base_model: Qwen/Qwen2.5-1.5B-Instruct
gate_mode: cheap_embed
architecture: qwen
experts_per_token: 4
dtype: bfloat16
experts:
  - source_model: Qwen/Qwen2.5-1.5B-Instruct
    positive_prompts: ["chat assistant"]
  - source_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    positive_prompts: ["code assistant"]
  - source_model: Qwen/Qwen2.5-Math-1.5B-Instruct
    positive_prompts: ["math assistant"]
  - source_model: huihui-ai/Qwen2.5-1.5B-Instruct-abliterated
    positive_prompts: ["uncensored assistant"]
  - source_model: Rombo-Org/Rombo-LLM-V2.5-Qwen-1.5b
    positive_prompts: ["review assistant"]
  - source_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
    positive_prompts: ["logical assistant"]
  - source_model: Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct
    positive_prompts: ["writing assistant"]
  - source_model: RefalMachine/RuadaptQwen2.5-1.5B-instruct
    positive_prompts: ["text editing assistant"]
shared_experts:
  - source_model: Qwen/Qwen2.5-1.5B-Instruct
    positive_prompts: ["chat assistant"]
    residual_scale: 0.1
Downloads last month
10
Safetensors
Model size
11B 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 ehristoforu/tmoe-v2

Quantizations
1 model