ondevicellm_-_phi-1_5_sft-gguf

RichardErkhov/ondevicellm_-_phi-1_5_sft-gguf

ondevicellm_-_phi-1_5_sft-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

2% of all-time downloads

All-time downloads

1.2K

Public

Repo size

16.6 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf19.3 GB · 100%

At a glance

Access: Public
Created: Oct 6, 2024
Updated: Oct 6, 2024
SHA: 86a6e1b4

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

phi-1_5_sft - GGUF

Model creator: https://huggingface.co/ondevicellm/
Original model: https://huggingface.co/ondevicellm/phi-1_5_sft/

Name	Quant method	Size
phi-1_5_sft.Q2_K.gguf	Q2_K	0.54GB
phi-1_5_sft.IQ3_XS.gguf	IQ3_XS	0.59GB
phi-1_5_sft.IQ3_S.gguf	IQ3_S	0.61GB
phi-1_5_sft.Q3_K_S.gguf	Q3_K_S	0.61GB
phi-1_5_sft.IQ3_M.gguf	IQ3_M	0.64GB
phi-1_5_sft.Q3_K.gguf	Q3_K	0.69GB
phi-1_5_sft.Q3_K_M.gguf	Q3_K_M	0.69GB
phi-1_5_sft.Q3_K_L.gguf	Q3_K_L	0.75GB
phi-1_5_sft.IQ4_XS.gguf	IQ4_XS	0.74GB
phi-1_5_sft.Q4_0.gguf	Q4_0	0.77GB
phi-1_5_sft.IQ4_NL.gguf	IQ4_NL	0.78GB
phi-1_5_sft.Q4_K_S.gguf	Q4_K_S	0.78GB
phi-1_5_sft.Q4_K.gguf	Q4_K	0.83GB
phi-1_5_sft.Q4_K_M.gguf	Q4_K_M	0.83GB
phi-1_5_sft.Q4_1.gguf	Q4_1	0.85GB
phi-1_5_sft.Q5_0.gguf	Q5_0	0.92GB
phi-1_5_sft.Q5_K_S.gguf	Q5_K_S	0.92GB
phi-1_5_sft.Q5_K.gguf	Q5_K	0.96GB
phi-1_5_sft.Q5_K_M.gguf	Q5_K_M	0.96GB
phi-1_5_sft.Q5_1.gguf	Q5_1	1.0GB
phi-1_5_sft.Q6_K.gguf	Q6_K	1.09GB
phi-1_5_sft.Q8_0.gguf	Q8_0	1.41GB

Original model description:

license: mit base_model: microsoft/phi-1_5 tags:

alignment-handbook
trl
sft
generated_from_trainer
trl
sft
generated_from_trainer datasets:
HuggingFaceH4/ultrachat_200k model-index:
name: phi-1_5_sft results: []

phi-1_5_sft

This model is a fine-tuned version of microsoft/phi-1_5 on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

Loss: 1.2542

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: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
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
lr_scheduler_warmup_steps: 120
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.3099	0.1	100	1.3398
1.3131	0.2	200	1.3159
1.3009	0.3	300	1.3046
1.2915	0.4	400	1.2967
1.2714	0.5	500	1.2906
1.2811	0.6	600	1.2854
1.2621	0.7	700	1.2807
1.2406	0.8	800	1.2767
1.2371	0.9	900	1.2731
1.2547	1.0	1000	1.2699
1.2085	1.1	1100	1.2693
1.2253	1.2	1200	1.2669
1.215	1.3	1300	1.2649
1.2103	1.4	1400	1.2630
1.2081	1.5	1500	1.2612
1.2033	1.6	1600	1.2597
1.2307	1.7	1700	1.2582
1.2038	1.8	1800	1.2568
1.2014	1.9	1900	1.2557
1.188	2.0	2000	1.2546
1.1473	2.1	2100	1.2563
1.1872	2.2	2200	1.2559
1.2086	2.3	2300	1.2553
1.1896	2.4	2400	1.2550
1.1733	2.5	2500	1.2548
1.1665	2.6	2600	1.2544
1.1499	2.7	2700	1.2543
1.1779	2.8	2800	1.2542
1.1746	2.9	2900	1.2542

Framework versions

Transformers 4.37.0
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0

Created: Oct 6, 2024
Updated: Oct 6, 2024