RichardErkhov/Edens-Gate_-_DPO-Baldur-testing-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

DPO-Baldur-testing - GGUF

• Model creator: https://huggingface.co/Edens-Gate/
• Original model: https://huggingface.co/Edens-Gate/DPO-Baldur-testing/

Name	Quant method	Size
DPO-Baldur-testing.Q2_K.gguf	Q2_K	2.96GB
DPO-Baldur-testing.IQ3_XS.gguf	IQ3_XS	3.28GB
DPO-Baldur-testing.IQ3_S.gguf	IQ3_S	3.43GB
DPO-Baldur-testing.Q3_K_S.gguf	Q3_K_S	3.41GB
DPO-Baldur-testing.IQ3_M.gguf	IQ3_M	3.52GB
DPO-Baldur-testing.Q3_K.gguf	Q3_K	3.74GB
DPO-Baldur-testing.Q3_K_M.gguf	Q3_K_M	3.74GB
DPO-Baldur-testing.Q3_K_L.gguf	Q3_K_L	4.03GB
DPO-Baldur-testing.IQ4_XS.gguf	IQ4_XS	4.18GB
DPO-Baldur-testing.Q4_0.gguf	Q4_0	4.34GB
DPO-Baldur-testing.IQ4_NL.gguf	IQ4_NL	4.38GB
DPO-Baldur-testing.Q4_K_S.gguf	Q4_K_S	4.37GB
DPO-Baldur-testing.Q4_K.gguf	Q4_K	4.58GB
DPO-Baldur-testing.Q4_K_M.gguf	Q4_K_M	4.58GB
DPO-Baldur-testing.Q4_1.gguf	Q4_1	4.78GB
DPO-Baldur-testing.Q5_0.gguf	Q5_0	5.21GB
DPO-Baldur-testing.Q5_K_S.gguf	Q5_K_S	5.21GB
DPO-Baldur-testing.Q5_K.gguf	Q5_K	5.34GB
DPO-Baldur-testing.Q5_K_M.gguf	Q5_K_M	5.34GB
DPO-Baldur-testing.Q5_1.gguf	Q5_1	5.65GB
DPO-Baldur-testing.Q6_K.gguf	Q6_K	6.14GB
DPO-Baldur-testing.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

• Delta-Vector/Baldur-8B
• NewEden/baldur-DPO-lora library_name: transformers tags:
• mergekit
• merge

---

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using Delta-Vector/Baldur-8B + NewEden/baldur-DPO-lora as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: Delta-Vector/Baldur-8B+NewEden/baldur-DPO-lora
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 32]
    model: Delta-Vector/Baldur-8B+NewEden/baldur-DPO-lora
    parameters:
      weight: 1.0