merge

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: linear
dtype: float32
out_dtype: bfloat16
models:
  - model: unsloth/Meta-Llama-3.1-8B
    parameters:
      weight: 1.0
  - model: unsloth/Meta-Llama-3.1-8B-Instruct
    parameters:
      weight: 0.0
tokenizer:
  source: unsloth/Meta-Llama-3.1-8B-Instruct
  tokens:
    <|begin_of_text|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|end_of_text|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|finetune_right_pad_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|start_header_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|end_header_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eom_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eot_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|python_tag|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eot_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eot_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
Downloads last month
5
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for mergekit-community/LLaMa-3.1-8B-InitializedEmbeds

Merge model
this model
Finetunes
1 model
Quantizations
1 model