You can deploy this model and start earning money today!

RichardErkhov/
abdeljalilELmajjodi_-_SmolLM2-135M-ft-ary-only-hs-gguf

Name: abdeljalilELmajjodi_-_SmolLM2-135M-ft-ary-only-hs-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

SmolLM2-135M-ft-ary-only-hs - GGUF

Name	Quant method	Size
SmolLM2-135M-ft-ary-only-hs.Q2_K.gguf	Q2_K	0.08GB
SmolLM2-135M-ft-ary-only-hs.IQ3_XS.gguf	IQ3_XS	0.08GB
SmolLM2-135M-ft-ary-only-hs.IQ3_S.gguf	IQ3_S	0.08GB
SmolLM2-135M-ft-ary-only-hs.Q3_K_S.gguf	Q3_K_S	0.08GB
SmolLM2-135M-ft-ary-only-hs.IQ3_M.gguf	IQ3_M	0.08GB
SmolLM2-135M-ft-ary-only-hs.Q3_K.gguf	Q3_K	0.09GB
SmolLM2-135M-ft-ary-only-hs.Q3_K_M.gguf	Q3_K_M	0.09GB
SmolLM2-135M-ft-ary-only-hs.Q3_K_L.gguf	Q3_K_L	0.09GB
SmolLM2-135M-ft-ary-only-hs.IQ4_XS.gguf	IQ4_XS	0.09GB
SmolLM2-135M-ft-ary-only-hs.Q4_0.gguf	Q4_0	0.09GB
SmolLM2-135M-ft-ary-only-hs.IQ4_NL.gguf	IQ4_NL	0.09GB
SmolLM2-135M-ft-ary-only-hs.Q4_K_S.gguf	Q4_K_S	0.1GB
SmolLM2-135M-ft-ary-only-hs.Q4_K.gguf	Q4_K	0.1GB
SmolLM2-135M-ft-ary-only-hs.Q4_K_M.gguf	Q4_K_M	0.1GB
SmolLM2-135M-ft-ary-only-hs.Q4_1.gguf	Q4_1	0.09GB
SmolLM2-135M-ft-ary-only-hs.Q5_0.gguf	Q5_0	0.1GB
SmolLM2-135M-ft-ary-only-hs.Q5_K_S.gguf	Q5_K_S	0.1GB
SmolLM2-135M-ft-ary-only-hs.Q5_K.gguf	Q5_K	0.1GB
SmolLM2-135M-ft-ary-only-hs.Q5_K_M.gguf	Q5_K_M	0.1GB
SmolLM2-135M-ft-ary-only-hs.Q5_1.gguf	Q5_1	0.1GB
SmolLM2-135M-ft-ary-only-hs.Q6_K.gguf	Q6_K	0.13GB
SmolLM2-135M-ft-ary-only-hs.Q8_0.gguf	Q8_0	0.13GB

Original model description:

library_name: transformers license: apache-2.0 base_model: HuggingFaceTB/SmolLM2-135M tags:

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 1

Training Loss	Epoch	Step	Validation Loss
1.6507	1.0	51039	1.6494