YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
algograpV4 - GGUF
- Model creator: https://huggingface.co/algograp-Inc/
- Original model: https://huggingface.co/algograp-Inc/algograpV4/
| Name | Quant method | Size |
|---|---|---|
| algograpV4.Q2_K.gguf | Q2_K | 3.77GB |
| algograpV4.Q3_K_S.gguf | Q3_K_S | 4.39GB |
| algograpV4.Q3_K.gguf | Q3_K | 4.88GB |
| algograpV4.Q3_K_M.gguf | Q3_K_M | 4.88GB |
| algograpV4.Q3_K_L.gguf | Q3_K_L | 5.31GB |
| algograpV4.IQ4_XS.gguf | IQ4_XS | 5.47GB |
| algograpV4.Q4_0.gguf | Q4_0 | 5.7GB |
| algograpV4.IQ4_NL.gguf | IQ4_NL | 5.77GB |
| algograpV4.Q4_K_S.gguf | Q4_K_S | 5.75GB |
| algograpV4.Q4_K.gguf | Q4_K | 6.07GB |
| algograpV4.Q4_K_M.gguf | Q4_K_M | 6.07GB |
| algograpV4.Q4_1.gguf | Q4_1 | 6.32GB |
| algograpV4.Q5_0.gguf | Q5_0 | 6.94GB |
| algograpV4.Q5_K_S.gguf | Q5_K_S | 6.94GB |
| algograpV4.Q5_K.gguf | Q5_K | 7.13GB |
| algograpV4.Q5_K_M.gguf | Q5_K_M | 7.13GB |
| algograpV4.Q5_1.gguf | Q5_1 | 7.56GB |
| algograpV4.Q6_K.gguf | Q6_K | 8.26GB |
| algograpV4.Q8_0.gguf | Q8_0 | 10.69GB |
Original model description:
library_name: transformers license: cc-by-nc-4.0 language: - ko
algograp-Inc/algograpV4
Model Details
- Developed by: algograp-Inc
- License: cc-by-nc-4.0
Hardware and Software
- Hardware: We utilized an H100x4 * 1
- Training Factors: We fine-tuned this model using a combination of the DeepSpeed library and the HuggingFace TRL Trainer / HuggingFace Accelerate
Method
- This model was trained using the learning method introduced in the SOLAR paper.
Base Model
- Downloads last month
- 1