Downloads · 30 days
86
2% of all-time downloads
LDCC_-_LDCC-SOLAR-10.7B-gguf
RichardErkhov/LDCC_-_LDCC-SOLAR-10.7B-gguf
LDCC_-_LDCC-SOLAR-10.7B-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
3.7K
Public
Repo size
112 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf131 GB · 100%
At a glance
- Access
- Public
- Created
- May 12, 2024
- Updated
- May 12, 2024
- SHA
- 3c9c43ec
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
LDCC-SOLAR-10.7B - GGUF
- Model creator: https://huggingface.co/LDCC/
- Original model: https://huggingface.co/LDCC/LDCC-SOLAR-10.7B/
| Name | Quant method | Size |
|---|---|---|
| LDCC-SOLAR-10.7B.Q2_K.gguf | Q2_K | 3.8GB |
| LDCC-SOLAR-10.7B.IQ3_XS.gguf | IQ3_XS | 4.22GB |
| LDCC-SOLAR-10.7B.IQ3_S.gguf | IQ3_S | 4.45GB |
| LDCC-SOLAR-10.7B.Q3_K_S.gguf | Q3_K_S | 4.42GB |
| LDCC-SOLAR-10.7B.IQ3_M.gguf | IQ3_M | 4.59GB |
| LDCC-SOLAR-10.7B.Q3_K.gguf | Q3_K | 4.92GB |
| LDCC-SOLAR-10.7B.Q3_K_M.gguf | Q3_K_M | 4.92GB |
| LDCC-SOLAR-10.7B.Q3_K_L.gguf | Q3_K_L | 5.34GB |
| LDCC-SOLAR-10.7B.IQ4_XS.gguf | IQ4_XS | 5.51GB |
| LDCC-SOLAR-10.7B.Q4_0.gguf | Q4_0 | 5.74GB |
| LDCC-SOLAR-10.7B.IQ4_NL.gguf | IQ4_NL | 5.8GB |
| LDCC-SOLAR-10.7B.Q4_K_S.gguf | Q4_K_S | 5.78GB |
| LDCC-SOLAR-10.7B.Q4_K.gguf | Q4_K | 6.1GB |
| LDCC-SOLAR-10.7B.Q4_K_M.gguf | Q4_K_M | 6.1GB |
| LDCC-SOLAR-10.7B.Q4_1.gguf | Q4_1 | 6.36GB |
| LDCC-SOLAR-10.7B.Q5_0.gguf | Q5_0 | 6.98GB |
| LDCC-SOLAR-10.7B.Q5_K_S.gguf | Q5_K_S | 6.98GB |
| LDCC-SOLAR-10.7B.Q5_K.gguf | Q5_K | 7.17GB |
| LDCC-SOLAR-10.7B.Q5_K_M.gguf | Q5_K_M | 7.17GB |
| LDCC-SOLAR-10.7B.Q5_1.gguf | Q5_1 | 7.6GB |
| LDCC-SOLAR-10.7B.Q6_K.gguf | Q6_K | 8.3GB |
Original model description:
license: cc-by-nc-4.0 language:
- ko
Model Card for LDCC-SOLAR-10.7B
Developed by : Wonchul Kim (Lotte Data Communication AI Technical Team)
Hardware and Software
- Hardware: We utilized an A100x4 * 1 for training our model
- 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
- yanolja/KoSOLAR-10.7B-v0.1 (This model is no longer supported due to a tokenizer issue.)
Caution
- If you want to fine-tune this model, it is recommended to use the tokenizer.json and tokenizer_config.json files from revision v1.1.
- Created
- May 12, 2024
- Updated
- May 12, 2024