Update README.md
Browse files
README.md
CHANGED
|
@@ -40,8 +40,7 @@ This model is a finetuned version of Qwen/Qwen2.5-0.5B-Instruct, a 0.5 billion p
|
|
| 40 |
The finetuning was performed using SFT following by Group Relative Policy Optimization (GRPO).
|
| 41 |
|
| 42 |
- **Developed by:** Qwen (original model), finetuning by Abaryan
|
| 43 |
-
- **Funded by :** Abaryan
|
| 44 |
-
- **Shared by :** Abaryan
|
| 45 |
- **Model type:** Causal Language Model
|
| 46 |
- **Language(s) (NLP):** English
|
| 47 |
- **License:** MIT
|
|
@@ -65,7 +64,7 @@ You can load this model using the `transformers` library in Python:
|
|
| 65 |
```python
|
| 66 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 67 |
|
| 68 |
-
model_id = "
|
| 69 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 70 |
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype="auto")
|
| 71 |
|
|
|
|
| 40 |
The finetuning was performed using SFT following by Group Relative Policy Optimization (GRPO).
|
| 41 |
|
| 42 |
- **Developed by:** Qwen (original model), finetuning by Abaryan
|
| 43 |
+
- **Funded & Shared by :** Abaryan
|
|
|
|
| 44 |
- **Model type:** Causal Language Model
|
| 45 |
- **Language(s) (NLP):** English
|
| 46 |
- **License:** MIT
|
|
|
|
| 64 |
```python
|
| 65 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 66 |
|
| 67 |
+
model_id = "abaryan/BioXP-0.5B-MedMCQA"
|
| 68 |
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 69 |
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype="auto")
|
| 70 |
|