Downloads · 30 days
113
9% of all-time downloads
alonzogarbanzo_-_Bloom-1b7-ropes-Cont-IT-Step2-gguf
RichardErkhov/alonzogarbanzo_-_Bloom-1b7-ropes-Cont-IT-Step2-gguf
alonzogarbanzo_-_Bloom-1b7-ropes-Cont-IT-Step2-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
1.3K
Public
Repo size
24.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf28.8 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 31, 2024
- Updated
- Oct 31, 2024
- SHA
- f471c144
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Bloom-1b7-ropes-Cont-IT-Step2 - GGUF
- Model creator: https://huggingface.co/alonzogarbanzo/
- Original model: https://huggingface.co/alonzogarbanzo/Bloom-1b7-ropes-Cont-IT-Step2/
| Name | Quant method | Size |
|---|---|---|
| Bloom-1b7-ropes-Cont-IT-Step2.Q2_K.gguf | Q2_K | 0.98GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q3_K_S.gguf | Q3_K_S | 1.1GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q3_K.gguf | Q3_K | 1.2GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q3_K_M.gguf | Q3_K_M | 1.2GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q3_K_L.gguf | Q3_K_L | 1.25GB |
| Bloom-1b7-ropes-Cont-IT-Step2.IQ4_XS.gguf | IQ4_XS | 1.27GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q4_0.gguf | Q4_0 | 1.31GB |
| Bloom-1b7-ropes-Cont-IT-Step2.IQ4_NL.gguf | IQ4_NL | 1.31GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q4_K_S.gguf | Q4_K_S | 1.31GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q4_K.gguf | Q4_K | 1.39GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q4_K_M.gguf | Q4_K_M | 1.39GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q4_1.gguf | Q4_1 | 1.41GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q5_0.gguf | Q5_0 | 1.51GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q5_K_S.gguf | Q5_K_S | 1.51GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q5_K.gguf | Q5_K | 1.57GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q5_K_M.gguf | Q5_K_M | 1.57GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q5_1.gguf | Q5_1 | 1.61GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q6_K.gguf | Q6_K | 1.72GB |
| Bloom-1b7-ropes-Cont-IT-Step2.Q8_0.gguf | Q8_0 | 2.23GB |
Original model description:
license: bigscience-bloom-rail-1.0 base_model: alonzogarbanzo/Bloom-1b7-winograd-wsc-IT-baseline tags:
- generated_from_trainer model-index:
- name: Bloom-1b7-ropes-Cont-IT-Step2 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. -->
Bloom-1b7-ropes-Cont-IT-Step2
This model is a fine-tuned version of alonzogarbanzo/Bloom-1b7-winograd-wsc-IT-baseline on an unknown dataset.
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: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Final Results: {'loss': 0.0261, 'grad_norm': 1.9494764804840088, 'learning_rate': 3.0000000000000004e-07, 'epoch': 10.0}
Average Results: {'train_runtime': 858.2936, 'train_samples_per_second': 2.33, 'train_steps_per_second': 0.583, 'train_loss': 0.4610937827527523, 'epoch': 10.0}
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Created
- Oct 31, 2024
- Updated
- Oct 31, 2024