Text Generation
Transformers
Safetensors
Thai
English
qwen2
text-generation-inference
sft
trl
4-bit precision
bitsandbytes
LoRA
Fine-Tuning with LoRA
LLM
GenAI
NT GenAI
ntgenai
lahnmah
NT Thai GPT
ntthaigpt
medical
medtech
HealthGPT
หลานม่า
NT Academy
conversational
Inference Endpoints
4-bit precision
Update README.md
Browse files
README.md
CHANGED
|
@@ -26,31 +26,19 @@ license: apache-2.0
|
|
| 26 |
new_version: Aekanun/openthaigpt-MedChatModelv5.1
|
| 27 |
---
|
| 28 |
|
| 29 |
-
# Model Card for `openthaigpt1.5-7b-medical-tuned`
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 42 |
This model is fine-tuned from `openthaigpt1.5-7b-instruct` using Supervised Fine-Tuning (SFT) on the `Thaweewat/thai-med-pack` dataset. The model is designed for medical question-answering tasks in Thai, specializing in providing accurate and contextual answers based on medical information.
|
| 43 |
|
| 44 |
-
|
|
|
|
| 45 |
|
| 46 |
-
|
| 47 |
This model was fine-tuned using Supervised Fine-Tuning (SFT) to optimize it for medical question answering in Thai. The base model is `openthaigpt1.5-7b-instruct`, and it has been enhanced with domain-specific knowledge using the `Thaweewat/thai-med-pack` dataset.
|
| 48 |
|
| 49 |
-
- **Developed by:** Amornpan Phornchaicharoen
|
| 50 |
-
- **Fine-tuned by:** Amornpan Phornchaicharoen
|
| 51 |
- **Model type:** Causal Language Model (AutoModelForCausalLM)
|
| 52 |
- **Language(s):** Thai
|
| 53 |
-
- **License:**
|
| 54 |
- **Fine-tuned from model:** `openthaigpt1.5-7b-instruct`
|
| 55 |
- **Dataset used for fine-tuning:** `Thaweewat/thai-med-pack`
|
| 56 |
|
|
@@ -89,6 +77,19 @@ This model can be used as a foundational model for medical assistance systems, c
|
|
| 89 |
- Limited to the medical domain.
|
| 90 |
- The model is sensitive to prompts and may generate off-topic responses for non-medical queries.
|
| 91 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
## How to Get Started with the Model
|
| 93 |
|
| 94 |
Here’s how to load and use the model for generating medical responses in Thai:
|
|
@@ -194,5 +195,6 @@ print(generated_text)
|
|
| 194 |
- มีความลำบากในการกิน มี
|
| 195 |
```
|
| 196 |
|
| 197 |
-
|
| 198 |
-
|
|
|
|
|
|
| 26 |
new_version: Aekanun/openthaigpt-MedChatModelv5.1
|
| 27 |
---
|
| 28 |
|
| 29 |
+
# 🇹🇭 Model Card for `openthaigpt1.5-7b-medical-tuned`
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 31 |
This model is fine-tuned from `openthaigpt1.5-7b-instruct` using Supervised Fine-Tuning (SFT) on the `Thaweewat/thai-med-pack` dataset. The model is designed for medical question-answering tasks in Thai, specializing in providing accurate and contextual answers based on medical information.
|
| 32 |
|
| 33 |
+
### 👤 **Developed and Fine-tuned by:**
|
| 34 |
+
**Amornpan Phornchaicharoen**, **Aekanun Thongtae**
|
| 35 |
|
| 36 |
+
## Model Description
|
| 37 |
This model was fine-tuned using Supervised Fine-Tuning (SFT) to optimize it for medical question answering in Thai. The base model is `openthaigpt1.5-7b-instruct`, and it has been enhanced with domain-specific knowledge using the `Thaweewat/thai-med-pack` dataset.
|
| 38 |
|
|
|
|
|
|
|
| 39 |
- **Model type:** Causal Language Model (AutoModelForCausalLM)
|
| 40 |
- **Language(s):** Thai
|
| 41 |
+
- **License:** Apache License 2.0
|
| 42 |
- **Fine-tuned from model:** `openthaigpt1.5-7b-instruct`
|
| 43 |
- **Dataset used for fine-tuning:** `Thaweewat/thai-med-pack`
|
| 44 |
|
|
|
|
| 77 |
- Limited to the medical domain.
|
| 78 |
- The model is sensitive to prompts and may generate off-topic responses for non-medical queries.
|
| 79 |
|
| 80 |
+
|
| 81 |
+
## Model Training Results:
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
|
| 93 |
## How to Get Started with the Model
|
| 94 |
|
| 95 |
Here’s how to load and use the model for generating medical responses in Thai:
|
|
|
|
| 195 |
- มีความลำบากในการกิน มี
|
| 196 |
```
|
| 197 |
|
| 198 |
+
### Authors
|
| 199 |
+
* Amornpan Phornchaicharoen (amornpan@gmail.com)
|
| 200 |
+
* Aekanun Thongtae (cto@bangkokfirsttech.com)
|