You can deploy this model and start earning money today!

RichardErkhov/
tsavage68_-_Na_M2_1000steps_1e6rate_SFT-gguf

Name: tsavage68_-_Na_M2_1000steps_1e6rate_SFT-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Na_M2_1000steps_1e6rate_SFT - GGUF

Model creator: https://huggingface.co/tsavage68/
Original model: https://huggingface.co/tsavage68/Na_M2_1000steps_1e6rate_SFT/

Name	Quant method	Size
Na_M2_1000steps_1e6rate_SFT.Q2_K.gguf	Q2_K	2.53GB
Na_M2_1000steps_1e6rate_SFT.IQ3_XS.gguf	IQ3_XS	2.81GB
Na_M2_1000steps_1e6rate_SFT.IQ3_S.gguf	IQ3_S	2.96GB
Na_M2_1000steps_1e6rate_SFT.Q3_K_S.gguf	Q3_K_S	2.95GB
Na_M2_1000steps_1e6rate_SFT.IQ3_M.gguf	IQ3_M	3.06GB
Na_M2_1000steps_1e6rate_SFT.Q3_K.gguf	Q3_K	3.28GB
Na_M2_1000steps_1e6rate_SFT.Q3_K_M.gguf	Q3_K_M	3.28GB
Na_M2_1000steps_1e6rate_SFT.Q3_K_L.gguf	Q3_K_L	3.4GB
Na_M2_1000steps_1e6rate_SFT.IQ4_XS.gguf	IQ4_XS	3.18GB
Na_M2_1000steps_1e6rate_SFT.Q4_0.gguf	Q4_0	3.08GB
Na_M2_1000steps_1e6rate_SFT.IQ4_NL.gguf	IQ4_NL	2.5GB
Na_M2_1000steps_1e6rate_SFT.Q4_K_S.gguf	Q4_K_S	3.86GB
Na_M2_1000steps_1e6rate_SFT.Q4_K.gguf	Q4_K	4.07GB
Na_M2_1000steps_1e6rate_SFT.Q4_K_M.gguf	Q4_K_M	4.07GB
Na_M2_1000steps_1e6rate_SFT.Q4_1.gguf	Q4_1	4.24GB
Na_M2_1000steps_1e6rate_SFT.Q5_0.gguf	Q5_0	4.65GB
Na_M2_1000steps_1e6rate_SFT.Q5_K_S.gguf	Q5_K_S	4.65GB
Na_M2_1000steps_1e6rate_SFT.Q5_K.gguf	Q5_K	4.78GB
Na_M2_1000steps_1e6rate_SFT.Q5_K_M.gguf	Q5_K_M	4.78GB
Na_M2_1000steps_1e6rate_SFT.Q5_1.gguf	Q5_1	5.07GB
Na_M2_1000steps_1e6rate_SFT.Q6_K.gguf	Q6_K	5.53GB
Na_M2_1000steps_1e6rate_SFT.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers license: apache-2.0 base_model: mistralai/Mistral-7B-Instruct-v0.2 tags:

trl
sft
generated_from_trainer model-index:
name: Na_M2_1000steps_1e6rate_SFT results: []

Na_M2_1000steps_1e6rate_SFT

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1550

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: 1e-06
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
0.349	0.2667	50	0.3425
0.2797	0.5333	100	0.2671
0.1882	0.8	150	0.1831
0.1593	1.0667	200	0.1748
0.1609	1.3333	250	0.1586
0.1544	1.6	300	0.1575
0.1558	1.8667	350	0.1564
0.1524	2.1333	400	0.1574
0.1527	2.4	450	0.1568
0.1564	2.6667	500	0.1554
0.1523	2.9333	550	0.1563
0.1519	3.2	600	0.1558
0.1532	3.4667	650	0.1555
0.1508	3.7333	700	0.1549
0.1518	4.0	750	0.1550
0.1507	4.2667	800	0.1551
0.1501	4.5333	850	0.1550
0.1477	4.8	900	0.1549
0.1464	5.0667	950	0.1550
0.1488	5.3333	1000	0.1550

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1

RichardErkhov/tsavage68_-_Na_M2_1000steps_1e6rate_SFT-gguf

Original model description:

Na_M2_1000steps_1e6rate_SFT

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
tsavage68_-_Na_M2_1000steps_1e6rate_SFT-gguf