Triangle104
commited on
Commit
•
0eb3b0c
1
Parent(s):
35e49d6
Update README.md
Browse files
README.md
CHANGED
@@ -18,6 +18,95 @@ library_name: transformers
|
|
18 |
This model was converted to GGUF format from [`Spestly/Ava-1.5-12B`](https://huggingface.co/Spestly/Ava-1.5-12B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
19 |
Refer to the [original model card](https://huggingface.co/Spestly/Ava-1.5-12B) for more details on the model.
|
20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
## Use with llama.cpp
|
22 |
Install llama.cpp through brew (works on Mac and Linux)
|
23 |
|
|
|
18 |
This model was converted to GGUF format from [`Spestly/Ava-1.5-12B`](https://huggingface.co/Spestly/Ava-1.5-12B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
19 |
Refer to the [original model card](https://huggingface.co/Spestly/Ava-1.5-12B) for more details on the model.
|
20 |
|
21 |
+
---
|
22 |
+
Model details:
|
23 |
+
-
|
24 |
+
Ava 1.5
|
25 |
+
|
26 |
+
Ava 1.5 is a cutting-edge conversational AI model, fine-tuned from Ava 1.0 to deliver exceptional conversational capabilities. Designed to be your go-to AI for engaging, accurate, and context-aware dialogues, Ava 1.5 incorporates updated knowledge and enhanced natural language understanding to provide an unparalleled user experience.
|
27 |
+
|
28 |
+
Key Features
|
29 |
+
-
|
30 |
+
Enhanced Conversational Skills: Ava 1.5 demonstrates fluid and human-like dialogue generation with improved contextual understanding.
|
31 |
+
Updated Knowledge Base: Trained on the latest datasets, Ava 1.0 ensures responses are relevant and informed.
|
32 |
+
Multi-Turn Conversation: Handles complex, multi-turn interactions seamlessly, maintaining coherence and focus.
|
33 |
+
Personalized Assistance: Adapts responses based on user preferences and context.
|
34 |
+
Multilingual Support: Capable of understanding and responding in multiple languages with high accuracy.
|
35 |
+
|
36 |
+
Why Ava 1.5?
|
37 |
+
-
|
38 |
+
Ava 1.5 is built to excel in a wide range of applications:
|
39 |
+
|
40 |
+
Customer Support: Provides intelligent, empathetic, and accurate responses to customer queries.
|
41 |
+
Education: Acts as an interactive tutor, offering explanations and personalized guidance.
|
42 |
+
Personal Assistance: Supports daily tasks, scheduling, and answering general queries with ease.
|
43 |
+
Creative Collaboration: Assists with brainstorming, writing, and other creative processes.
|
44 |
+
|
45 |
+
Usage
|
46 |
+
-
|
47 |
+
Using Ava 1.5 in your project is straightforward. Here’s a quick setup guide:
|
48 |
+
|
49 |
+
Installation
|
50 |
+
-
|
51 |
+
Ensure you have the necessary libraries and dependencies installed. Use the following command:
|
52 |
+
|
53 |
+
pip install transformers
|
54 |
+
|
55 |
+
Implementation
|
56 |
+
-
|
57 |
+
Here’s a sample Python script to interact with Ava 1.5:
|
58 |
+
|
59 |
+
# Use a pipeline as a high-level helper
|
60 |
+
from transformers import pipeline
|
61 |
+
|
62 |
+
pipe = pipeline("text-generation", model="Spestly/Ava-1.5-12B")
|
63 |
+
|
64 |
+
# Load model directly
|
65 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
66 |
+
|
67 |
+
tokenizer = AutoTokenizer.from_pretrained("Spestly/Ava-1.5-12B")
|
68 |
+
model = AutoModelForCausalLM.from_pretrained("Spestly/Ava-1.5-12B")
|
69 |
+
|
70 |
+
Training Highlights
|
71 |
+
-
|
72 |
+
Ava 1.5 was fine-tuned with the following enhancements:
|
73 |
+
|
74 |
+
Extensive Conversational Dataset: Leveraging a wide array of open-domain and specialized conversational datasets.
|
75 |
+
Knowledge Integration: Incorporating recent advancements and updates to provide cutting-edge insights.
|
76 |
+
Fine-Tuning on Ava 1.0: Utilizing the powerful Ava 1.0 model to further refine and expand upon the model's ability to perform tasks!
|
77 |
+
|
78 |
+
Limitations
|
79 |
+
-
|
80 |
+
Contextual Challenges: In rare cases, Ava 1.0 may misinterpret ambiguous inputs.
|
81 |
+
Hardware Requirements: Optimal performance requires a robust system with GPU acceleration.
|
82 |
+
|
83 |
+
Roadmap
|
84 |
+
-
|
85 |
+
Ava 2.0: Introducing real-time learning capabilities and broader conversational adaptability.
|
86 |
+
Lightweight Model: Developing a lightweight version optimized for edge devices.
|
87 |
+
Domain-Specific Fine-Tunes: Specialized versions for industries like healthcare, education, and finance.
|
88 |
+
|
89 |
+
Contributing
|
90 |
+
-
|
91 |
+
We welcome contributions to enhance Ava! Here’s how you can get involved:
|
92 |
+
|
93 |
+
Fork this repository.
|
94 |
+
Create a feature branch.
|
95 |
+
Submit a pull request with detailed explanations of your changes.
|
96 |
+
|
97 |
+
License
|
98 |
+
-
|
99 |
+
Ava 1.5 is released under Apache 2.0 License. Please review the LICENSE file for more details.
|
100 |
+
|
101 |
+
Contact
|
102 |
+
-
|
103 |
+
For inquiries, feedback, or support, feel free to reach out:
|
104 |
+
|
105 |
+
Email: aayan.mishra@proton.me
|
106 |
+
GitHub: Spestly
|
107 |
+
Website: Ava Project Page
|
108 |
+
|
109 |
+
---
|
110 |
## Use with llama.cpp
|
111 |
Install llama.cpp through brew (works on Mac and Linux)
|
112 |
|