Update README.md
Browse files
README.md
CHANGED
|
@@ -10,22 +10,16 @@ language:
|
|
| 10 |
pipeline_tag: text-generation
|
| 11 |
---
|
| 12 |
|
| 13 |
-
# Model
|
| 14 |
-
|
| 15 |
ReidLM is a fine-tuned version of Meta's LLaMA 3 model, specifically optimized for generating high-quality, contextually accurate responses in the domain of rare diseases. <br>
|
| 16 |
Utilizing the Evol-Instruct methodology, this model was fine-tuned with dataset of over 400 rare diseases.
|
| 17 |
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
## Model Details
|
| 21 |
-
|
| 22 |
-
|
| 23 |
### Model Description
|
| 24 |
|
| 25 |
- **Developed by:** MSRIT
|
| 26 |
- **Model type:** Transformer-based Large Language Model (LLM)
|
| 27 |
- **Language(s) (NLP):** English
|
| 28 |
-
- **License:**
|
| 29 |
- **Finetuned from model:** Meta-Llama-3-8B-Instruct
|
| 30 |
|
| 31 |
## Uses
|
|
@@ -40,8 +34,6 @@ ReidLM is specifically designed for generating information related to rare disea
|
|
| 40 |
- **General Conversational AI:** While capable of generating detailed information on rare diseases, ReidLM may not be suitable for general conversational AI tasks that require a broad understanding of various topics. <br>
|
| 41 |
|
| 42 |
|
| 43 |
-
|
| 44 |
-
|
| 45 |
## Bias, Risks, and Limitations
|
| 46 |
|
| 47 |
ReidLM, like all large language models, has inherent biases and limitations that users should be aware of:<br>
|
|
@@ -77,7 +69,7 @@ generated_text = generate_text(prompt)
|
|
| 77 |
print(generated_text)
|
| 78 |
```
|
| 79 |
|
| 80 |
-
|
| 81 |
|
| 82 |
## Training Details
|
| 83 |
|
|
@@ -94,7 +86,6 @@ print(generated_text)
|
|
| 94 |
|
| 95 |
#### Training Hyperparameters
|
| 96 |
|
| 97 |
-
- **Training regime:**
|
| 98 |
num_train_epochs=3, <br>
|
| 99 |
per_device_train_batch_size=4,<br>
|
| 100 |
gradient_accumulation_steps=2,<br>
|
|
|
|
| 10 |
pipeline_tag: text-generation
|
| 11 |
---
|
| 12 |
|
| 13 |
+
## Model Details
|
|
|
|
| 14 |
ReidLM is a fine-tuned version of Meta's LLaMA 3 model, specifically optimized for generating high-quality, contextually accurate responses in the domain of rare diseases. <br>
|
| 15 |
Utilizing the Evol-Instruct methodology, this model was fine-tuned with dataset of over 400 rare diseases.
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
### Model Description
|
| 18 |
|
| 19 |
- **Developed by:** MSRIT
|
| 20 |
- **Model type:** Transformer-based Large Language Model (LLM)
|
| 21 |
- **Language(s) (NLP):** English
|
| 22 |
+
- **License:**
|
| 23 |
- **Finetuned from model:** Meta-Llama-3-8B-Instruct
|
| 24 |
|
| 25 |
## Uses
|
|
|
|
| 34 |
- **General Conversational AI:** While capable of generating detailed information on rare diseases, ReidLM may not be suitable for general conversational AI tasks that require a broad understanding of various topics. <br>
|
| 35 |
|
| 36 |
|
|
|
|
|
|
|
| 37 |
## Bias, Risks, and Limitations
|
| 38 |
|
| 39 |
ReidLM, like all large language models, has inherent biases and limitations that users should be aware of:<br>
|
|
|
|
| 69 |
print(generated_text)
|
| 70 |
```
|
| 71 |
|
| 72 |
+
<br>
|
| 73 |
|
| 74 |
## Training Details
|
| 75 |
|
|
|
|
| 86 |
|
| 87 |
#### Training Hyperparameters
|
| 88 |
|
|
|
|
| 89 |
num_train_epochs=3, <br>
|
| 90 |
per_device_train_batch_size=4,<br>
|
| 91 |
gradient_accumulation_steps=2,<br>
|