You can deploy this model and start earning money today!

RichardErkhov/
win10_-_Phi-3.5-mini-instruct-24-9-29-gguf

Name: win10_-_Phi-3.5-mini-instruct-24-9-29-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Phi-3.5-mini-instruct-24-9-29 - GGUF

Model creator: https://huggingface.co/win10/
Original model: https://huggingface.co/win10/Phi-3.5-mini-instruct-24-9-29/

Name	Quant method	Size
Phi-3.5-mini-instruct-24-9-29.Q2_K.gguf	Q2_K	1.32GB
Phi-3.5-mini-instruct-24-9-29.IQ3_XS.gguf	IQ3_XS	1.51GB
Phi-3.5-mini-instruct-24-9-29.IQ3_S.gguf	IQ3_S	1.57GB
Phi-3.5-mini-instruct-24-9-29.Q3_K_S.gguf	Q3_K_S	1.57GB
Phi-3.5-mini-instruct-24-9-29.IQ3_M.gguf	IQ3_M	1.73GB
Phi-3.5-mini-instruct-24-9-29.Q3_K.gguf	Q3_K	1.82GB
Phi-3.5-mini-instruct-24-9-29.Q3_K_M.gguf	Q3_K_M	1.82GB
Phi-3.5-mini-instruct-24-9-29.Q3_K_L.gguf	Q3_K_L	1.94GB
Phi-3.5-mini-instruct-24-9-29.IQ4_XS.gguf	IQ4_XS	1.93GB
Phi-3.5-mini-instruct-24-9-29.Q4_0.gguf	Q4_0	2.03GB
Phi-3.5-mini-instruct-24-9-29.IQ4_NL.gguf	IQ4_NL	2.04GB
Phi-3.5-mini-instruct-24-9-29.Q4_K_S.gguf	Q4_K_S	2.04GB
Phi-3.5-mini-instruct-24-9-29.Q4_K.gguf	Q4_K	2.23GB
Phi-3.5-mini-instruct-24-9-29.Q4_K_M.gguf	Q4_K_M	2.23GB
Phi-3.5-mini-instruct-24-9-29.Q4_1.gguf	Q4_1	2.24GB
Phi-3.5-mini-instruct-24-9-29.Q5_0.gguf	Q5_0	2.46GB
Phi-3.5-mini-instruct-24-9-29.Q5_K_S.gguf	Q5_K_S	2.46GB
Phi-3.5-mini-instruct-24-9-29.Q5_K.gguf	Q5_K	2.62GB
Phi-3.5-mini-instruct-24-9-29.Q5_K_M.gguf	Q5_K_M	2.62GB
Phi-3.5-mini-instruct-24-9-29.Q5_1.gguf	Q5_1	2.68GB
Phi-3.5-mini-instruct-24-9-29.Q6_K.gguf	Q6_K	2.92GB
Phi-3.5-mini-instruct-24-9-29.Q8_0.gguf	Q8_0	3.78GB

Original model description:

library_name: transformers license: other base_model: microsoft/Phi-3.5-mini-instruct tags:

llama-factory
freeze
generated_from_trainer model-index:
name: microsoft/Phi-3.5-mini-instruct results: []

my DC sever

https://discord.gg/yaTfFF6Ut2

我正在計畫微調64K指令模型，請幫助我進行計畫

Support me here if you're interested:

Ko-fi: https://ko-fi.com/ogodwin10

Phi-3.5-mini-instruct-24-9-29

This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on the lmsys_chat dataset. It achieves the following results on the evaluation set:

Loss: 1.3194

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: 0.0001
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: reduce_lr_on_plateau
training_steps: 1000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.428	0.0160	100	1.3194
1.2653	0.0320	200	1.3194
1.3084	0.0480	300	1.3194
1.3234	0.0641	400	1.3194
1.4091	0.0801	500	1.3194
1.2878	0.0961	600	1.3194
1.2933	0.1121	700	1.3194
1.3246	0.1281	800	1.3194
1.2911	0.1441	900	1.3194
1.4227	0.1602	1000	1.3194

Framework versions

Transformers 4.45.0
Pytorch 2.4.0+cu124
Datasets 2.19.1
Tokenizers 0.20.0

RichardErkhov/win10_-_Phi-3.5-mini-instruct-24-9-29-gguf

Original model description:

my DC sever

我正在計畫微調64K指令模型，請幫助我進行計畫

Ko-fi: https://ko-fi.com/ogodwin10

Phi-3.5-mini-instruct-24-9-29

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
win10_-_Phi-3.5-mini-instruct-24-9-29-gguf