YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Quantization made by Richard Erkhov.
MetaModelv2 - GGUF
- Model creator: https://huggingface.co/gagan3012/
- Original model: https://huggingface.co/gagan3012/MetaModelv2/
| Name | Quant method | Size |
|---|---|---|
| MetaModelv2.Q2_K.gguf | Q2_K | 3.73GB |
| MetaModelv2.IQ3_XS.gguf | IQ3_XS | 4.14GB |
| MetaModelv2.IQ3_S.gguf | IQ3_S | 4.37GB |
| MetaModelv2.Q3_K_S.gguf | Q3_K_S | 4.34GB |
| MetaModelv2.IQ3_M.gguf | IQ3_M | 4.51GB |
| MetaModelv2.Q3_K.gguf | Q3_K | 4.84GB |
| MetaModelv2.Q3_K_M.gguf | Q3_K_M | 4.84GB |
| MetaModelv2.Q3_K_L.gguf | Q3_K_L | 5.26GB |
| MetaModelv2.IQ4_XS.gguf | IQ4_XS | 5.43GB |
| MetaModelv2.Q4_0.gguf | Q4_0 | 5.66GB |
| MetaModelv2.IQ4_NL.gguf | IQ4_NL | 5.72GB |
| MetaModelv2.Q4_K_S.gguf | Q4_K_S | 5.7GB |
| MetaModelv2.Q4_K.gguf | Q4_K | 6.02GB |
| MetaModelv2.Q4_K_M.gguf | Q4_K_M | 6.02GB |
| MetaModelv2.Q4_1.gguf | Q4_1 | 6.27GB |
| MetaModelv2.Q5_0.gguf | Q5_0 | 6.89GB |
| MetaModelv2.Q5_K_S.gguf | Q5_K_S | 6.89GB |
| MetaModelv2.Q5_K.gguf | Q5_K | 7.08GB |
| MetaModelv2.Q5_K_M.gguf | Q5_K_M | 7.08GB |
| MetaModelv2.Q5_1.gguf | Q5_1 | 7.51GB |
| MetaModelv2.Q6_K.gguf | Q6_K | 8.2GB |
| MetaModelv2.Q8_0.gguf | Q8_0 | 10.62GB |
Original model description:
license: apache-2.0 tags: - MetaModelv2 - merge
MetaModelv2
This model is a hybrid of the following models and is trained using the following configuration:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 74.24 |
| ARC (25-shot) | 71.08 |
| HellaSwag (10-shot) | 88.56 |
| MMLU (5-shot) | 66.29 |
| TruthfulQA (0-shot) | 71.94 |
| Winogrande (5-shot) | 83.11 |
| GSM8K (5-shot) | 64.44 |
- Downloads last month
- 249
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support