Quantizations of https://huggingface.co/NECOUDBFM/Jellyfish-13B
Experiment
Quants ending in "_X" are experimental quants. These quants are the same as normal quants, but their token embedding weights are set to Q8_0 except for Q6_K and Q8_0 which are set to F16. The change will make these experimental quants larger but in theory, should result in improved performance.
List of experimental quants:
- Q2_K_X
- Q4_K_M_X
- Q5_K_M_X
- Q6_K_X
- Q8_0_X
Inference Clients/UIs
From original readme
Model Details
Jellyfish-13B is a large language model equipped with 13 billion parameters. It's tailored specifically for data preprocessing tasks, including entity matching, data imputation, error detection, and schema matching.
Prompt Template
### Instruction:
<prompt> (without the <>)
### Response:
- Downloads last month
- 1,782