Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: bigcode-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: bigcode-openrail-m
|
| 3 |
+
datasets:
|
| 4 |
+
- tiiuae/falcon-refinedweb
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
---
|
| 8 |
+
This a ~90m assistant model for cameloid models like LLama/Alpaca/Vicuna/Guanaco that use the llama tokenizer, allowing for speedups up to 3x with greed sampling. Its trained on 5.5 billion tokens of refinedweb and uses the GPTBigcode architecture and has a context window: 1024. To use please see this article on assisted generation https://huggingface.co/blog/assisted-generation.
|