RichardErkhov/tcapelle_-_dummy-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

dummy - GGUF

• Model creator: https://huggingface.co/tcapelle/
• Original model: https://huggingface.co/tcapelle/dummy/

Name	Quant method	Size
dummy.Q2_K.gguf	Q2_K	0.08GB
dummy.IQ3_XS.gguf	IQ3_XS	0.08GB
dummy.IQ3_S.gguf	IQ3_S	0.08GB
dummy.Q3_K_S.gguf	Q3_K_S	0.08GB
dummy.IQ3_M.gguf	IQ3_M	0.08GB
dummy.Q3_K.gguf	Q3_K	0.09GB
dummy.Q3_K_M.gguf	Q3_K_M	0.09GB
dummy.Q3_K_L.gguf	Q3_K_L	0.09GB
dummy.IQ4_XS.gguf	IQ4_XS	0.09GB
dummy.Q4_0.gguf	Q4_0	0.09GB
dummy.IQ4_NL.gguf	IQ4_NL	0.09GB
dummy.Q4_K_S.gguf	Q4_K_S	0.1GB
dummy.Q4_K.gguf	Q4_K	0.1GB
dummy.Q4_K_M.gguf	Q4_K_M	0.1GB
dummy.Q4_1.gguf	Q4_1	0.09GB
dummy.Q5_0.gguf	Q5_0	0.1GB
dummy.Q5_K_S.gguf	Q5_K_S	0.1GB
dummy.Q5_K.gguf	Q5_K	0.1GB
dummy.Q5_K_M.gguf	Q5_K_M	0.1GB
dummy.Q5_1.gguf	Q5_1	0.1GB
dummy.Q6_K.gguf	Q6_K	0.13GB
dummy.Q8_0.gguf	Q8_0	0.13GB

Original model description:

library_name: transformers license: apache-2.0 base_model: HuggingFaceTB/SmolLM2-135M-Instruct tags: - generated_from_trainer model-index: - name: dummy results: []

dummy

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.8188

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	3.8389
3.8269	1.0	63	3.8188

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3