Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
|
| 2 |
language: - entags: - text-generation - conversational - code-generation - ai-assistantlicense: apache-2.0library_name: transformerspipeline_tag: text-generation
|
| 3 |
VIA-01 by Rapnss
|
|
@@ -44,20 +54,20 @@ Install required dependencies:
|
|
| 44 |
```bash
|
| 45 |
pip install transformers torch accelerate gradio
|
| 46 |
```
|
| 47 |
-
Performance
|
| 48 |
|
| 49 |
Inference Speed: Optimized for low-latency responses, typically ~20-40 seconds on standard CPU hardware (e.g., Hugging Face free Space). For sub-10-second responses, use a GPU-enabled environment (e.g., Hugging Face Pro Space).
|
| 50 |
Model Size: ~8GB, balanced for efficiency and performance.
|
| 51 |
Capabilities: Excels in conversational queries, technical problem-solving, and code generation tasks like writing functions or debugging snippets.
|
| 52 |
|
| 53 |
-
Try It Out
|
| 54 |
Interact with VIA-01 via our Hugging Face Space, featuring a Gradio interface for real-time testing.
|
| 55 |
Limitations
|
| 56 |
|
| 57 |
Response Length: Short responses (up to 15 tokens) recommended for optimal speed on free-tier hosting.
|
| 58 |
Hardware: CPU-based inference may be slower than GPU; performance varies with deployment setup.
|
| 59 |
|
| 60 |
-
License
|
| 61 |
Licensed under the Apache 2.0 License, enabling flexible use and redistribution.
|
| 62 |
Contact
|
| 63 |
Created by Rapnss. For inquiries or feedback, reach out via Hugging Face or the VIA-01 Space.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: question-answering
|
| 6 |
+
tags:
|
| 7 |
+
- VIA
|
| 8 |
+
- Rapnss
|
| 9 |
+
- Vidyut
|
| 10 |
+
---
|
| 11 |
|
| 12 |
language: - entags: - text-generation - conversational - code-generation - ai-assistantlicense: apache-2.0library_name: transformerspipeline_tag: text-generation
|
| 13 |
VIA-01 by Rapnss
|
|
|
|
| 54 |
```bash
|
| 55 |
pip install transformers torch accelerate gradio
|
| 56 |
```
|
| 57 |
+
# Performance
|
| 58 |
|
| 59 |
Inference Speed: Optimized for low-latency responses, typically ~20-40 seconds on standard CPU hardware (e.g., Hugging Face free Space). For sub-10-second responses, use a GPU-enabled environment (e.g., Hugging Face Pro Space).
|
| 60 |
Model Size: ~8GB, balanced for efficiency and performance.
|
| 61 |
Capabilities: Excels in conversational queries, technical problem-solving, and code generation tasks like writing functions or debugging snippets.
|
| 62 |
|
| 63 |
+
# Try It Out
|
| 64 |
Interact with VIA-01 via our Hugging Face Space, featuring a Gradio interface for real-time testing.
|
| 65 |
Limitations
|
| 66 |
|
| 67 |
Response Length: Short responses (up to 15 tokens) recommended for optimal speed on free-tier hosting.
|
| 68 |
Hardware: CPU-based inference may be slower than GPU; performance varies with deployment setup.
|
| 69 |
|
| 70 |
+
# License
|
| 71 |
Licensed under the Apache 2.0 License, enabling flexible use and redistribution.
|
| 72 |
Contact
|
| 73 |
Created by Rapnss. For inquiries or feedback, reach out via Hugging Face or the VIA-01 Space.
|