Commit 95d58c0d authored by zhuwenwen's avatar zhuwenwen
Browse files

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

parent 4ddb5447
...@@ -575,6 +575,11 @@ See [this page](#generative-models) for more information on how to use generativ ...@@ -575,6 +575,11 @@ See [this page](#generative-models) for more information on how to use generativ
* `xverse/XVERSE-7B-Chat`, `xverse/XVERSE-13B-Chat`, `xverse/XVERSE-65B-Chat`, etc. * `xverse/XVERSE-7B-Chat`, `xverse/XVERSE-13B-Chat`, `xverse/XVERSE-65B-Chat`, etc.
* ✅︎ * ✅︎
* ✅︎ * ✅︎
- * `MiniMaxM1ForCausalLM`
* MiniMax-Text
* `MiniMaxAI/MiniMax-M1-40k`, etc.
*
* ✅︎
- * `MiniMaxText01ForCausalLM` - * `MiniMaxText01ForCausalLM`
* MiniMax-Text * MiniMax-Text
* `MiniMaxAI/MiniMax-Text-01`, etc. * `MiniMaxAI/MiniMax-Text-01`, etc.
......
...@@ -209,6 +209,8 @@ _TEXT_GENERATION_EXAMPLE_MODELS = { ...@@ -209,6 +209,8 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
trust_remote_code=True), trust_remote_code=True),
"MiniMaxText01ForCausalLM": _HfExamplesInfo(os.path.join(models_path_prefix, "MiniMaxAI/MiniMax-Text-01"), "MiniMaxText01ForCausalLM": _HfExamplesInfo(os.path.join(models_path_prefix, "MiniMaxAI/MiniMax-Text-01"),
trust_remote_code=True), trust_remote_code=True),
"MiniMaxM1ForCausalLM": _HfExamplesInfo(os.path.join(models_path_prefix, "MiniMaxAI/MiniMax-M1-40k"),
trust_remote_code=True),
"MistralForCausalLM": _HfExamplesInfo(os.path.join(models_path_prefix, "mistralai/Mistral-7B-Instruct-v0.1")), "MistralForCausalLM": _HfExamplesInfo(os.path.join(models_path_prefix, "mistralai/Mistral-7B-Instruct-v0.1")),
"MixtralForCausalLM": _HfExamplesInfo(os.path.join(models_path_prefix, "mistralai/Mixtral-8x7B-Instruct-v0.1"), # noqa: E501 "MixtralForCausalLM": _HfExamplesInfo(os.path.join(models_path_prefix, "mistralai/Mixtral-8x7B-Instruct-v0.1"), # noqa: E501
{"tiny": os.path.join(models_path_prefix, "TitanML/tiny-mixtral")}), # noqa: E501 {"tiny": os.path.join(models_path_prefix, "TitanML/tiny-mixtral")}), # noqa: E501
......
...@@ -36,6 +36,7 @@ _TEXT_GENERATION_MODELS = { ...@@ -36,6 +36,7 @@ _TEXT_GENERATION_MODELS = {
"AquilaForCausalLM": ("llama", "LlamaForCausalLM"), # AquilaChat2 "AquilaForCausalLM": ("llama", "LlamaForCausalLM"), # AquilaChat2
"ArcticForCausalLM": ("arctic", "ArcticForCausalLM"), "ArcticForCausalLM": ("arctic", "ArcticForCausalLM"),
"MiniMaxText01ForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"), "MiniMaxText01ForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"),
"MiniMaxM1ForCausalLM": ("minimax_text_01", "MiniMaxText01ForCausalLM"),
# baichuan-7b, upper case 'C' in the class name # baichuan-7b, upper case 'C' in the class name
"BaiChuanForCausalLM": ("baichuan", "BaiChuanForCausalLM"), "BaiChuanForCausalLM": ("baichuan", "BaiChuanForCausalLM"),
# baichuan-13b, lower case 'c' in the class name # baichuan-13b, lower case 'c' in the class name
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment