You can deploy this model and start earning money today!

RichardErkhov/
niteshagarwala_-_distilled_chat_math-gguf

Name: niteshagarwala_-_distilled_chat_math-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

distilled_chat_math - GGUF

Model creator: https://huggingface.co/niteshagarwala/
Original model: https://huggingface.co/niteshagarwala/distilled_chat_math/

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

Original model description:

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

generated_from_trainer model-index:
name: distilled_chat_math results: []

distilled_chat_math

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

Loss: 0.1308

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: 4
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.1408	1.3378	500	0.1368
0.1268	2.6756	1000	0.1308

Framework versions

Transformers 4.45.2
Pytorch 2.4.0
Datasets 3.1.0
Tokenizers 0.20.3

RichardErkhov/niteshagarwala_-_distilled_chat_math-gguf

Original model description:

distilled_chat_math

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
niteshagarwala_-_distilled_chat_math-gguf