Downloads · 30 days
372
4% of all-time downloads
lightblue_-_reranker_0.5_bin_filt-gguf
RichardErkhov/lightblue_-_reranker_0.5_bin_filt-gguf
lightblue_-_reranker_0.5_bin_filt-gguf is a text ranking model from RichardErkhov. Use it for the text ranking task on the model card, and read the license before you ship it in a product.
All-time downloads
9.3K
Public
Repo size
8.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf10.5 GB · 100%
At a glance
- Task
- Text Ranking
- Access
- Public
- Created
- Mar 14, 2025
- Updated
- Apr 2, 2025
- SHA
- ef110dd2
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
reranker_0.5_bin_filt - GGUF
- Model creator: https://huggingface.co/lightblue/
- Original model: https://huggingface.co/lightblue/reranker_0.5_bin_filt/
| Name | Quant method | Size |
|---|---|---|
| reranker_0.5_bin_filt.Q2_K.gguf | Q2_K | 0.39GB |
| reranker_0.5_bin_filt.IQ3_XS.gguf | IQ3_XS | 0.39GB |
| reranker_0.5_bin_filt.IQ3_S.gguf | IQ3_S | 0.39GB |
| reranker_0.5_bin_filt.Q3_K_S.gguf | Q3_K_S | 0.39GB |
| reranker_0.5_bin_filt.IQ3_M.gguf | IQ3_M | 0.39GB |
| reranker_0.5_bin_filt.Q3_K.gguf | Q3_K | 0.4GB |
| reranker_0.5_bin_filt.Q3_K_M.gguf | Q3_K_M | 0.4GB |
| reranker_0.5_bin_filt.Q3_K_L.gguf | Q3_K_L | 0.42GB |
| reranker_0.5_bin_filt.IQ4_XS.gguf | IQ4_XS | 0.4GB |
| reranker_0.5_bin_filt.Q4_0.gguf | Q4_0 | 0.4GB |
| reranker_0.5_bin_filt.IQ4_NL.gguf | IQ4_NL | 0.4GB |
| reranker_0.5_bin_filt.Q4_K_S.gguf | Q4_K_S | 0.45GB |
| reranker_0.5_bin_filt.Q4_K.gguf | Q4_K | 0.46GB |
| reranker_0.5_bin_filt.Q4_K_M.gguf | Q4_K_M | 0.46GB |
| reranker_0.5_bin_filt.Q4_1.gguf | Q4_1 | 0.43GB |
| reranker_0.5_bin_filt.Q5_0.gguf | Q5_0 | 0.46GB |
| reranker_0.5_bin_filt.Q5_K_S.gguf | Q5_K_S | 0.48GB |
| reranker_0.5_bin_filt.Q5_K.gguf | Q5_K | 0.49GB |
| reranker_0.5_bin_filt.Q5_K_M.gguf | Q5_K_M | 0.49GB |
| reranker_0.5_bin_filt.Q5_1.gguf | Q5_1 | 0.49GB |
| reranker_0.5_bin_filt.Q6_K.gguf | Q6_K | 0.61GB |
| reranker_0.5_bin_filt.Q8_0.gguf | Q8_0 | 0.63GB |
Original model description:
library_name: transformers license: other base_model: Qwen/Qwen2.5-0.5B-Instruct tags:
- llama-factory
- full
- generated_from_trainer model-index:
- name: reranker_binary_filt_train 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. -->
reranker_binary_filt_train
This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the reranker_binary_filt_train dataset. It achieves the following results on the evaluation set:
- Loss: 0.0526
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 8
- total_eval_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0517 | 0.1000 | 1937 | 0.0871 |
| 0.114 | 0.2001 | 3874 | 0.0835 |
| 0.1033 | 0.3001 | 5811 | 0.0735 |
| 0.0544 | 0.4001 | 7748 | 0.0663 |
| 0.1169 | 0.5001 | 9685 | 0.0623 |
| 0.05 | 0.6002 | 11622 | 0.0599 |
| 0.0951 | 0.7002 | 13559 | 0.0566 |
| 0.0497 | 0.8002 | 15496 | 0.0551 |
| 0.1002 | 0.9002 | 17433 | 0.0532 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Text Ranking
- Created
- Mar 14, 2025
- Updated
- Apr 2, 2025