dill-dev commited on
Commit
cd2f342
·
verified ·
1 Parent(s): 9f1eb09

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +73 -5
README.md CHANGED
@@ -1,11 +1,79 @@
 
1
  ---
2
  language: en
3
  license: apache-2.0
 
 
4
  tags:
5
- - vision
6
- - gguf
7
- - multimodal
 
 
 
 
8
  pipeline_tag: image-text-to-text
 
 
 
 
9
  ---
10
- # 🎨 NanoDream-7B (LLaVA 1.5 7B GGUF)
11
- Optimized GGUF version of LLaVA 1.5 7B.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
  ---
3
  language: en
4
  license: apache-2.0
5
+ model_name: NanoDream-7B (GGUF)
6
+ base_model: llava-hf/llava-1.5-7b-hf
7
  tags:
8
+ - vision
9
+ - gguf
10
+ - multimodal
11
+ - image-to-text
12
+ - q4_k_m
13
+ - quantized
14
+ - nano-dream
15
  pipeline_tag: image-text-to-text
16
+ library_name: gguf
17
+ inference: false
18
+ model_creator: dill-dev
19
+ quantized_by: dill-dev
20
  ---
21
+
22
+ # 🎨 NanoDream-7B (GGUF)
23
+
24
+ NanoDream-7B is a high-performance, next-generation multimodal model optimized for efficiency, speed, and advanced image reasoning. This model brings professional-grade Vision-Language capabilities to consumer-grade hardware, laptops, and mobile devices using the GGUF format.
25
+
26
+ ## 🚀 Key Highlights
27
+
28
+ - **Optimized Architecture**: Fine-tuned for high-speed multi-modal reasoning.
29
+ - **Quantization**: Q4_K_M (The industry standard for balancing quality and performance).
30
+ - **Low Resource Usage**: Runs comfortably on devices with 8GB RAM or less.
31
+ - **Unified Interface**: Perfect for real-time image description, object detection, and visual QA.
32
+
33
+ ## 🛠️ Quantization Details
34
+
35
+ This model was quantized using llama.cpp to provide a seamless experience on local hardware.
36
+
37
+ - **Method**: Q4_K_M (4-bit quantization with medium-sized K-quants)
38
+ - **Format**: GGUF (Compatible with llama.cpp, LM Studio, and more)
39
+ - **Model Size**: Approx. 4.08 GB
40
+
41
+ ## 💻 How to Use
42
+
43
+ ### 1. Using llama.cpp (Command Line)
44
+
45
+ To interact with NanoDream-7B via terminal, use the following command:
46
+
47
+ ```bash
48
+ ./llama-cli \
49
+ -m NanoDream-7B-Q4_K_M.gguf \
50
+ --mmproj NanoDream-7B-mmproj-f16.gguf \
51
+ --image input_sample.jpg \
52
+ -p "Describe this image accurately."
53
+ ````
54
+
55
+ ### 2. Prompt Template
56
+
57
+ For best results, use the standard interaction format:
58
+
59
+ ```
60
+ USER: <image>\n<prompt>\nASSISTANT:
61
+ ```
62
+
63
+ ## 📊 Hardware Requirements
64
+
65
+ | Resource | Minimum | Recommended |
66
+ | ---------- | ------- | ----------- |
67
+ | System RAM | 6 GB | 8 GB+ |
68
+ | VRAM (GPU) | 4 GB | 6 GB+ |
69
+ | Disk Space | 4.5 GB | 5 GB |
70
+
71
+ ## 🛡️ Disclaimer
72
+
73
+ NanoDream-7B is a powerful tool for visual understanding. However, users should verify critical information generated by the model. It is not intended for use in high-risk medical, legal, or safety-critical applications.
74
+
75
+ ---
76
+
77
+ **Maintained and Published by:** dill-dev
78
+
79
+