Downloads · 30 days
89
6% of all-time downloads
Harshatheeswar_-_babylama-gpttoken-gguf
RichardErkhov/Harshatheeswar_-_babylama-gpttoken-gguf
Harshatheeswar_-_babylama-gpttoken-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
1.5K
Public
Repo size
1.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf1.4 GB · 100%
At a glance
- Access
- Public
- Created
- Feb 12, 2025
- Updated
- Feb 12, 2025
- SHA
- 97176ec5
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
babylama-gpttoken - GGUF
- Model creator: https://huggingface.co/Harshatheeswar/
- Original model: https://huggingface.co/Harshatheeswar/babylama-gpttoken/
| Name | Quant method | Size |
|---|---|---|
| babylama-gpttoken.Q2_K.gguf | Q2_K | 0.04GB |
| babylama-gpttoken.IQ3_XS.gguf | IQ3_XS | 0.05GB |
| babylama-gpttoken.IQ3_S.gguf | IQ3_S | 0.05GB |
| babylama-gpttoken.Q3_K_S.gguf | Q3_K_S | 0.05GB |
| babylama-gpttoken.IQ3_M.gguf | IQ3_M | 0.05GB |
| babylama-gpttoken.Q3_K.gguf | Q3_K | 0.05GB |
| babylama-gpttoken.Q3_K_M.gguf | Q3_K_M | 0.05GB |
| babylama-gpttoken.Q3_K_L.gguf | Q3_K_L | 0.05GB |
| babylama-gpttoken.IQ4_XS.gguf | IQ4_XS | 0.06GB |
| babylama-gpttoken.Q4_0.gguf | Q4_0 | 0.06GB |
| babylama-gpttoken.IQ4_NL.gguf | IQ4_NL | 0.06GB |
| babylama-gpttoken.Q4_K_S.gguf | Q4_K_S | 0.06GB |
| babylama-gpttoken.Q4_K.gguf | Q4_K | 0.06GB |
| babylama-gpttoken.Q4_K_M.gguf | Q4_K_M | 0.06GB |
| babylama-gpttoken.Q4_1.gguf | Q4_1 | 0.06GB |
| babylama-gpttoken.Q5_0.gguf | Q5_0 | 0.06GB |
| babylama-gpttoken.Q5_K_S.gguf | Q5_K_S | 0.06GB |
| babylama-gpttoken.Q5_K.gguf | Q5_K | 0.07GB |
| babylama-gpttoken.Q5_K_M.gguf | Q5_K_M | 0.07GB |
| babylama-gpttoken.Q5_1.gguf | Q5_1 | 0.07GB |
| babylama-gpttoken.Q6_K.gguf | Q6_K | 0.07GB |
| babylama-gpttoken.Q8_0.gguf | Q8_0 | 0.09GB |
Original model description:
library_name: transformers base_model: babylm/babyllama-100m-2024 tags:
- generated_from_trainer model-index:
- name: babylama-gpttoken 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. -->
babylama-gpttoken
This model is a fine-tuned version of babylm/babyllama-100m-2024 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 38.2921
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 30.4256 | 0.9999 | 5559 | 29.8987 |
| 38.306 | 1.9999 | 11119 | 37.7677 |
| 38.7146 | 3.0000 | 16679 | 37.7375 |
| 37.8024 | 4.0 | 22239 | 38.2709 |
| 37.35 | 4.9993 | 27795 | 38.2921 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1
- Created
- Feb 12, 2025
- Updated
- Feb 12, 2025