Update model card
Browse files
README.md
CHANGED
|
@@ -2,7 +2,6 @@
|
|
| 2 |
license: llama3.1
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
-
pipeline_tag: text-classification
|
| 6 |
tags:
|
| 7 |
- reward-model
|
| 8 |
- RLHF
|
|
@@ -31,12 +30,6 @@ Binary-Think-RM addresses limitations of conventional reward models by incorpora
|
|
| 31 |
To evaluate the model, please use the following prompt template:
|
| 32 |
|
| 33 |
```python
|
| 34 |
-
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 35 |
-
|
| 36 |
-
model_name = "ilgee/Binary-Think-RM-8B"
|
| 37 |
-
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 38 |
-
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto")
|
| 39 |
-
|
| 40 |
system_msg = (
|
| 41 |
"You are an impartial judge, tasked with evaluating the quality of the two AI assistants' responses to the context displayed below. "
|
| 42 |
"Your evaluation should be based on the following six criteria:\n\n"
|
|
|
|
| 2 |
license: llama3.1
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
| 5 |
tags:
|
| 6 |
- reward-model
|
| 7 |
- RLHF
|
|
|
|
| 30 |
To evaluate the model, please use the following prompt template:
|
| 31 |
|
| 32 |
```python
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
system_msg = (
|
| 34 |
"You are an impartial judge, tasked with evaluating the quality of the two AI assistants' responses to the context displayed below. "
|
| 35 |
"Your evaluation should be based on the following six criteria:\n\n"
|