Downloads · 30 days
15
5% of all-time downloads
Dayyyan_-_sft_model-gguf
RichardErkhov/Dayyyan_-_sft_model-gguf
Dayyyan_-_sft_model-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
304
Public
Repo size
1.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2.2 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 29, 2024
- Updated
- Sep 29, 2024
- SHA
- a71b4b64
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
sft_model - GGUF
- Model creator: https://huggingface.co/Dayyyan/
- Original model: https://huggingface.co/Dayyyan/sft_model/
| Name | Quant method | Size |
|---|---|---|
| sft_model.Q2_K.gguf | Q2_K | 0.08GB |
| sft_model.IQ3_XS.gguf | IQ3_XS | 0.08GB |
| sft_model.IQ3_S.gguf | IQ3_S | 0.08GB |
| sft_model.Q3_K_S.gguf | Q3_K_S | 0.08GB |
| sft_model.IQ3_M.gguf | IQ3_M | 0.08GB |
| sft_model.Q3_K.gguf | Q3_K | 0.09GB |
| sft_model.Q3_K_M.gguf | Q3_K_M | 0.09GB |
| sft_model.Q3_K_L.gguf | Q3_K_L | 0.09GB |
| sft_model.IQ4_XS.gguf | IQ4_XS | 0.09GB |
| sft_model.Q4_0.gguf | Q4_0 | 0.09GB |
| sft_model.IQ4_NL.gguf | IQ4_NL | 0.09GB |
| sft_model.Q4_K_S.gguf | Q4_K_S | 0.1GB |
| sft_model.Q4_K.gguf | Q4_K | 0.1GB |
| sft_model.Q4_K_M.gguf | Q4_K_M | 0.1GB |
| sft_model.Q4_1.gguf | Q4_1 | 0.09GB |
| sft_model.Q5_0.gguf | Q5_0 | 0.1GB |
| sft_model.Q5_K_S.gguf | Q5_K_S | 0.1GB |
| sft_model.Q5_K.gguf | Q5_K | 0.1GB |
| sft_model.Q5_K_M.gguf | Q5_K_M | 0.1GB |
| sft_model.Q5_1.gguf | Q5_1 | 0.1GB |
| sft_model.Q6_K.gguf | Q6_K | 0.13GB |
| sft_model.Q8_0.gguf | Q8_0 | 0.13GB |
Original model description:
library_name: transformers license: apache-2.0 base_model: HuggingFaceTB/SmolLM-135M tags:
- trl
- sft
- generated_from_trainer model-index:
- name: sft_model results: []
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
sft_model
This model is a fine-tuned version of HuggingFaceTB/SmolLM-135M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9023
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3123 | 0.9992 | 619 | 0.9023 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Created
- Sep 29, 2024
- Updated
- Sep 29, 2024