Hugging Face's logo

prithivMLmods
/
Deepthink-Reasoning-Adapter

Text Generation
PEFT
Safetensors
English
text-generation-inference
code-solve
algorithm
codepy
qwen_base
7b
LoRA
CoT
conversational
Model card Files Community
prithivMLmods commited on
Commit
e826f82
·
verified ·
1 Parent(s): 10a4925

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +90 -1
README.md CHANGED
@@ -14,4 +14,93 @@ tags:
14
  - 7b
15
  - LoRA
16
  library_name: peft
17
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  - 7b
15
  - LoRA
16
  library_name: peft
17
+ ---
18
+
19
+ <pre align="center">
20
+ .___ __ .__ .__ __
21
+ __| _/ ____ ____ ______ _/ |_ | |__ |__| ____ | | __
22
+ / __ | _/ __ \ _/ __ \ \____ \ \ __\| | \ | | / \ | |/ /
23
+ / /_/ | \ ___/ \ ___/ | |_> > | | | Y \| || | \| <
24
+ \____ | \___ > \___ >| __/ |__| |___| /|__||___| /|__|_ \
25
+ \/ \/ \/ |__| \/ \/ \/
26
+ </pre>
27
+
28
+ The **Deepthink-Reasoning-Adapter** is a fine-tuned version of the **Qwen2.5-7B-Instruct** base model, designed for text generation tasks that require deep reasoning, logical structuring, and problem-solving. This model leverages its optimized architecture to provide accurate and contextually relevant outputs for complex queries, making it ideal for applications in education, programming, and creative writing.
29
+
30
+ With its robust natural language processing capabilities, **Deepthink-Reasoning-Adapter** excels in generating step-by-step solutions, creative content, and logical analyses. Its architecture integrates advanced understanding of both structured and unstructured data, ensuring precise text generation aligned with user inputs.
31
+
32
+ - Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.
33
+ - Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.
34
+ - **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
35
+ - **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
36
+
37
+ # **Demo Start**
38
+
39
+ Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
40
+
41
+ ```python
42
+ from transformers import AutoModelForCausalLM, AutoTokenizer
43
+
44
+ model_name = "prithivMLmods/Deepthink-Reasoning-7B"
45
+
46
+ model = AutoModelForCausalLM.from_pretrained(
47
+ model_name,
48
+ torch_dtype="auto",
49
+ device_map="auto"
50
+ )
51
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
52
+
53
+ prompt = "Give me a short introduction to large language model."
54
+ messages = [
55
+ {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
56
+ {"role": "user", "content": prompt}
57
+ ]
58
+ text = tokenizer.apply_chat_template(
59
+ messages,
60
+ tokenize=False,
61
+ add_generation_prompt=True
62
+ )
63
+ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
64
+
65
+ generated_ids = model.generate(
66
+ **model_inputs,
67
+ max_new_tokens=512
68
+ )
69
+ generated_ids = [
70
+ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
71
+ ]
72
+
73
+ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
74
+ ```
75
+ # **Run with Ollama [Ollama Run]**
76
+
77
+ Ollama makes running machine learning models simple and efficient. Follow these steps to set up and run your GGUF models quickly.
78
+
79
+ ## Quick Start: Step-by-Step Guide
80
+
81
+ | Step | Description | Command / Instructions |
82
+ |------|-------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------|
83
+ | 1 | **Install Ollama 🦙** | Download Ollama from [https://ollama.com/download](https://ollama.com/download) and install it on your system. |
84
+ | 2 | **Create Your Model File** | - Create a file named after your model, e.g., `metallama`. |
85
+ | | | - Add the following line to specify the base model: |
86
+ | | | ```bash |
87
+ | | | FROM Llama-3.2-1B.F16.gguf |
88
+ | | | ``` |
89
+ | | | - Ensure the base model file is in the same directory. |
90
+ | 3 | **Create and Patch the Model** | Run the following commands to create and verify your model: |
91
+ | | | ```bash |
92
+ | | | ollama create metallama -f ./metallama |
93
+ | | | ollama list |
94
+ | | | ``` |
95
+ | 4 | **Run the Model** | Use the following command to start your model: |
96
+ | | | ```bash |
97
+ | | | ollama run metallama |
98
+ | | | ``` |
99
+ | 5 | **Interact with the Model** | Once the model is running, interact with it: |
100
+ | | | ```plaintext |
101
+ | | | >>> Tell me about Space X. |
102
+ | | | Space X, the private aerospace company founded by Elon Musk, is revolutionizing space exploration... |
103
+ | | | ``` |
104
+
105
+ ## Conclusion
106
+ With Ollama, running and interacting with models is seamless. Start experimenting today!