Merge 9cb07dd1ec into e41bf7cacf

[fix] float16 下 attention mask 的 -1e9 溢出成 -inf，导致整条序列输出 NaN

model/model_minimind.py

@@ -125,10 +125,14 @@ class Attention(nn.Module):
         if self.flash and (seq_len > 1) and (not self.is_causal or past_key_value is None) and (attention_mask is None or torch.all(attention_mask == 1)):
             output = F.scaled_dot_product_attention(xq, xk, xv, dropout_p=self.dropout if self.training else 0.0, is_causal=self.is_causal)
         else:
-            scores = (xq @ xk.transpose(-2, -1)) / math.sqrt(self.head_dim)
+            # 先转 float32 再加 mask：-1e9 超出 float16 的表示范围（min≈-65504），
+            # 在 float16 张量上累加会饱和成 -inf。若某个 query 在因果范围内可见的
+            # key 全被 mask 掉（左 padding 时必然出现），softmax 整行就是 NaN，
+            # 并在下一层通过 K/V 投影扩散到同序列里有效的 token 上。
+            scores = (xq @ xk.transpose(-2, -1)).float() / math.sqrt(self.head_dim)
             if self.is_causal: scores[:, :, :, -seq_len:] += torch.full((seq_len, seq_len), float("-inf"), device=scores.device).triu(1)
             if attention_mask is not None: scores += (1.0 - attention_mask.unsqueeze(1).unsqueeze(2)) * -1e9
-            output = self.attn_dropout(F.softmax(scores.float(), dim=-1).type_as(xq)) @ xv
+            output = self.attn_dropout(F.softmax(scores, dim=-1).type_as(xq)) @ xv
         output = output.transpose(1, 2).reshape(bsz, seq_len, -1)
         output = self.resid_dropout(self.o_proj(output))
         return output, past_kv

requirements.txt

@@ -28,6 +28,8 @@ streamlit==1.50.0
 einops==0.8.1
 swanlab==0.9.8
 modelscope==1.37.0
+fastapi==0.120.1
+uvicorn==0.38.0
 # torch==2.6.0
 # torchvision==0.21.0
 # peft==0.7.1

scripts/serve_openai_api.py

@@ -202,7 +202,7 @@ async def chat_completions(request: ChatRequest):
             with torch.no_grad():
                 generated_ids = model.generate(
                     inputs["input_ids"],
-                    max_length=inputs["input_ids"].shape[1] + request.max_tokens,
+                    max_new_tokens=request.max_tokens,
                     do_sample=True,
                     attention_mask=inputs["attention_mask"],
                     pad_token_id=tokenizer.pad_token_id,

trainer/train_full_sft.py

@@ -137,7 +137,7 @@ if __name__ == "__main__":
     train_ds = SFTDataset(args.data_path, tokenizer, max_length=args.max_seq_len)
     train_sampler = DistributedSampler(train_ds) if dist.is_initialized() else None
     scaler = torch.cuda.amp.GradScaler(enabled=(args.dtype == 'float16'))
-    optimizer = optim.AdamW(model.parameters(), lr=args.learning_rate)
+    optimizer = optim.AdamW(model.parameters(), lr=args.learning_rate, fused=('cuda' in args.device))
     
     # ========== 6. 从ckp恢复状态 ==========
     start_epoch, start_step = 0, 0

trainer/train_pretrain.py

@@ -136,7 +136,7 @@ if __name__ == "__main__":
     train_ds = PretrainDataset(args.data_path, tokenizer, max_length=args.max_seq_len)
     train_sampler = DistributedSampler(train_ds) if dist.is_initialized() else None
     scaler = torch.cuda.amp.GradScaler(enabled=(args.dtype == 'float16'))
-    optimizer = optim.AdamW(model.parameters(), lr=args.learning_rate)
+    optimizer = optim.AdamW(model.parameters(), lr=args.learning_rate, fused=(device_type == 'cuda'))
     
     # ========== 6. 从ckp恢复状态 ==========
     start_epoch, start_step = 0, 0

trainer/train_tokenizer.py

@@ -8,18 +8,39 @@ DATA_PATH = '../dataset/sft_t2t_mini.jsonl'
 TOKENIZER_DIR = '../model_learn_tokenizer/'
 VOCAB_SIZE = 6400
 SPECIAL_TOKENS_NUM = 36
+MAX_LINES = 0  # 0 表示读取全部；设为正数则只取前 N 条（快速试跑）
 
-def get_texts(data_path):
+def get_texts(data_path, max_lines=MAX_LINES):
+    """逐行产出用于训练 BPE 的文本，兼容两种主线数据格式。
+
+    pretrain_t2t(_mini).jsonl 是 {"text": ...}，
+    sft_t2t(_mini).jsonl 是 {"conversations": [{"role":..., "content":...}, ...]}。
+    原先只解析 conversations，所以把 DATA_PATH 指向预训练语料时一条文本都取不到，
+    BPE 仅基于 initial_alphabet 训练，产出一个没有任何 merge 的词表，且全程不报错。
+    """
+    used = 0
     with open(data_path, 'r', encoding='utf-8', errors='ignore') as f:
-        for i, line in enumerate(f):
-            if i >= 10000: break # 选10000行测试
+        for line in f:
+            if max_lines and used >= max_lines:
+                break
             try:
                 data = json.loads(line)
-                contents = [item.get('content') for item in data.get('conversations', []) if item.get('content')]
-                if contents:
-                    yield "\n".join(contents)
             except json.JSONDecodeError:
                 continue
+            if 'text' in data:
+                text = str(data['text'])
+            else:
+                contents = [item.get('content') for item in data.get('conversations', []) if item.get('content')]
+                text = "\n".join(contents) if contents else ''
+            if text.strip():
+                used += 1
+                yield text
+    if used == 0:
+        raise ValueError(
+            f'{data_path} 中没有可用文本：每行应为 {{"text": ...}} 或 '
+            f'{{"conversations": [{{"role":..., "content":...}}, ...]}}。'
+            f'继续训练只会得到一个空词表。'
+        )
 
 def train_tokenizer(data_path, tokenizer_dir, vocab_size, special_tokens_num=SPECIAL_TOKENS_NUM):
     tokenizer = Tokenizer(models.BPE())