CreativeWorks commited on
Commit
9f06800
Β·
verified Β·
1 Parent(s): 97fa6a7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -13
README.md CHANGED
@@ -1,26 +1,65 @@
1
  ---
2
- base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
3
- language:
4
- - multilingual
 
 
5
  license: apache-2.0
6
  tags:
7
  - text-generation-inference
8
  - transformers
9
- - unsloth
 
 
10
  - llama
11
  - gguf
12
- - CreativeWorksAi
13
  - NeuraLake
14
  - 256k
 
 
15
  model_creator: Celso H A Diniz
 
16
  ---
17
 
18
- # CreativeWorks + NeuraLake
19
 
20
- - **Developed by:** CreativeWorksAi
21
- - **License:** apache-2.0
22
- - **Finetuned from model :** unsloth/llama-3.2-3b-instruct-bnb-4bit
23
- - **Introducing NeuraLake, the Artificial Intelligence and Advanced Projects division of CreativeWorks :** https://www.linkedin.com/company/neuralake-cloud
24
- - **The model was trained on synthetic data generated by the NeuraLake/Megalodon LLM, which is specifically designed for realistic simulations, reasoning and RAG :** https://www.neuralake.com.br/
25
-
26
- "CreativeWorks's Intelligence System for Advanced Dialogue and Organized Responses Assistance."
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: meta-llama/Llama-3.2-3B-Instruct
3
+ languages:
4
+ - en
5
+ - es
6
+ - pt
7
  license: apache-2.0
8
  tags:
9
  - text-generation-inference
10
  - transformers
11
+ - facebook
12
+ - meta
13
+ - pytorch
14
  - llama
15
  - gguf
16
+ - CreativeWorksAi
17
  - NeuraLake
18
  - 256k
19
+ - region:br
20
+ - πŸ‡§πŸ‡·
21
  model_creator: Celso H A Diniz
22
+ model_name: iSA-01-Mini-3B-GGUF
23
  ---
24
 
25
+ Note: This is our first public release on Hugging Face, and the Model Card is still a work in progress. Further improvements and updates will follow.
26
 
27
+ # CreativeWorksAi + NeuraLake: Designed by Earth's Creatives, Assembled by AI
28
+
29
+ ## Model Description
30
+ The **iSA-01-Mini-3B-GGUF** is a small yet advanced language model developed by CreativeWorksAi, designed to enhance text generation and reasoning capabilities. It extends the context window from 128K to 256K tokens, effectively doubling its information retention and significantly improving performance compared to its base model, **[meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)**.
31
+
32
+
33
+ ## Hardware Requirements Estimate
34
+
35
+ | Name | Quant method | Size | Memory (RAM, vRAM) required |
36
+ | ---- | ---- | ---- | ---- |
37
+ | [iSA-01-Mini-3B.F16.gguf](https://huggingface.co/CreativeWorksAi/iSA-01-Mini-3B-GGUF/blob/main/iSA-01-Mini-3B.F16.gguf) | F16 | 6.43 GB | 12.86 GB |
38
+ | [iSA-01-Mini-3B.Q4_K_M.gguf](https://huggingface.co/CreativeWorksAi/iSA-01-Mini-3B-GGUF/blob/main/iSA-01-Mini-3B.Q4_K_M.gguf) | Q4_K_M | 2.02 GB | 4.04 GB |
39
+ | [iSA-01-Mini-3B.Q5_K_M.gguf](https://huggingface.co/CreativeWorksAi/iSA-01-Mini-3B-GGUF/blob/main/iSA-01-Mini-3B.Q5_K_M.gguf) | Q5_K_M | 2.32 GB | 4.64 GB |
40
+
41
+ ## Evaluation (Coming Soon)
42
+
43
+
44
+ ## Key Features
45
+ - **Extended Context Window**: The model's context window has been expanded from 128K to 256K tokens, enabling it to retain more information for better reasoning and logical deductions.
46
+ - **Enhanced Reasoning**: The increased context size leads to superior performance in complex tasks like **Retrieval-Augmented Generation (RAG)**, resulting in more precise and context-aware outputs.
47
+ - **Improved Information Integration**: With a larger context window, the model integrates external information more effectively, producing accurate and contextually relevant responses.
48
+ - **Fine-tuned with NeuraLake/Megalodon**: The model was fine-tuned using synthetic data generated by the state-of-the-art **NeuraLake/Megalodon**, enhancing its ability to process and analyze complex scenarios.
49
+ - **NeuraLake/Megalodon Model**: This proprietary, closed-source LLM has been developed by NeuraLake over the past three years to enhance reasoning capabilities, especially for small models and agents.
50
+
51
+ ## Training Data
52
+ The **iSA-01-Mini-3B-GGUF** was trained using synthetic data generated by **NeuraLake/Megalodon**, focused on realistic scenarios to improve reasoning and performance in **RAG** tasks.
53
+
54
+
55
+ ## Model Details
56
+ - **Developed by**: CreativeWorksAi
57
+ - **License**: Apache License 2.0
58
+ - **Fine-tuned from**: [unsloth/llama-3.2-3b-instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit)
59
+ - **NeuraLake**: Learn more about NeuraLake and its advanced AI projects at [NeuraLake Cloud](https://www.linkedin.com/company/neuralake-cloud).
60
+ - **NeuraLake/Megalodon Model**: Discover more about the model used for synthetic data generation at [NeuraLake](https://www.neuralake.com.br/).
61
+ - **Model Card Contact**: Celso H A Diniz [LinkedIn profile](https://www.linkedin.com/in/celso-h-a-diniz).
62
+ ## Usage
63
+ CreativeWorksAi's **Intelligence System for Advanced Dialogue and Organized Responses Assistance (i.S.A.D.O.R.A. architecture)** is designed to offer users a sophisticated tool for generating coherent, contextually rich text, making it ideal for applications that require advanced natural language understanding and generation.
64
+
65
+ ## πŸ‡§πŸ‡·