ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update template

Browse Source 
Former-commit-id: a95f3a4d62de1073a78125401cf4289ec0523156
This commit is contained in:
hiyouga
2023-08-22 19:46:09 +08:00
parent f55907dbea
commit 6310613699
6 changed files with 38 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/llmtuner/hparams/finetuning_args.py
View File

@@ -21,7 +21,8 @@ class FinetuningArguments:
Falcon choices: [\"32\", \"60\"], \
Baichuan choices: [\"32\", \"40\"] \
Qwen choices: [\"32\"], \
XVERSE choices: [\"40\"]"}
XVERSE choices: [\"40\"], \
ChatGLM2 choices: [\"28\"]"}
)
num_layer_trainable: Optional[int] = field(
default=3,
@@ -31,7 +32,7 @@ class FinetuningArguments:
default="mlp",
metadata={"help": "Name of trainable modules for partial-parameter (freeze) fine-tuning. \
LLaMA choices: [\"mlp\", \"self_attn\"], \
BLOOM & Falcon choices: [\"mlp\", \"self_attention\"], \
BLOOM & Falcon & ChatGLM2 choices: [\"mlp\", \"self_attention\"], \
Baichuan choices: [\"mlp\", \"self_attn\"], \
Qwen choices: [\"mlp\", \"attn\"], \
LLaMA-2, InternLM, XVERSE choices: the same as LLaMA."}
@@ -52,7 +53,7 @@ class FinetuningArguments:
default=None,
metadata={"help": "Name(s) of target modules to apply LoRA. Use commas to separate multiple modules. \
LLaMA choices: [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\", \"gate_proj\", \"up_proj\", \"down_proj\"], \
BLOOM & Falcon choices: [\"query_key_value\", \"self_attention.dense\", \"mlp.dense\"], \
BLOOM & Falcon & ChatGLM2 choices: [\"query_key_value\", \"self_attention.dense\", \"mlp.dense\"], \
Baichuan choices: [\"W_pack\", \"o_proj\", \"gate_proj\", \"up_proj\", \"down_proj\"], \
Qwen choices: [\"c_attn\", \"attn.c_proj\", \"w1\", \"w2\", \"mlp.c_proj\"], \
LLaMA-2, InternLM, XVERSE choices: the same as LLaMA."}