初始化项目,由ModelHub XC社区提供模型

Model: mesolitica/llama-1b-hf-32768-fpf
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 14:54:06 +08:00
commit e9b6888a83
10 changed files with 162 additions and 0 deletions

12
README.md Normal file
View File

@@ -0,0 +1,12 @@
---
language:
- ms
---
# Full Parameter Finetuning 1B 32768 context length Llama2 on Malaysian text
1B derived from first 4 layers 7B model.
README at https://github.com/mesolitica/malaya/tree/5.1/session/llama2#1b-32768-context-length-flash-attention-2
WandB, https://wandb.ai/mesolitica/fpf-Llama-2-1b-32k-hf