cmedina/agenx-lora-training
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: use Ornith-1.0-35B-FP8 with multi-GPU support

Browse Source
This commit is contained in:
Christian Medina
2026-06-30 15:57:54 -04:00
parent 215886d6a7
commit 2074d3d993
2 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
training/configs/llama2-7b-lora.yaml
View File

@@ -1,7 +1,7 @@
# LoRA Training Configuration for Llama-2-7b
# Dataset: cyron_summary_lora_dataset (20k examples)
base_model: meta-llama/Llama-2-7b-hf
base_model: deepreinforce-ai/Ornith-1.0-35B-FP8
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer