Quantization made by Richard Erkhov.

UnFimbulvetr-20B - GGUF

Model creator: https://huggingface.co/KaraKaraWitch/
Original model: https://huggingface.co/KaraKaraWitch/UnFimbulvetr-20B/

Name	Quant method	Size
UnFimbulvetr-20B.Q2_K.gguf	Q2_K	6.87GB
UnFimbulvetr-20B.Q3_K_S.gguf	Q3_K_S	8.01GB
UnFimbulvetr-20B.Q3_K.gguf	Q3_K	8.93GB
UnFimbulvetr-20B.Q3_K_M.gguf	Q3_K_M	8.93GB
UnFimbulvetr-20B.Q3_K_L.gguf	Q3_K_L	9.73GB
UnFimbulvetr-20B.IQ4_XS.gguf	IQ4_XS	10.03GB
UnFimbulvetr-20B.Q4_0.gguf	Q4_0	10.46GB
UnFimbulvetr-20B.IQ4_NL.gguf	IQ4_NL	10.57GB
UnFimbulvetr-20B.Q4_K_S.gguf	Q4_K_S	10.53GB
UnFimbulvetr-20B.Q4_K.gguf	Q4_K	11.14GB
UnFimbulvetr-20B.Q4_K_M.gguf	Q4_K_M	11.14GB
UnFimbulvetr-20B.Q4_1.gguf	Q4_1	11.61GB
UnFimbulvetr-20B.Q5_0.gguf	Q5_0	12.76GB
UnFimbulvetr-20B.Q5_K_S.gguf	Q5_K_S	12.76GB
UnFimbulvetr-20B.Q5_K.gguf	Q5_K	13.11GB
UnFimbulvetr-20B.Q5_K_M.gguf	Q5_K_M	13.11GB
UnFimbulvetr-20B.Q5_1.gguf	Q5_1	13.91GB
UnFimbulvetr-20B.Q6_K.gguf	Q6_K	15.2GB
UnFimbulvetr-20B.Q8_0.gguf	Q8_0	19.69GB

Original model description:

base_model: ["Sao10K/Fimbulvetr-11B-v2"] library_name: transformers tags:

mergekit
merge

UnFimbulvetr-20B

Waifu to catch your attention

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

NOTE: Only tested this just for a bit. YMMV.

Next Day Tests...

Downloaded the GGUF model that someone quantized... And... nope. No.

Do not use model.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Sao10K/Fimbulvetr-11B-v2

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: FimbMagic
      layer_range: [0, 13]
  - sources:
    - model: FimbMagic
      layer_range: [8, 13]
  - sources:
    - model: FimbMagic
      layer_range: [12, 36]
  - sources:
    - model: FimbMagic
      layer_range: [12, 36]
  - sources:
    - model: FimbMagic
      layer_range: [36, 48]
  - sources:
    - model: FimbMagic
      layer_range: [36, 48]
merge_method: passthrough
dtype: bfloat16

Additional Notes

Fimbulvetr 11B is still a very good model. This model is for extreme trailblazers who wants to test stuff!

Eval results? Don't bother.

Last one before I sleep: I'm so sorry Sao10K...