updata weight v20240321
d6d03ad
version: v20240321
- train 17B tokens with 256k context window
- recall of "Needle in A HayStack": 99.0%
version: v20240318
- train 12B tokens with 256k context window
- recall of "Needle in A HayStack": 97.5%
version: initial
- train 6B tokens with 256k context window
- recall of "Needle in A HayStack": 87.1%