Quantization made by Richard Erkhov.
btulu - GGUF
- Model creator: https://huggingface.co/vwxyzjn/
- Original model: https://huggingface.co/vwxyzjn/btulu/
Name | Quant method | Size |
---|---|---|
btulu.Q2_K.gguf | Q2_K | 2.96GB |
btulu.IQ3_XS.gguf | IQ3_XS | 3.28GB |
btulu.IQ3_S.gguf | IQ3_S | 3.43GB |
btulu.Q3_K_S.gguf | Q3_K_S | 3.41GB |
btulu.IQ3_M.gguf | IQ3_M | 3.52GB |
btulu.Q3_K.gguf | Q3_K | 3.74GB |
btulu.Q3_K_M.gguf | Q3_K_M | 3.74GB |
btulu.Q3_K_L.gguf | Q3_K_L | 4.03GB |
btulu.IQ4_XS.gguf | IQ4_XS | 4.18GB |
btulu.Q4_0.gguf | Q4_0 | 4.34GB |
btulu.IQ4_NL.gguf | IQ4_NL | 4.38GB |
btulu.Q4_K_S.gguf | Q4_K_S | 4.37GB |
btulu.Q4_K.gguf | Q4_K | 4.58GB |
btulu.Q4_K_M.gguf | Q4_K_M | 4.58GB |
btulu.Q4_1.gguf | Q4_1 | 4.78GB |
btulu.Q5_0.gguf | Q5_0 | 5.21GB |
btulu.Q5_K_S.gguf | Q5_K_S | 5.21GB |
btulu.Q5_K.gguf | Q5_K | 5.34GB |
btulu.Q5_K_M.gguf | Q5_K_M | 5.34GB |
btulu.Q5_1.gguf | Q5_1 | 5.65GB |
btulu.Q6_K.gguf | Q6_K | 6.14GB |
btulu.Q8_0.gguf | Q8_0 | 7.95GB |
Original model description:
base_model: [] library_name: transformers tags:
- mergekit
- merge
Untitled Model (1)
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:
- ./llama-3-8b-tulu-v2-numina
- ./llama_3_8b-tulu_v3_mix_preview_4096_OLMoE
Configuration
The following YAML configuration was used to produce this model:
models:
- model: ./llama-3-8b-tulu-v2-numina
parameters:
weight: 0.4
- model: ./llama_3_8b-tulu_v3_mix_preview_4096_OLMoE
parameters:
weight: 0.6
merge_method: linear
dtype: bfloat16