You can deploy this model and start earning money today!

Meggido/
L3-SAO-MIX-8B-V1-6.5bpw-h8-exl2

Name: L3-SAO-MIX-8B-V1-6.5bpw-h8-exl2
Availability: InStock

Views

No views yet

⚡ExLlamaV2 quant of : L3-SAO-MIX-8B-V1

[!note] ➡️ Exl2 version : 0.2.3
➡️ Cal. dataset : Default.
📄 Measurement.json file.

Experimental merge of Sao10k Llama3-8B based model

L3-SAO-MIX-8B-V1

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

I'm trying to combine the best model from Sao10k. And turn out, this is beyond my expectation. I use it for RP and ERP on scenario card. And it follow the instruction very well (At least for me). All credits and thanks go to Sao10k for providing amazing models used in the merge.

Prompt template: Llama3 Instruct.

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>

Settings

Temprature: 1.3
Min-P: 0.1
// If using DRY
Multiplier: 2
Base: 1.75
Allowed Length: 2
Penalty Range: 0

Merge details

Merge Method

This model was merged using the della merge method using Sao10K/L3-8B-Niitama-v1 as a base.

Models Merged

The following models were included in the merge:

Sao10K/L3-8B-Lunaris-v1
Sao10K/L3-8B-Stheno-v3.2
Sao10K/L3-8B-Niitama-v1
Sao10K/L3-8B-Tamamo-v1

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model: Sao10K/L3-8B-Niitama-v1
merge_method: della
dtype: bfloat16
models:
  - model: Sao10K/L3-8B-Lunaris-v1
    parameters:
      weight: 1.0
  - model: Sao10K/L3-8B-Stheno-v3.2
    parameters:
      weight: 1.0
  - model: Sao10K/L3-8B-Niitama-v1
    parameters:
      weight: 1.0
  - model: Sao10K/L3-8B-Tamamo-v1
    parameters:
      weight: 1.0

Meggido/L3-SAO-MIX-8B-V1-6.5bpw-h8-exl2