[Model] Add support for MiniMaxM1ForCausalLM (shares architecture with MiniMaxText01ForCausalLM) (#19677)

Signed-off-by: QscQ <qscqesze@gmail.com>
This commit is contained in:
qscqesze
2025-06-17 00:47:14 +08:00
committed by GitHub
parent 5e5baa91aa
commit 387bdf0ab9
3 changed files with 4 additions and 0 deletions

View File

@ -370,6 +370,7 @@ Specified using `--task generate`.
| `TeleChat2ForCausalLM` | TeleChat2 | `Tele-AI/TeleChat2-3B`, `Tele-AI/TeleChat2-7B`, `Tele-AI/TeleChat2-35B`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `TeleFLMForCausalLM` | TeleFLM | `CofeAI/FLM-2-52B-Instruct-2407`, `CofeAI/Tele-FLM`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `XverseForCausalLM` | XVERSE | `xverse/XVERSE-7B-Chat`, `xverse/XVERSE-13B-Chat`, `xverse/XVERSE-65B-Chat`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `MiniMaxM1ForCausalLM` | MiniMax-Text | `MiniMaxAI/MiniMax-M1-40k`, `MiniMaxAI/MiniMax-M1-80k`etc. | | | |
| `MiniMaxText01ForCausalLM` | MiniMax-Text | `MiniMaxAI/MiniMax-Text-01`, etc. | | | |
| `Zamba2ForCausalLM` | Zamba2 | `Zyphra/Zamba2-7B-instruct`, `Zyphra/Zamba2-2.7B-instruct`, `Zyphra/Zamba2-1.2B-instruct`, etc. | | | |

View File

@ -205,6 +205,8 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
trust_remote_code=True),
"MiniMaxText01ForCausalLM": _HfExamplesInfo("MiniMaxAI/MiniMax-Text-01",
trust_remote_code=True),
"MiniMaxM1ForCausalLM": _HfExamplesInfo("MiniMaxAI/MiniMax-M1-40k",
trust_remote_code=True),
"MistralForCausalLM": _HfExamplesInfo("mistralai/Mistral-7B-Instruct-v0.1"),
"MixtralForCausalLM": _HfExamplesInfo("mistralai/Mixtral-8x7B-Instruct-v0.1", # noqa: E501
{"tiny": "TitanML/tiny-mixtral"}), # noqa: E501

View File

@ -36,6 +36,7 @@ _TEXT_GENERATION_MODELS = {
"AquilaForCausalLM": ("llama", "LlamaForCausalLM"), # AquilaChat2
"ArcticForCausalLM": ("arctic", "ArcticForCausalLM"),
"MiniMaxText01ForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"),
"MiniMaxM1ForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"),
# baichuan-7b, upper case 'C' in the class name
"BaiChuanForCausalLM": ("baichuan", "BaiChuanForCausalLM"),
# baichuan-13b, lower case 'c' in the class name