Update README.md
Browse files
README.md
CHANGED
|
@@ -23,13 +23,13 @@ license: apache-2.0
|
|
| 23 |
|
| 24 |
---
|
| 25 |
|
| 26 |
-
##
|
| 27 |
|
| 28 |
`hippocratically_llama3.2` is a LoRA-finetuned version of Meta’s LLaMA 3.2B-Instruct model, adapted for clinical dialogue and general medical question-answering. It uses instruction-tuning and parameter-efficient fine-tuning (PEFT) methods to create a compact and responsive healthcare assistant for research and educational use.
|
| 29 |
|
| 30 |
---
|
| 31 |
|
| 32 |
-
##
|
| 33 |
|
| 34 |
- Medical Q&A chatbot simulations
|
| 35 |
- Research on LoRA-based instruction tuning
|
|
@@ -38,7 +38,7 @@ license: apache-2.0
|
|
| 38 |
|
| 39 |
---
|
| 40 |
|
| 41 |
-
##
|
| 42 |
|
| 43 |
- Not suitable for clinical deployment
|
| 44 |
- May hallucinate outdated or unsafe information
|
|
@@ -47,7 +47,7 @@ license: apache-2.0
|
|
| 47 |
|
| 48 |
---
|
| 49 |
|
| 50 |
-
##
|
| 51 |
|
| 52 |
- **Base model:** `meta-llama/Llama-3.2-3B-Instruct`
|
| 53 |
- **Fine-tuning method:** LoRA (`r=8`, `alpha=16`, dropout `0.05`)
|
|
@@ -60,3 +60,26 @@ license: apache-2.0
|
|
| 60 |
- **Output dir:** `./llama3.2-medical-chat`
|
| 61 |
|
| 62 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
---
|
| 25 |
|
| 26 |
+
## Model Description
|
| 27 |
|
| 28 |
`hippocratically_llama3.2` is a LoRA-finetuned version of Meta’s LLaMA 3.2B-Instruct model, adapted for clinical dialogue and general medical question-answering. It uses instruction-tuning and parameter-efficient fine-tuning (PEFT) methods to create a compact and responsive healthcare assistant for research and educational use.
|
| 29 |
|
| 30 |
---
|
| 31 |
|
| 32 |
+
## Intended Use
|
| 33 |
|
| 34 |
- Medical Q&A chatbot simulations
|
| 35 |
- Research on LoRA-based instruction tuning
|
|
|
|
| 38 |
|
| 39 |
---
|
| 40 |
|
| 41 |
+
## Limitations
|
| 42 |
|
| 43 |
- Not suitable for clinical deployment
|
| 44 |
- May hallucinate outdated or unsafe information
|
|
|
|
| 47 |
|
| 48 |
---
|
| 49 |
|
| 50 |
+
## Training Details
|
| 51 |
|
| 52 |
- **Base model:** `meta-llama/Llama-3.2-3B-Instruct`
|
| 53 |
- **Fine-tuning method:** LoRA (`r=8`, `alpha=16`, dropout `0.05`)
|
|
|
|
| 60 |
- **Output dir:** `./llama3.2-medical-chat`
|
| 61 |
|
| 62 |
---
|
| 63 |
+
|
| 64 |
+
## Example Prompt:
|
| 65 |
+
prompt: |
|
| 66 |
+
How can someone determine their metabolic rate?
|
| 67 |
+
|
| 68 |
+
## Example response:
|
| 69 |
+
Metabolic rate can be determined in several ways, depending on the context and level of precision required.
|
| 70 |
+
|
| 71 |
+
1. **Basal Metabolic Rate (BMR):** This is the number of calories your body needs at rest. A commonly used formula to estimate BMR for women is:
|
| 72 |
+
|
| 73 |
+
BMR = 655 + (4.35 × weight in lbs) + (4.7 × height in inches) – (4.7 × age in years)
|
| 74 |
+
|
| 75 |
+
For men:
|
| 76 |
+
|
| 77 |
+
BMR = 66 + (6.23 × weight in lbs) + (12.7 × height in inches) – (6.8 × age in years)
|
| 78 |
+
|
| 79 |
+
2. **Harris-Benedict Equation:** This builds on BMR to estimate **Total Daily Energy Expenditure (TDEE)** by multiplying the BMR by an activity factor (e.g., 1.2 for sedentary, 1.55 for moderate activity).
|
| 80 |
+
|
| 81 |
+
3. **Clinical Methods:** More accurate tests, like **indirect calorimetry**, measure oxygen consumption and carbon dioxide production to calculate actual energy expenditure.
|
| 82 |
+
|
| 83 |
+
4. **Wearables and Apps:** Fitness trackers and smart devices offer real-time estimates, though they are less precise.
|
| 84 |
+
|
| 85 |
+
Always consult a healthcare provider for personalized metabolic assessments or weight management planning.
|