fine_tune_model

slerp yöntemiyle mergekit kullanılarak üretildi. Son Fıçı RPG projesi için Türkçe + roleplay yeteneklerini birleştirmeyi hedefler.

Birleştirilen modeller

ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1
Sao10K/L3-8B-Lunaris-v1

Konfigürasyon

slices:
  - sources:
      - model: ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1
        layer_range: [0, 32]
      - model: Sao10K/L3-8B-Lunaris-v1
        layer_range: [0, 32]
merge_method: slerp
base_model: ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1
parameters:
  t:
    - filter: self_attn
      value: [0.0, 0.5, 0.3, 0.7, 1.0]
    - filter: mlp
      value: [1.0, 0.5, 0.7, 0.3, 0.0]
    - value: 0.4
dtype: bfloat16
tokenizer_source: base

Downloads last month: 91

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mrtoncl/fine_tune_model-gguf

Sao10K/L3-8B-Lunaris-v1

ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1

Merge model

this model