license: apache-2.0
tags:
- moe
- mergekit
- Ahmad0067/llama3_Referral_Synth_Data_Phase_1_and_2_merged_adopter
- Ahmad0067/llama3_Bloodwork_Order_Synth_Data_Phase_1_and_2_merged_adopter
- Ahmad0067/llama3_Prescription_Order_Synth_Data_Phase_1_and_2_merged_adopter
---

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

llama-3-8b-Instruct-moe-ref-blood-pres is a Mixture of Experts (MoE) model, configured as follows:
* [Ahmad0067/llama3_Referral_Synth_Data_Phase_1_and_2_merged_adopter](https://huggingface.co/Ahmad0067/llama3_Referral_Synth_Data_Phase_1_and_2_merged_adopter)
  - **Positive Prompts**: This model excels at extracting Referral Orders from medical notes. Therefore, it should be used for exracting Referral Orders.
  - **Negative Prompts**: This model is NOT goog for Bloodwork Orders, nor for Prescription Orders. Therefore, it should NOT be used for Bloodwork Orders and for Prescription Orders extraction.
* [Ahmad0067/llama3_Bloodwork_Order_Synth_Data_Phase_1_and_2_merged_adopter](https://huggingface.co/Ahmad0067/llama3_Bloodwork_Order_Synth_Data_Phase_1_and_2_merged_adopter)
  - **Positive Prompts**: This model excels at extracting Bloodwork Orders from medical notes. Therefore, it should be used for exracting Bloodwork Orders.
  - **Negative Prompts**: This model is NOT goog for Referral Orders, nor for Prescription Orders. Therefore, it should NOT be used for Referral Orders and for Prescription Orders extraction.
* [Ahmad0067/llama3_Prescription_Order_Synth_Data_Phase_1_and_2_merged_adopter](https://huggingface.co/Ahmad0067/llama3_Prescription_Order_Synth_Data_Phase_1_and_2_merged_adopter)
  - **Positive Prompts**: This model excels at extracting Prescription Orders from medical notes. Therefore, it should be used for exracting Prescription Orders.
  - **Negative Prompts**: This model is NOT goog for Bloodwork Orders, nor for Referral Orders. Therefore, it should NOT be used for Bloodwork Orders and for Referral Orders extraction.

## 🧩 Configuration

```yaml

base_model: unsloth/llama-3-8b-Instruct gate_mode: hidden dtype: bfloat16 experts:

  • source_model: Ahmad0067/llama3_Referral_Synth_Data_Phase_1_and_2_merged_adopter positive_prompts:
    • This model excels at extracting Referral Orders from medical notes. Therefore, it should be used for exracting Referral Orders. negative_prompts:
    • This model is NOT goog for Bloodwork Orders, nor for Prescription Orders. Therefore, it should NOT be used for Bloodwork Orders and for Prescription Orders extraction.
  • source_model: Ahmad0067/llama3_Bloodwork_Order_Synth_Data_Phase_1_and_2_merged_adopter positive_prompts:
    • This model excels at extracting Bloodwork Orders from medical notes. Therefore, it should be used for exracting Bloodwork Orders. negative_prompts:
    • This model is NOT goog for Referral Orders, nor for Prescription Orders. Therefore, it should NOT be used for Referral Orders and for Prescription Orders extraction.
  • source_model: Ahmad0067/llama3_Prescription_Order_Synth_Data_Phase_1_and_2_merged_adopter positive_prompts:
    • This model excels at extracting Prescription Orders from medical notes. Therefore, it should be used for exracting Prescription Orders. negative_prompts:
    • This model is NOT goog for Bloodwork Orders, nor for Referral Orders. Therefore, it should NOT be used for Bloodwork Orders and for Referral Orders extraction.

Downloads last month
2
Safetensors
Model size
19.3B params
Tensor type
BF16
·
Inference API
Unable to determine this model's library. Check the docs .