refactor: Transformer更名为AutoRegressiveLM并新增EmbeddingEncoder

- AutoRegressiveLM 注册名改为 autoregressive_lm
- 新增 EmbeddingEncoder 支持 mean/cls/last pooling
- ModelConfig 增加 pooling_type / normalize_embeddings 字段
- 导入、注释、测试全部同步更新

tests/conftest.py

@@ -8,8 +8,8 @@ import torch
 from tokenizers import Tokenizer, models, pre_tokenizers, trainers
 from torch.utils.data import Dataset
 
-from astrai.config.model_config import ModelConfig
-from astrai.model.transformer import Transformer
+from astrai.config.model_config import AutoRegressiveLMConfig
+from astrai.model.transformer import AutoRegressiveLM
 from astrai.tokenize import AutoTokenizer
 
 
@@ -104,8 +104,8 @@ def test_tokenizer():
 
 @pytest.fixture(scope="session")
 def test_model():
-    """Session-scoped small Transformer model, created once."""
-    config = ModelConfig(
+    """Session-scoped small AutoRegressiveLM model, created once."""
+    config = AutoRegressiveLMConfig(
         vocab_size=1000,
         dim=8,
         n_heads=2,
@@ -116,7 +116,7 @@ def test_model():
         norm_eps=1e-5,
     )
     device = "cuda" if torch.cuda.is_available() else "cpu"
-    model = Transformer(config).to(device=device)
+    model = AutoRegressiveLM(config).to(device=device)
 
     return {
         "model": model,

tests/module/test_encoder.py

@@ -0,0 +1,166 @@
+import torch
+
+from astrai.config.model_config import EncoderConfig
+from astrai.model.encoder import EmbeddingEncoder
+
+TINY_CONFIG = dict(
+    vocab_size=128,
+    dim=8,
+    n_heads=2,
+    n_kv_heads=1,
+    dim_ffn=16,
+    max_len=64,
+    n_layers=2,
+    norm_eps=1e-5,
+)
+
+
+def test_encoder_forward_mean():
+    config = EncoderConfig(**TINY_CONFIG)
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = EmbeddingEncoder(config).to(device=device)
+    model.eval()
+
+    batch_size, seq_len = 2, 8
+    input_ids = torch.randint(
+        0, config.vocab_size, (batch_size, seq_len), device=device
+    )
+
+    with torch.no_grad():
+        output = model(input_ids)
+
+    assert output.shape == (batch_size, config.dim)
+    assert not torch.isnan(output).any()
+
+
+def test_encoder_forward_cls():
+    config = EncoderConfig(**{**TINY_CONFIG, "pooling_type": "cls"})
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = EmbeddingEncoder(config).to(device=device)
+    model.eval()
+
+    batch_size, seq_len = 2, 8
+    input_ids = torch.randint(
+        0, config.vocab_size, (batch_size, seq_len), device=device
+    )
+
+    with torch.no_grad():
+        output = model(input_ids)
+
+    assert output.shape == (batch_size, config.dim)
+    assert not torch.isnan(output).any()
+
+
+def test_encoder_forward_last():
+    config = EncoderConfig(**{**TINY_CONFIG, "pooling_type": "last"})
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = EmbeddingEncoder(config).to(device=device)
+    model.eval()
+
+    batch_size, seq_len = 2, 8
+    input_ids = torch.randint(
+        0, config.vocab_size, (batch_size, seq_len), device=device
+    )
+
+    with torch.no_grad():
+        output = model(input_ids)
+
+    assert output.shape == (batch_size, config.dim)
+    assert not torch.isnan(output).any()
+
+
+def test_encoder_forward_with_padding():
+    config = EncoderConfig(**TINY_CONFIG)
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = EmbeddingEncoder(config).to(device=device)
+    model.eval()
+
+    batch_size, seq_len = 2, 8
+    input_ids = torch.randint(
+        0, config.vocab_size, (batch_size, seq_len), device=device
+    )
+    input_mask = torch.ones(batch_size, seq_len, dtype=torch.bool, device=device)
+    input_mask[:, 4:] = False
+
+    with torch.no_grad():
+        output = model(input_ids, input_mask=input_mask)
+
+    assert output.shape == (batch_size, config.dim)
+    assert not torch.isnan(output).any()
+
+
+def test_encoder_normalize():
+    config = EncoderConfig(
+        **{**TINY_CONFIG, "pooling_type": "mean", "normalize_embeddings": True}
+    )
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = EmbeddingEncoder(config).to(device=device)
+    model.eval()
+
+    batch_size, seq_len = 2, 8
+    input_ids = torch.randint(
+        0, config.vocab_size, (batch_size, seq_len), device=device
+    )
+
+    with torch.no_grad():
+        output = model(input_ids)
+
+    norms = output.norm(p=2, dim=-1)
+    assert torch.allclose(norms, torch.ones_like(norms), atol=1e-4)
+
+
+def test_encoder_register():
+    from astrai.model.automodel import AutoModel
+
+    assert AutoModel.is_registered("embedding")
+    cls = AutoModel.get_component_class("embedding")
+    assert cls is EmbeddingEncoder
+
+
+def test_encoder_from_transformer_checkpoint():
+    config = EncoderConfig(**TINY_CONFIG)
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = EmbeddingEncoder(config).to(device=device)
+
+    state_dict = model.state_dict()
+    state_dict["lm_head.weight"] = torch.randn(
+        config.vocab_size, config.dim, device=device
+    )
+
+    new_model = EmbeddingEncoder(config).to(device=device)
+    new_model.load_state_dict(state_dict, strict=True)
+
+    for key in model.state_dict():
+        assert torch.equal(new_model.state_dict()[key], model.state_dict()[key])
+
+
+def test_encoder_save_load():
+    import json
+    import os
+    import tempfile
+
+    import safetensors.torch as st
+
+    test_dir = tempfile.mkdtemp(prefix="encoder_test_")
+    config_path = os.path.join(test_dir, "config.json")
+    weights_path = os.path.join(test_dir, "model.safetensors")
+
+    try:
+        config_data = {**TINY_CONFIG, "pooling_type": "mean"}
+        with open(config_path, "w") as f:
+            json.dump(config_data, f)
+
+        config = EncoderConfig.from_file(config_path)
+        original = EmbeddingEncoder(config)
+        st.save_file(original.state_dict(), weights_path)
+
+        loaded = EmbeddingEncoder(config)
+        loaded.load_state_dict(st.load_file(weights_path))
+
+        for key in original.state_dict():
+            assert torch.equal(original.state_dict()[key], loaded.state_dict()[key])
+    finally:
+        if os.path.exists(test_dir):
+            for f in os.listdir(test_dir):
+                os.remove(os.path.join(test_dir, f))
+            os.rmdir(test_dir)

tests/module/test_forward_configs.py

@@ -1,8 +1,8 @@
 import pytest
 import torch
 
-from astrai.config.model_config import ModelConfig
-from astrai.model.transformer import Transformer
+from astrai.config.model_config import AutoRegressiveLMConfig
+from astrai.model.transformer import AutoRegressiveLM
 
 TINY_CONFIG = dict(
     vocab_size=128,
@@ -66,9 +66,9 @@ CONFIGS = [
 
 @pytest.mark.parametrize("config_kwargs", CONFIGS)
 def test_model_forward(config_kwargs):
-    config = ModelConfig(**config_kwargs)
+    config = AutoRegressiveLMConfig(**config_kwargs)
     device = "cuda" if torch.cuda.is_available() else "cpu"
-    model = Transformer(config).to(device=device)
+    model = AutoRegressiveLM(config).to(device=device)
     model.eval()
 
     batch_size, seq_len = 2, 8
@@ -89,9 +89,9 @@ def test_model_forward(config_kwargs):
 
 @pytest.mark.parametrize("config_kwargs", CONFIGS)
 def test_model_forward_with_padding(config_kwargs):
-    config = ModelConfig(**config_kwargs)
+    config = AutoRegressiveLMConfig(**config_kwargs)
     device = "cuda" if torch.cuda.is_available() else "cpu"
-    model = Transformer(config).to(device=device)
+    model = AutoRegressiveLM(config).to(device=device)
     model.eval()
 
     batch_size, seq_len = 2, 8

tests/module/test_tie_weight.py

@@ -6,8 +6,8 @@ import pytest
 import safetensors.torch as st
 import torch
 
-from astrai.config.model_config import ModelConfig
-from astrai.model.transformer import Transformer
+from astrai.config.model_config import AutoRegressiveLMConfig
+from astrai.model.transformer import AutoRegressiveLM
 
 
 @pytest.fixture
@@ -50,8 +50,8 @@ def test_tie_weight_init(transformer_test_env):
     with open(config_path, "w") as f:
         json.dump(config_data, f)
 
-    config = ModelConfig.from_file(config_path)
-    model = Transformer(config)
+    config = AutoRegressiveLMConfig.from_file(config_path)
+    model = AutoRegressiveLM(config)
 
     assert torch.equal(model.lm_head.weight, model.embed_tokens.weight)
     assert model.lm_head.weight.data_ptr() == model.embed_tokens.weight.data_ptr()
@@ -68,8 +68,8 @@ def test_tie_weight_init(transformer_test_env):
     with open(config_path, "w") as f:
         json.dump(config_data, f)
 
-    config = ModelConfig.from_file(config_path)
-    model = Transformer(config)
+    config = AutoRegressiveLMConfig.from_file(config_path)
+    model = AutoRegressiveLM(config)
 
     assert not torch.equal(model.lm_head.weight, model.embed_tokens.weight)
     assert model.lm_head.weight.data_ptr() != model.embed_tokens.weight.data_ptr()
@@ -94,13 +94,13 @@ def test_model_save_load_with_tie_weight(transformer_test_env):
     with open(config_path, "w") as f:
         json.dump(config_data, f)
 
-    config = ModelConfig.from_file(config_path)
-    original_model = Transformer(config)
+    config = AutoRegressiveLMConfig.from_file(config_path)
+    original_model = AutoRegressiveLM(config)
 
     st.save_file(original_model.state_dict(), model_path)
 
-    loaded_config = ModelConfig.from_file(config_path)
-    model = Transformer(loaded_config)
+    loaded_config = AutoRegressiveLMConfig.from_file(config_path)
+    model = AutoRegressiveLM(loaded_config)
     model.load_state_dict(st.load_file(model_path))
 
     assert torch.equal(model.lm_head.weight, model.embed_tokens.weight)
@@ -112,8 +112,8 @@ def test_model_save_load_with_tie_weight(transformer_test_env):
     with open(config_path, "w") as f:
         json.dump(config_data, f)
 
-    loaded_config = ModelConfig.from_file(config_path)
-    model = Transformer(loaded_config)
+    loaded_config = AutoRegressiveLMConfig.from_file(config_path)
+    model = AutoRegressiveLM(loaded_config)
     model.load_state_dict(st.load_file(model_path))
 
     assert torch.equal(model.lm_head.weight, model.embed_tokens.weight)