DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1-GGUF

Original Model : https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1

---

This is a version of the <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B">DeepSeek-R1-Distill-Qwen-1.5B</a> model re-distilled for better performance.

Performance

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
compute_dtype = torch.bfloat16
device   = 'cuda'
model_id = "mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1"

model     = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=compute_dtype, attn_implementation="sdpa", device_map=device)
tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt  = "What is 1.5+102.2?"
chat    = tokenizer.apply_chat_template([{"role":"user", "content":prompt}], tokenize=True, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(chat.to(device), max_new_tokens=1024, do_sample=True) 
print(tokenizer.decode(outputs[0]))

Output:

<｜begin▁of▁sentence｜><｜User｜>What is 1.5+102.2?<｜Assistant｜><think>
First, I identify the numbers involved in the addition: 1.5 and 102.2.

Next, I add the whole numbers: 1 + 102 equals 103.

Then, I add the decimal parts: 0.5 + 0.2 equals 0.7.

Finally, I combine the results: 103 + 0.7 equals 103.7.
</think>

To solve the addition \(1.5 + 102.2\), follow these steps:

1. **Add the whole numbers:**
   \[
   1 + 102 = 103
   \]

2. **Add the decimal parts:**
   \[
   0.5 + 0.2 = 0.7
   \]

3. **Combine the results:**
   \[
   103 + 0.7 = 103.7
   \]

So, the final answer is \(\boxed{103.7}\).<｜end▁of▁sentence｜>

---