You can deploy this model and start earning money today!

RichardErkhov/
anthonymeo_-_full-train-gguf

Name: anthonymeo_-_full-train-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

full-train - GGUF

Model creator: https://huggingface.co/anthonymeo/
Original model: https://huggingface.co/anthonymeo/full-train/

Name	Quant method	Size
full-train.Q2_K.gguf	Q2_K	0.72GB
full-train.IQ3_XS.gguf	IQ3_XS	0.79GB
full-train.IQ3_S.gguf	IQ3_S	0.83GB
full-train.Q3_K_S.gguf	Q3_K_S	0.83GB
full-train.IQ3_M.gguf	IQ3_M	0.85GB
full-train.Q3_K.gguf	Q3_K	0.9GB
full-train.Q3_K_M.gguf	Q3_K_M	0.9GB
full-train.Q3_K_L.gguf	Q3_K_L	0.96GB
full-train.IQ4_XS.gguf	IQ4_XS	1.0GB
full-train.Q4_0.gguf	Q4_0	1.04GB
full-train.IQ4_NL.gguf	IQ4_NL	1.04GB
full-train.Q4_K_S.gguf	Q4_K_S	1.04GB
full-train.Q4_K.gguf	Q4_K	1.09GB
full-train.Q4_K_M.gguf	Q4_K_M	1.09GB
full-train.Q4_1.gguf	Q4_1	1.14GB
full-train.Q5_0.gguf	Q5_0	1.24GB
full-train.Q5_K_S.gguf	Q5_K_S	1.24GB
full-train.Q5_K.gguf	Q5_K	1.26GB
full-train.Q5_K_M.gguf	Q5_K_M	1.26GB
full-train.Q5_1.gguf	Q5_1	1.33GB
full-train.Q6_K.gguf	Q6_K	1.45GB
full-train.Q8_0.gguf	Q8_0	1.87GB

Original model description:

library_name: transformers license: other base_model: internlm/internlm2_5-1_8b-chat tags:

llama-factory
full
generated_from_trainer model-index:
name: predict results: []

predict

This model is a fine-tuned version of internlm/internlm2_5-1_8b-chat on the expanded dataset. It achieves the following results on the evaluation set:

Loss: 0.3829

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-05
train_batch_size: 4
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.3932	0.5398	100	0.3729
0.235	1.0796	200	0.3673
0.2243	1.6194	300	0.3492
0.1416	2.1592	400	0.3768
0.1247	2.6991	500	0.3841

Framework versions

Transformers 4.44.2
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1

RichardErkhov/anthonymeo_-_full-train-gguf

Original model description:

predict

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
anthonymeo_-_full-train-gguf