---
{}
---
---
    license: apache-2.0
    tags:
    - moe
    - mergekit
    - Ahmad0067/llama-3-8b-Instruct-Referral_Synth_data_Phase_1_and_2_corect_unsloth_merged
    - Ahmad0067/llama-3-8b-Instruct-Prescriptin_Synth_data_Phase_1_and_2_corect_unsloth_merged
    ---

    # llama-3-8b-Instruct-moe-ref-blood-pres_Unsloth_correct_v2

    llama-3-8b-Instruct-moe-ref-blood-pres_Unsloth_correct_v2 is a Mixture of Experts (MoE) model, configured as follows:
    * [Ahmad0067/llama-3-8b-Instruct-Referral_Synth_data_Phase_1_and_2_corect_unsloth_merged](https://huggingface.co/Ahmad0067/llama-3-8b-Instruct-Referral_Synth_data_Phase_1_and_2_corect_unsloth_merged)
      - **Positive Prompts**: Expert on Referral Orders extraction.
      - **Negative Prompts**: NOT good for Bloodwork Orders., NOT good for Prescription Orders.
    * [Ahmad0067/llama-3-8b-Instruct-Prescriptin_Synth_data_Phase_1_and_2_corect_unsloth_merged](https://huggingface.co/Ahmad0067/llama-3-8b-Instruct-Prescriptin_Synth_data_Phase_1_and_2_corect_unsloth_merged)
      - **Positive Prompts**: Expert on Prescription Orders extraction.
      - **Negative Prompts**: NOT good for Bloodwork Orders., NOT good for Referal Orders.

    ## 🧩 Configuration

    ```yaml
base_model: unsloth/llama-3-8b-Instruct
gate_mode: hidden
dtype: bfloat16
experts:
  - source_model: Ahmad0067/llama-3-8b-Instruct-Referral_Synth_data_Phase_1_and_2_corect_unsloth_merged
    positive_prompts:
      - Expert on Referral Orders extraction.
    negative_prompts:
      - NOT good for Bloodwork Orders.
      - NOT good for Prescription Orders.
  - source_model: Ahmad0067/llama-3-8b-Instruct-Prescriptin_Synth_data_Phase_1_and_2_corect_unsloth_merged
    positive_prompts:
      - Expert on Prescription Orders extraction.
    negative_prompts:
      - NOT good for Bloodwork Orders. 
      - NOT good for Referal Orders.
```