Downloads · 30 days
7
13% of all-time downloads
llama-3-8b-Instruct-moe-ref-blood-pres_Unsloth_correct_v2
Ahmad0067/llama-3-8b-Instruct-moe-ref-blood-pres_Unsloth_correct_v2
llama-3-8b-Instruct-moe-ref-blood-pres_Unsloth_correct_v2 is a machine learning model from Ahmad0067. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
--- license: apache-2.0 tags: - moe - mergekit - Ahmad0067/llama-3-8b-Instruct-ReferralSynthdataPhase1and2corectunslothmerged - Ahmad0067/llama-3-8b-Instruct-PrescriptinSynthdataPhase1and2corectunslothmerged ---
All-time downloads
55
Public
Parameters
13.7B
27.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors27.3 GB · 100%
At a glance
- Model type
- mixtral
- Access
- Public
- Created
- Sep 9, 2024
- Updated
- Sep 9, 2024
- SHA
- 66b376bc
Model card
From the Hugging Face model README
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.
- Type
- mixtral
- Created
- Sep 9, 2024
- Updated
- Sep 9, 2024