feat: add lfm2 family and latest moe model (#3208)
* feat: add lfm2 family and latest moe model * fix: use ml-cross-entropy for lfm2 examples
This commit is contained in:
@@ -14,4 +14,5 @@ MOE_ARCH_BLOCK = {
|
||||
"qwen3_moe": "Qwen3MoeSparseMoeBlock",
|
||||
"deepseek_v2": "DeepseekV2MoE",
|
||||
"gpt_oss": "GptOssDecoderLayer",
|
||||
"lfm2_moe": "Lfm2MoeSparseMoeBlock",
|
||||
}
|
||||
|
||||
@@ -19,7 +19,7 @@ python scripts/cutcrossentropy_install.py | sh
|
||||
|
||||
- If you are installing from pip
|
||||
```bash
|
||||
pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@147ea28"
|
||||
pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@49f3308"
|
||||
```
|
||||
|
||||
## Usage
|
||||
@@ -54,9 +54,13 @@ plugins:
|
||||
- granitemoehybrid
|
||||
- hunyuan_v1_dense
|
||||
- hunyuan_v1_moe
|
||||
- lfm2
|
||||
- lfm2_moe
|
||||
- lfm2_vl
|
||||
- llama
|
||||
- llama4
|
||||
- llama4_text
|
||||
- llava
|
||||
- mistral
|
||||
- mistral3
|
||||
- mixtral
|
||||
|
||||
@@ -35,7 +35,7 @@ LOG = get_logger(__name__)
|
||||
|
||||
_CCE_INSTALL_MESSAGE = (
|
||||
"Please install Axolotl's fork of cut_cross_entropy with transformers support using "
|
||||
'`pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@147ea28"`'
|
||||
'`pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@49f3308"`'
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -45,6 +45,8 @@ SUPPORTED_MULTIPACK_MODEL_TYPES = [
|
||||
"gpt_oss",
|
||||
"arcee",
|
||||
"seed_oss",
|
||||
"lfm2",
|
||||
"lfm2_moe",
|
||||
]
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user