You can deploy this model and start earning money today!

RichardErkhov/
cutelemonlili_-_Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview-gguf

Name: cutelemonlili_-_Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview - GGUF

Model creator: https://huggingface.co/cutelemonlili/
Original model: https://huggingface.co/cutelemonlili/Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview/

Name	Quant method	Size
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q2_K.gguf	Q2_K	0.63GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.IQ3_XS.gguf	IQ3_XS	0.68GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.IQ3_S.gguf	IQ3_S	0.71GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q3_K_S.gguf	Q3_K_S	0.71GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.IQ3_M.gguf	IQ3_M	0.72GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q3_K.gguf	Q3_K	0.77GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q3_K_M.gguf	Q3_K_M	0.77GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q3_K_L.gguf	Q3_K_L	0.82GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.IQ4_XS.gguf	IQ4_XS	0.84GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q4_0.gguf	Q4_0	0.87GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.IQ4_NL.gguf	IQ4_NL	0.88GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q4_K_S.gguf	Q4_K_S	0.88GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q4_K.gguf	Q4_K	0.92GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q4_K_M.gguf	Q4_K_M	0.92GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q4_1.gguf	Q4_1	0.95GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q5_0.gguf	Q5_0	1.02GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q5_K_S.gguf	Q5_K_S	1.02GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q5_K.gguf	Q5_K	1.05GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q5_K_M.gguf	Q5_K_M	1.05GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q5_1.gguf	Q5_1	1.1GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q6_K.gguf	Q6_K	1.19GB
Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview.Q8_0.gguf	Q8_0	1.53GB

Original model description:

library_name: transformers license: other base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct tags:

llama-factory
full
generated_from_trainer model-index:
name: MATH_training_Qwen_QwQ_32B_Preview results: []

MATH_training_Qwen_QwQ_32B_Preview

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-1.5B-Instruct on the MATH_training_Qwen_QwQ_32B_Preview dataset. It achieves the following results on the evaluation set:

Loss: 0.3736

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: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 16
total_eval_batch_size: 4
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.342	0.5988	200	0.3859
0.3094	1.1976	400	0.3811
0.2983	1.7964	600	0.3738

Framework versions

Transformers 4.46.1
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3

RichardErkhov/cutelemonlili_-_Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview-gguf

Original model description:

MATH_training_Qwen_QwQ_32B_Preview

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
cutelemonlili_-_Qwen2.5-Coder-1.5B-Instruct_MATH_training_Qwen_QwQ_32B_Preview-gguf