Poolnoodle-LongNoodle
Poolnoodle-LongNoodle is a colleague model of Poolnoodle-BigNoodle, but with far less parameters. It has been trained on mostly the same datasets though. The difference between LongNoodle and BigNoodle is that LongNoodle supports more than 128K tokens in its context length.
With this large context length, Poolnoodle-LongNoodle's primary expertise is to read, process and summarize big chunks of text and data.
Poolnoodle-LongNoodlei is capable of extracting information from formatted text like HTML, markup and other structured text formats, as long as the source material is clear text.
The context length of Poolnoodle-LongNoodle can be extended even further via RoPE Scaling, although this comes at a huge expense of memory.
Model Faceplate
| Model name | Poolnoodle-LongNoodle |
| Family | Poolnoodle |
| Model Base UUID | 9aad7c4e-85b7-472d-a362-7528054435c5 |
| Parameters | Circa 13 billion |
| Origin | Llama 2 |
| License | LLama 2 license and ScaiLabs Model License |
| Context Length | 131072 |
| RoPE Scaling Supported | Yes, dynamic |
| Tokenizer | scaitoken-1 |
| Embeddings model | scailar-1 |
| Runtime compatibility | HF Transformers, FastChat |
Model Versions
| Version | Version String | Release date | UUID |
| 0.1 | poolnoodle-0.1-longnoodle | 2023-12-22 | fa1c2c2f-65be-4937-a58d-9c874a74a993 |
| 0.2 | poolnoodle-0.2-longnoodle | 2023-10-13 | 4954b497-87f0-4c0e-b29a-fb27bfcda8d1 |
No Comments