Update README.md
Browse files
README.md
CHANGED
|
@@ -10,12 +10,11 @@ tags:
|
|
| 10 |
Intellect-1 is a high-performance instruction-tuned model developed by Qwen, designed to handle a broad range of natural language processing tasks with efficiency and precision. Optimized for dialogue, reasoning, and knowledge-intensive applications, Intellect-1 excels in structured generation, summarization, and retrieval-augmented tasks. It is part of an open ecosystem, providing transparency in training data, model architecture, and fine-tuning methodologies.
|
| 11 |
|
| 12 |
|
| 13 |
-
|
| 14 |
## Variants
|
| 15 |
|
| 16 |
| No | Variant | Cortex CLI command |
|
| 17 |
| --- | --- | --- |
|
| 18 |
-
| 1 | [
|
| 19 |
|
| 20 |
## Use it with Jan (UI)
|
| 21 |
|
|
@@ -36,6 +35,6 @@ Intellect-1 is a high-performance instruction-tuned model developed by Qwen, des
|
|
| 36 |
## Credits
|
| 37 |
|
| 38 |
- **Author:** Qwen
|
| 39 |
-
- **Converter:** [Homebrew]
|
| 40 |
-
- **Original License:** [Licence]
|
| 41 |
-
- **Papers:** [Paper]
|
|
|
|
| 10 |
Intellect-1 is a high-performance instruction-tuned model developed by Qwen, designed to handle a broad range of natural language processing tasks with efficiency and precision. Optimized for dialogue, reasoning, and knowledge-intensive applications, Intellect-1 excels in structured generation, summarization, and retrieval-augmented tasks. It is part of an open ecosystem, providing transparency in training data, model architecture, and fine-tuning methodologies.
|
| 11 |
|
| 12 |
|
|
|
|
| 13 |
## Variants
|
| 14 |
|
| 15 |
| No | Variant | Cortex CLI command |
|
| 16 |
| --- | --- | --- |
|
| 17 |
+
| 1 | [Intellect-1-10b](https://huggingface.co/cortexso/intellect-1/tree/10b) | `cortex run intellect-1:10b` |
|
| 18 |
|
| 19 |
## Use it with Jan (UI)
|
| 20 |
|
|
|
|
| 35 |
## Credits
|
| 36 |
|
| 37 |
- **Author:** Qwen
|
| 38 |
+
- **Converter:** [Homebrew](https://homebrew.ltd/)
|
| 39 |
+
- **Original License:** [Licence](https://choosealicense.com/licenses/apache-2.0/)
|
| 40 |
+
- **Papers:** [Technical Paper](https://github.com/PrimeIntellect-ai/prime)
|