38 lines
762 B
Markdown
38 lines
762 B
Markdown
|
---
|
||
|
|
license: mit
|
||
|
|
datasets:
|
||
|
|
- CreitinGameplays/r1_annotated_math-mistral
|
||
|
|
- CreitinGameplays/DeepSeek-R1-Distill-Qwen-32B_NUMINA_train_amc_aime-mistral
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
base_model:
|
||
|
|
- mistralai/Mistral-Nemo-Instruct-2407
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
library_name: transformers
|
||
|
|
---
|
||
|
|
|
||
|
|
Run the model:
|
||
|
|
```python
|
||
|
|
import torch
|
||
|
|
from transformers import pipeline
|
||
|
|
|
||
|
|
model_id = "CreitinGameplays/Mistral-Nemo-12B-R1-v0.1alpha"
|
||
|
|
pipe = pipeline(
|
||
|
|
"text-generation",
|
||
|
|
model=model_id,
|
||
|
|
torch_dtype=torch.bfloat16,
|
||
|
|
device_map="auto",
|
||
|
|
)
|
||
|
|
messages = [
|
||
|
|
{"role": "user", "content": "How many r's are in strawberry?"},
|
||
|
|
]
|
||
|
|
outputs = pipe(
|
||
|
|
messages,
|
||
|
|
temperature=0.8,
|
||
|
|
top_p=1.0,
|
||
|
|
top_k=50,
|
||
|
|
max_new_tokens=4096,
|
||
|
|
)
|
||
|
|
print(outputs[0]["generated_text"][-1])
|
||
|
|
|
||
|
|
```
|