Downloads · 30 days
80
3% of all-time downloads
amy011872_-_LawToken-0.5B-a2-gguf
RichardErkhov/amy011872_-_LawToken-0.5B-a2-gguf
amy011872_-_LawToken-0.5B-a2-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
2.3K
Public
Repo size
7.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf8.8 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 22, 2024
- Updated
- Jul 22, 2024
- SHA
- c178272c
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
LawToken-0.5B-a2 - GGUF
- Model creator: https://huggingface.co/amy011872/
- Original model: https://huggingface.co/amy011872/LawToken-0.5B-a2/
| Name | Quant method | Size |
|---|---|---|
| LawToken-0.5B-a2.Q2_K.gguf | Q2_K | 0.33GB |
| LawToken-0.5B-a2.IQ3_XS.gguf | IQ3_XS | 0.33GB |
| LawToken-0.5B-a2.IQ3_S.gguf | IQ3_S | 0.33GB |
| LawToken-0.5B-a2.Q3_K_S.gguf | Q3_K_S | 0.33GB |
| LawToken-0.5B-a2.IQ3_M.gguf | IQ3_M | 0.33GB |
| LawToken-0.5B-a2.Q3_K.gguf | Q3_K | 0.34GB |
| LawToken-0.5B-a2.Q3_K_M.gguf | Q3_K_M | 0.34GB |
| LawToken-0.5B-a2.Q3_K_L.gguf | Q3_K_L | 0.36GB |
| LawToken-0.5B-a2.IQ4_XS.gguf | IQ4_XS | 0.34GB |
| LawToken-0.5B-a2.Q4_0.gguf | Q4_0 | 0.34GB |
| LawToken-0.5B-a2.IQ4_NL.gguf | IQ4_NL | 0.34GB |
| LawToken-0.5B-a2.Q4_K_S.gguf | Q4_K_S | 0.37GB |
| LawToken-0.5B-a2.Q4_K.gguf | Q4_K | 0.38GB |
| LawToken-0.5B-a2.Q4_K_M.gguf | Q4_K_M | 0.38GB |
| LawToken-0.5B-a2.Q4_1.gguf | Q4_1 | 0.36GB |
| LawToken-0.5B-a2.Q5_0.gguf | Q5_0 | 0.38GB |
| LawToken-0.5B-a2.Q5_K_S.gguf | Q5_K_S | 0.4GB |
| LawToken-0.5B-a2.Q5_K.gguf | Q5_K | 0.4GB |
| LawToken-0.5B-a2.Q5_K_M.gguf | Q5_K_M | 0.4GB |
| LawToken-0.5B-a2.Q5_1.gguf | Q5_1 | 0.4GB |
| LawToken-0.5B-a2.Q6_K.gguf | Q6_K | 0.48GB |
| LawToken-0.5B-a2.Q8_0.gguf | Q8_0 | 0.51GB |
Original model description:
license: apache-2.0 base_model: Qwen/Qwen2-0.5B tags:
- trl
- sft
- generated_from_trainer datasets:
- generator model-index:
- name: LawToken-0.5B-a2 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. -->
LawToken-0.5B-a2
This model is a fine-tuned version of Qwen/Qwen2-0.5B on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.8634
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.14 | 0.14 | 10000 | 1.1605 |
| 1.0485 | 0.28 | 20000 | 1.0663 |
| 1.0592 | 0.42 | 30000 | 1.0069 |
| 0.9293 | 0.56 | 40000 | 0.9609 |
| 0.8503 | 0.71 | 50000 | 0.9210 |
| 0.9322 | 0.85 | 60000 | 0.8858 |
| 0.8238 | 0.99 | 70000 | 0.8634 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.3.0a0+ebedce2
- Datasets 2.19.1
- Tokenizers 0.15.2
- Created
- Jul 22, 2024
- Updated
- Jul 22, 2024