merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-Coder-7B-Instruct
  - model: Qwen/Qwen2.5-Coder-7B-Instruct
merge_method: slerp
tokenizer_merge_method: slerp
tokenizer_parameters:
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
dtype: bfloat16
parameters:
  t: [0, 0.3, 0.6, 0.8, 0.6, 0.3, 0]  # Curva che favorisce leggermente il centro del merge
  temp: 1.0   # Temperatura aumentata per un merge più audace
density:
  - threshold: 0.05
    t: 0.8
  - threshold: 0.3
    t: 0.6
  - threshold: 0.7
    t: 0.4
  - threshold: 0.95
    t: 0.2
noise: 0.1  # Aggiunto rumore per ulteriore variabilità
Downloads last month
18
Safetensors
Model size
7.62B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ClaudioItaly/Coder

Base model

Qwen/Qwen2.5-7B
Finetuned
(26)
this model
Quantizations
2 models