README.md

---
license: cc-by-nc-sa-4.0
language:
- en
- zh
base_model: Krystalan/DRT-o1-7B
tags:
- machine tranlsation
- O1-like model
- Chat
- llama-cpp
- gguf-my-repo
pipeline_tag: text-generation
---

# Triangle104/DRT-o1-7B-Q4_K_S-GGUF
This model was converted to GGUF format from [`Krystalan/DRT-o1-7B`](https://huggingface.co/Krystalan/DRT-o1-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Krystalan/DRT-o1-7B) for more details on the model.

---
Model details:
-
This repository contains the resources for our paper "DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought"

Updates:
2024.12.24: We released our paper. Check it out!
2024.12.23: We released our model checkpoints. 🤗 DRT-o1-7B and 🤗 DRT-o1-14B.
Introduction
In this work, we introduce DRT-o1, an attempt to bring the success of long thought reasoning to neural machine translation (MT). To this end,

🌟 We mine English sentences with similes or metaphors from existing literature books, which are suitable for translation via long thought.
🌟 We propose a designed multi-agent framework with three agents (i.e., a translator, an advisor and an evaluator) to synthesize the MT samples with long thought. There are 22,264 synthesized samples in total.
🌟 We train DRT-o1-7B and DRT-o1-14B using Qwen2.5-7B-Instruct and Qwen2.5-14B-Instruct as backbones.
Quickstart
⛷️ Huggingface Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Krystalan/DRT-o1-7B"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Please translate the following text from English to Chinese:\nThe mother, with her feet propped up on a stool, seemed to be trying to get to the bottom of that answer, whose feminine profundity had struck her all of a heap."
messages = [
    {"role": "system", "content": "You are a philosopher skilled in deep thinking, accustomed to exploring complex problems with profound insight."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=2048
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

⛷️ vllm
Deploying LLMs:

python3 -m vllm.entrypoints.openai.api_server --model [model_ckpt] --served-model-name [model_name]

Calling LLMs:

from openai import OpenAI
# Set OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

chat_response = client.chat.completions.create(
    model=[model_name],
    messages=[
        {"role": "system", "content": "You are a philosopher skilled in deep thinking, accustomed to exploring complex problems with profound insight."},
        {"role": "user", "content": "Please translate the following text from English to Chinese:\nThe mother, with her feet propped up on a stool, seemed to be trying to get to the bottom of that answer, whose feminine profundity had struck her all of a heap."},
    ],
    temperature=0.7,
    top_p=0.8,
    max_tokens=2048,
    extra_body={
        "repetition_penalty": 1.05,
    },
)
print("Chat response:", chat_response)

License
This work is licensed under cc-by-nc-sa-4.0

---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo Triangle104/DRT-o1-7B-Q4_K_S-GGUF --hf-file drt-o1-7b-q4_k_s.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Triangle104/DRT-o1-7B-Q4_K_S-GGUF --hf-file drt-o1-7b-q4_k_s.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```

Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/DRT-o1-7B-Q4_K_S-GGUF --hf-file drt-o1-7b-q4_k_s.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo Triangle104/DRT-o1-7B-Q4_K_S-GGUF --hf-file drt-o1-7b-q4_k_s.gguf -c 2048
```