1B-step-715k-1.5T - GGUF

• Model creator: https://huggingface.co/Tensoic/
• Original model: https://huggingface.co/Tensoic/Tiny-Llama-openhermes-1.1B-step-715k-1.5T/

Name	Quant method	Size
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q2_K.gguf	Q2_K	0.4GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.IQ3_XS.gguf	IQ3_XS	0.44GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.IQ3_S.gguf	IQ3_S	0.47GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q3_K_S.gguf	Q3_K_S	0.47GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.IQ3_M.gguf	IQ3_M	0.48GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q3_K.gguf	Q3_K	0.51GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q3_K_M.gguf	Q3_K_M	0.51GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q3_K_L.gguf	Q3_K_L	0.55GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.IQ4_XS.gguf	IQ4_XS	0.57GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q4_0.gguf	Q4_0	0.59GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.IQ4_NL.gguf	IQ4_NL	0.6GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q4_K_S.gguf	Q4_K_S	0.6GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q4_K.gguf	Q4_K	0.62GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q4_K_M.gguf	Q4_K_M	0.62GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q4_1.gguf	Q4_1	0.65GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q5_0.gguf	Q5_0	0.71GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q5_K_S.gguf	Q5_K_S	0.71GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q5_K.gguf	Q5_K	0.73GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q5_K_M.gguf	Q5_K_M	0.73GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q5_1.gguf	Q5_1	0.77GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q6_K.gguf	Q6_K	0.84GB
Tiny-Llama-openhermes-1.1B-step-715k-1.5T.Q8_0.gguf	Q8_0	1.09GB

Original model description:

license: apache-2.0 base_model: PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T tags: - generated_from_trainer model-index: - name: out results: [] datasets: - teknium/openhermes

This model is a fine-tuned version of PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T on the openhermes dataset. It achieves the following results on the evaluation set:

• Loss: 1.2355

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 8
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.4654	0.0	1	3.5326
1.2162	0.05	1503	1.9335
1.1918	0.1	3006	1.7391
1.4188	0.15	4509	1.7574
1.8281	0.2	6012	1.6704
0.8639	0.25	7515	1.7459
1.3764	0.3	9018	1.6832
2.1172	0.35	10521	1.6398
1.1855	0.4	12024	1.6007
1.5604	0.45	13527	1.5256
1.0224	0.5	15030	1.4891
1.5582	0.55	16533	1.4903
0.9489	0.6	18036	1.4179
1.67	0.65	19539	1.4585
0.8542	0.7	21042	1.3810
1.5301	0.75	22545	1.3645
0.951	0.8	24048	1.3087
1.1791	0.85	25551	1.3018
1.3342	0.9	27054	1.2595
1.1221	0.95	28557	1.2355

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.6
• Tokenizers 0.14.1