Quantization made by Richard Erkhov.
dissim_round6 - GGUF
- Model creator: https://huggingface.co/s1ghhh/
- Original model: https://huggingface.co/s1ghhh/dissim_round6/
| Name | Quant method | Size |
|---|---|---|
| dissim_round6.Q2_K.gguf | Q2_K | 2.53GB |
| dissim_round6.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| dissim_round6.IQ3_S.gguf | IQ3_S | 2.96GB |
| dissim_round6.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| dissim_round6.IQ3_M.gguf | IQ3_M | 3.06GB |
| dissim_round6.Q3_K.gguf | Q3_K | 3.28GB |
| dissim_round6.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| dissim_round6.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| dissim_round6.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| dissim_round6.Q4_0.gguf | Q4_0 | 3.83GB |
| dissim_round6.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| dissim_round6.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| dissim_round6.Q4_K.gguf | Q4_K | 4.07GB |
| dissim_round6.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| dissim_round6.Q4_1.gguf | Q4_1 | 4.24GB |
| dissim_round6.Q5_0.gguf | Q5_0 | 4.65GB |
| dissim_round6.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| dissim_round6.Q5_K.gguf | Q5_K | 4.78GB |
| dissim_round6.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| dissim_round6.Q5_1.gguf | Q5_1 | 5.07GB |
| dissim_round6.Q6_K.gguf | Q6_K | 5.53GB |
| dissim_round6.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
base_model:
- HuggingFaceH4/zephyr-7b-beta library_name: transformers tags:
- mergekit
- merge
round_5
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the linear merge method.
Models Merged
The following models were included in the merge:
- HuggingFaceH4/zephyr-7b-beta
- /workspace/0814_nips_db_rebuttal/heur/old_codebase/dissim/round_2
Configuration
The following YAML configuration was used to produce this model:
dtype: bfloat16
merge_method: linear
models:
- model: /workspace/0814_nips_db_rebuttal/heur/old_codebase/dissim/round_2
parameters:
weight: 0.7
- model: HuggingFaceH4/zephyr-7b-beta
parameters:
weight: 0.30000000000000004