Hugging Face's logo

prithivMLmods
/
Llama-Deepsync-1B

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Llama
Code
CoT
Math
Deepsync
3b
conversational
Model card Files
xet
 Community
prithivMLmods commited on
Commit
6be2ec7
·
verified ·
1 Parent(s): cdfaeb6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -1
README.md CHANGED
@@ -1,5 +1,20 @@
1
  ---
2
  license: creativeml-openrail-m
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
4
  <pre align="center">
5
  .___ _______.
@@ -8,4 +23,80 @@ license: creativeml-openrail-m
8
  / /_/ \ ___/\ ___/| |_> >___ \ \___ | | \ \___ | || \_\ \
9
  \____ |\___ >\___ > __/____ >/ ____|___| /\___ > |___||___ /
10
  \/ \/ \/|__| \/ \/ \/ \/ \/
11
- </pre>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: creativeml-openrail-m
3
+ language:
4
+ - en
5
+ - de
6
+ - fr
7
+ - it
8
+ - pt
9
+ - hi
10
+ - es
11
+ - th
12
+ base_model:
13
+ - meta-llama/Llama-3.2-1B-Instruct
14
+ pipeline_tag: text-generation
15
+ tags:
16
+ - text-generation-inference
17
+ library_name: transformers
18
  ---
19
  <pre align="center">
20
  .___ _______.
 
23
  / /_/ \ ___/\ ___/| |_> >___ \ \___ | | \ \___ | || \_\ \
24
  \____ |\___ >\___ > __/____ >/ ____|___| /\___ > |___||___ /
25
  \/ \/ \/|__| \/ \/ \/ \/ \/
26
+ </pre>
27
+
28
+ The **Llama-Deepsync-1B** is a fine-tuned version of the **Llama-3.2-1B-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, **Llama-Deepsync-1B** 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
+ # **Model Architecture**
38
+
39
+ Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
40
+
41
+ # **Use with transformers**
42
+
43
+ Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.
44
+
45
+ Make sure to update your transformers installation via `pip install --upgrade transformers`.
46
+
47
+ ```python
48
+ import torch
49
+ from transformers import pipeline
50
+
51
+ model_id = "prithivMLmods/Llama-Deepsync-1B"
52
+ pipe = pipeline(
53
+ "text-generation",
54
+ model=model_id,
55
+ torch_dtype=torch.bfloat16,
56
+ device_map="auto",
57
+ )
58
+ messages = [
59
+ {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
60
+ {"role": "user", "content": "Who are you?"},
61
+ ]
62
+ outputs = pipe(
63
+ messages,
64
+ max_new_tokens=256,
65
+ )
66
+ print(outputs[0]["generated_text"][-1])
67
+ ```
68
+
69
+ Note: You can also find detailed recipes on how to use the model locally, with `torch.compile()`, assisted generations, quantised and more at [`huggingface-llama-recipes`](https://github.com/huggingface/huggingface-llama-recipes)
70
+
71
+ # **Run with Ollama [Ollama Run]**
72
+
73
+ Ollama makes running machine learning models simple and efficient. Follow these steps to set up and run your GGUF models quickly.
74
+
75
+ ## Quick Start: Step-by-Step Guide
76
+
77
+ | Step | Description | Command / Instructions |
78
+ |------|-------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------|
79
+ | 1 | **Install Ollama 🦙** | Download Ollama from [https://ollama.com/download](https://ollama.com/download) and install it on your system. |
80
+ | 2 | **Create Your Model File** | - Create a file named after your model, e.g., `metallama`. |
81
+ | | | - Add the following line to specify the base model: |
82
+ | | | ```bash |
83
+ | | | FROM Llama-3.2-1B.F16.gguf |
84
+ | | | ``` |
85
+ | | | - Ensure the base model file is in the same directory. |
86
+ | 3 | **Create and Patch the Model** | Run the following commands to create and verify your model: |
87
+ | | | ```bash |
88
+ | | | ollama create metallama -f ./metallama |
89
+ | | | ollama list |
90
+ | | | ``` |
91
+ | 4 | **Run the Model** | Use the following command to start your model: |
92
+ | | | ```bash |
93
+ | | | ollama run metallama |
94
+ | | | ``` |
95
+ | 5 | **Interact with the Model** | Once the model is running, interact with it: |
96
+ | | | ```plaintext |
97
+ | | | >>> Tell me about Space X. |
98
+ | | | Space X, the private aerospace company founded by Elon Musk, is revolutionizing space exploration... |
99
+ | | | ``` |
100
+
101
+ ## Conclusion
102
+ With Ollama, running and interacting with models is seamless. Start experimenting today!