File size: 2,640 Bytes
f661d13 dec316b f661d13 dec316b 9773714 dec316b 634047d dec316b 73887b1 2f47b1c 73887b1 4ac6942 73887b1 abcb321 73887b1 abcb321 4ac6942 abcb321 4ac6942 abcb321 4ac6942 abcb321 4ac6942 abcb321 eb34306 dec316b e1bff9e dec316b 30b566b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
---
license: mit
datasets:
- >-
CreitinGameplays/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B-filtered-mistral
language:
- en
base_model:
- mistralai/Mistral-Nemo-Instruct-2407
pipeline_tag: text-generation
library_name: transformers
---
## Mistral Nemo 12B R1
Took **12 hours** to finetune on **1x Nvidia H100** with the following settings:
- Batch size: 26
- Gradient accumulation steps: 1
- Epochs: 1
- Learning rate: 2e-5
- Warmup ratio: 0.1
Run the model:
```python
import torch
from transformers import pipeline
model_id = "CreitinGameplays/Mistral-Nemo-12B-R1-v0.2"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto"
)
messages = [
{"role": "system", "content": "You are a helpful AI assistant named Mistral Nemo."},
{"role": "user", "content": "How many r's are in strawberry?"}
]
outputs = pipe(
messages,
temperature=0.6,
top_p=0.95,
top_k=40,
repetition_penalty=1.1,
max_new_tokens=2048
)
print(outputs[0]["generated_text"][-1])
```
### Example response generated with this model:
- User prompt:
```
how many r's are in strawberry?
```
- Model output:
```
<think>
To determine the number of 'r's in the word "strawberry," I will start by breaking down the word into its component parts: "straw" and "berry."
Next, I will count the number of 'r's in each part. The word "straw" contains one 'r,' and the word "berry" contains two 'r's.
Finally, I will add the number of 'r's from both parts together, which gives me a total of three 'r's in the word "strawberry."
</think>
To determine the number of 'r's in the word "strawberry," let's break it down step by step:
1. **Break down the word:**
The word "strawberry" can be divided into two parts: "straw" and "berry."
2. **Count the 'r's in each part:**
- In "straw": There is **1** 'r'.
- In "berry": There are **2** 'r's.
3. **Add the 'r's together:**
\( 1 \text{ (from straw)} + 2 \text{ (from berry)} = 3 \)
Therefore, the word "strawberry" contains **3** 'r's.
\[
\boxed{3}
\]</s>
```
Recommended system prompt for activating reasoning step:
```
You are an AI focused on providing systematic, well-reasoned responses. Response Structure: - Format: <think>{reasoning}</think>{answer} - Reasoning: Minimum 6 logical steps only when it required in <think> block - Process: Think first, then answer.
```
**Note**: The model was mainly finetuned on English dataset, meaning the model may not perform well in other languages. |