Your support = more models

My Ko-fi page (Click here)

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using sthenno-com/miscii-14b-1225 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: sthenno-com/miscii-14b-1225
    parameters:
      density: 1
      weight: 1
  - model: unsloth/DeepSeek-R1-Distill-Qwen-14B
    parameters:
      density: 1
      weight: 1
  - model: sthenno/tempesthenno-ppo-ckpt40
    parameters:
      density: 1
      weight: 1

merge_method: ties
base_model: sthenno-com/miscii-14b-1225
tokenizer:
  source: "union"
  tokens: 
    <|im_start|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|im_end|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|object_ref_start|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|object_ref_end|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|box_start|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|box_end|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|quad_start|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|quad_end|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|vision_start|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|vision_end|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|vision_pad|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|image_pad|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|video_pad|>:
      source: "sthenno/tempesthenno-ppo-ckpt40"
    <|begin▁of▁sentence|>:
      source: "unsloth/DeepSeek-R1-Distill-Qwen-14B"
    <|end▁of▁sentence|>:
      source: "unsloth/DeepSeek-R1-Distill-Qwen-14B"
    <|User|>:
      source: "unsloth/DeepSeek-R1-Distill-Qwen-14B"
    <|Assistant|>:
      source: "unsloth/DeepSeek-R1-Distill-Qwen-14B"
    <|begin▁of▁sentence|>:
      source: "unsloth/DeepSeek-R1-Distill-Qwen-14B"
    <|EOT|>:
      source: "unsloth/DeepSeek-R1-Distill-Qwen-14B"
    <think>:
      source: "unsloth/DeepSeek-R1-Distill-Qwen-14B"
    </think>:
      source: "unsloth/DeepSeek-R1-Distill-Qwen-14B"
    <|quad_start|>:
      source: "unsloth/DeepSeek-R1-Distill-Qwen-14B"
    <|quad_end|>:
      source: "unsloth/DeepSeek-R1-Distill-Qwen-14B"
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
Downloads last month
20
Safetensors
Model size
14.8B 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 win10/DeepSeek-R1-Distill-sthenno-14b-0121-union-tokenizer