RichardErkhov/kromcomp_-_L3.1-Blackened-Form-8B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

L3.1-Blackened-Form-8B - GGUF

• Model creator: https://huggingface.co/kromcomp/
• Original model: https://huggingface.co/kromcomp/L3.1-Blackened-Form-8B/

Name	Quant method	Size
L3.1-Blackened-Form-8B.Q2_K.gguf	Q2_K	2.96GB
L3.1-Blackened-Form-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
L3.1-Blackened-Form-8B.IQ3_S.gguf	IQ3_S	3.43GB
L3.1-Blackened-Form-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
L3.1-Blackened-Form-8B.IQ3_M.gguf	IQ3_M	3.52GB
L3.1-Blackened-Form-8B.Q3_K.gguf	Q3_K	3.74GB
L3.1-Blackened-Form-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
L3.1-Blackened-Form-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
L3.1-Blackened-Form-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
L3.1-Blackened-Form-8B.Q4_0.gguf	Q4_0	4.34GB
L3.1-Blackened-Form-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
L3.1-Blackened-Form-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
L3.1-Blackened-Form-8B.Q4_K.gguf	Q4_K	4.58GB
L3.1-Blackened-Form-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
L3.1-Blackened-Form-8B.Q4_1.gguf	Q4_1	4.78GB
L3.1-Blackened-Form-8B.Q5_0.gguf	Q5_0	5.21GB
L3.1-Blackened-Form-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
L3.1-Blackened-Form-8B.Q5_K.gguf	Q5_K	5.34GB
L3.1-Blackened-Form-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
L3.1-Blackened-Form-8B.Q5_1.gguf	Q5_1	5.65GB
L3.1-Blackened-Form-8B.Q6_K.gguf	Q6_K	6.14GB
L3.1-Blackened-Form-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

• ArliAI/Llama-3.1-8B-ArliAI-Formax-v1.0
• Blackroot/Llama3-RP-Lora library_name: transformers tags:
• mergekit
• merge

---

blackened

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• ArliAI/Llama-3.1-8B-ArliAI-Formax-v1.0 + Blackroot/Llama3-RP-Lora

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
parameters:
  int8_mask: 1.0
slices:
- sources:
  - layer_range: [0, 32]
    model: ArliAI/Llama-3.1-8B-ArliAI-Formax-v1.0+Blackroot/Llama3-RP-Lora