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

support Yi 1.5

Browse Source 
Former-commit-id: e580823676cbb83ddb9a0f685992e6054ae5ffaa
This commit is contained in:
hiyouga
2024-05-13 16:51:20 +08:00
parent 1e1b8899f5
commit b1c791fb0d
4 changed files with 38 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
src/llmtuner/extras/constants.py
View File

@@ -320,14 +320,14 @@ register_model_group(
DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-base",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-base",
},
"DeepSeek-MoE-236B-Base": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2",
},
"DeepSeek-MoE-16B-Chat": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat",
},
"DeepSeek-MoE-236B": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2",
},
"DeepSeek-MoE-236B-Chat": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2-Chat",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2-Chat",
@@ -424,13 +424,13 @@ register_model_group(
register_model_group(
models={
"CodeGemma-2B": {
DownloadSource.DEFAULT: "google/codegemma-2b",
DownloadSource.DEFAULT: "google/codegemma-1.1-2b",
},
"CodeGemma-7B": {
DownloadSource.DEFAULT: "google/codegemma-7b",
},
"CodeGemma-7B-Chat": {
DownloadSource.DEFAULT: "google/codegemma-7b-it",
DownloadSource.DEFAULT: "google/codegemma-1.1-7b-it",
DownloadSource.MODELSCOPE: "AI-ModelScope/codegemma-7b-it",
},
},
@@ -581,6 +581,9 @@ register_model_group(
DownloadSource.DEFAULT: "shenzhi-wang/Llama3-8B-Chinese-Chat",
DownloadSource.MODELSCOPE: "LLM-Research/Llama3-8B-Chinese-Chat",
},
"LLaMA3-70B-Chinese-Chat": {
DownloadSource.DEFAULT: "shenzhi-wang/Llama3-70B-Chinese-Chat",
},
},
template="llama3",
)
@@ -1174,6 +1177,30 @@ register_model_group(
DownloadSource.DEFAULT: "01-ai/Yi-34B-Chat-4bits",
DownloadSource.MODELSCOPE: "01ai/Yi-34B-Chat-4bits",
},
"Yi-1.5-6B": {
DownloadSource.DEFAULT: "01-ai/Yi-1.5-6B",
DownloadSource.MODELSCOPE: "01ai/Yi-1.5-6B",
},
"Yi-1.5-9B": {
DownloadSource.DEFAULT: "01-ai/Yi-1.5-9B",
DownloadSource.MODELSCOPE: "01ai/Yi-1.5-9B",
},
"Yi-1.5-34B": {
DownloadSource.DEFAULT: "01-ai/Yi-1.5-34B",
DownloadSource.MODELSCOPE: "01ai/Yi-1.5-34B",
},
"Yi-1.5-6B-Chat": {
DownloadSource.DEFAULT: "01-ai/Yi-1.5-6B-Chat",
DownloadSource.MODELSCOPE: "01ai/Yi-1.5-6B-Chat",
},
"Yi-1.5-9B-Chat": {
DownloadSource.DEFAULT: "01-ai/Yi-1.5-9B-Chat",
DownloadSource.MODELSCOPE: "01ai/Yi-1.5-9B-Chat",
},
"Yi-1.5-34B-Chat": {
DownloadSource.DEFAULT: "01-ai/Yi-1.5-34B-Chat",
DownloadSource.MODELSCOPE: "01ai/Yi-1.5-34B-Chat",
},
},
template="yi",
)

2
src/llmtuner/model/utils/longlora.py
View File

@@ -302,7 +302,7 @@ def llama_sdpa_attention_forward(
def _apply_llama_patch() -> None:
require_version("transformers==4.40.1", "To fix: pip install transformers==4.40.1")
require_version("transformers==4.40.2", "To fix: pip install transformers==4.40.2")
LlamaAttention.forward = llama_attention_forward
LlamaFlashAttention2.forward = llama_flash_attention_2_forward
LlamaSdpaAttention.forward = llama_sdpa_attention_forward