Upload 3 files

configuration_decilm.py

@@ -0,0 +1,46 @@
+from packaging import version
+import transformers
+if version.parse(transformers.__version__) < version.parse("4.31.0"):
+    raise ImportError(
+        f"You are using transformers=={transformers.__version__}, but transformers>=4.31.0 is required to use DeciLM. Please upgrade transformers."
+    )
+from transformers.models.llama.configuration_llama import LlamaConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+
+
+class DeciLMConfig(LlamaConfig):
+    r"""
+
+    Args:
+        num_key_value_heads_per_layer (`List[int]`):
+            The number of key-value heads per layer.
+        naive_attention_prefill (`bool`, *optional*, defaults to False):
+            Whether to use naive matmul or scaled dot product attention during prefill.
+        naive_attention_decode_batched (`bool`, *optional*, defaults to True):
+            Whether to use naive matmul or scaled dot product attention during decode for batch_size > 1.
+        naive_attention_decode_single (`bool`, *optional*, defaults to False):
+            Whether to use naive matmul or scaled dot product attention during decode for batch_size == 1.
+       
+
+       ```"""
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        num_key_value_heads_per_layer: list = None,
+        naive_attention_prefill: bool = False,
+        naive_attention_decode_batched: bool = False,
+        naive_attention_decode_single: bool = False,
+        **kwargs,
+    ):
+        self.num_key_value_heads_per_layer = num_key_value_heads_per_layer
+        self.naive_attention_prefill = naive_attention_prefill
+        self.naive_attention_decode_batched = naive_attention_decode_batched
+        self.naive_attention_decode_single = naive_attention_decode_single
+        super().__init__(**kwargs, )
+

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 11434205184
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

modeling_decilm.py

@@ -0,0 +1,253 @@
+# coding=utf-8
+# Copyright and license here
+""" PyTorch DeciLM model."""
+import math
+from typing import Optional, Tuple
+
+import torch
+import torch.nn.functional as F
+import torch.utils.checkpoint
+from torch import nn
+from packaging import version
+import transformers
+if version.parse(transformers.__version__) < version.parse("4.31.0"):
+    raise ImportError(
+        f"You are using transformers=={transformers.__version__}, but transformers>=4.31.0 is required to use DeciLM. Please upgrade transformers."
+    )
+from transformers.models.llama.modeling_llama import LlamaMLP, LlamaRMSNorm, LlamaAttention, apply_rotary_pos_emb, \
+    repeat_kv, LlamaPreTrainedModel, LLAMA_START_DOCSTRING, LlamaDecoderLayer, LlamaForCausalLM, LlamaModel
+from transformers.utils import add_start_docstrings
+
+from .configuration_decilm import DeciLMConfig
+
+_CONFIG_FOR_DOC = "DeciLMConfig"
+
+
+class DeciLMAttention(LlamaAttention):
+    """Multi-headed attention from 'Attention Is All You Need' paper"""
+
+    def __init__(self, config: DeciLMConfig, layer_idx: int):
+        nn.Module.__init__(self)
+        self.config = config
+        self.hidden_size = config.hidden_size
+        self.num_heads = config.num_attention_heads
+        self.head_dim = self.hidden_size // self.num_heads
+        self.layer_idx = layer_idx
+        self.num_key_value_heads = config.num_key_value_heads_per_layer[layer_idx]
+        self.num_key_value_groups = self.num_heads // self.num_key_value_heads
+        self.pretraining_tp = config.pretraining_tp
+        self.max_position_embeddings = config.max_position_embeddings
+        self.rope_theta = getattr(config, 'rope_theta', None)
+
+        if (self.head_dim * self.num_heads) != self.hidden_size:
+            raise ValueError(
+                f"hidden_size must be divisible by num_heads (got `hidden_size`: {self.hidden_size}"
+                f" and `num_heads`: {self.num_heads})."
+            )
+        self.q_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False)
+        self.k_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
+        self.v_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
+        self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=False)
+
+        self.naive_attention_prefill = config.naive_attention_prefill
+        self.naive_attention_decode_batched = config.naive_attention_decode_batched
+        self.naive_attention_decode_single = config.naive_attention_decode_single
+        self._init_rope()
+
+    def forward(
+            self,
+            hidden_states: torch.Tensor,
+            attention_mask: Optional[torch.Tensor] = None,
+            position_ids: Optional[torch.LongTensor] = None,
+            past_key_value: Optional[Tuple[torch.Tensor]] = None,
+            output_attentions: bool = False,
+            use_cache: bool = False,
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
+        bsz, q_len, _ = hidden_states.size()
+        if past_key_value is None:
+            is_decode = False
+        else:
+            is_decode = True
+        if self.pretraining_tp > 1:
+            key_value_slicing = (self.num_key_value_heads * self.head_dim) // self.pretraining_tp
+            query_slices = self.q_proj.weight.split((self.num_heads * self.head_dim) // self.pretraining_tp, dim=0)
+            key_slices = self.k_proj.weight.split(key_value_slicing, dim=0)
+            value_slices = self.v_proj.weight.split(key_value_slicing, dim=0)
+
+            query_states = [F.linear(hidden_states, query_slices[i]) for i in range(self.pretraining_tp)]
+            query_states = torch.cat(query_states, dim=-1)
+
+            key_states = [F.linear(hidden_states, key_slices[i]) for i in range(self.pretraining_tp)]
+            key_states = torch.cat(key_states, dim=-1)
+
+            value_states = [F.linear(hidden_states, value_slices[i]) for i in range(self.pretraining_tp)]
+            value_states = torch.cat(value_states, dim=-1)
+
+        else:
+            query_states = self.q_proj(hidden_states)
+            key_states = self.k_proj(hidden_states)
+            value_states = self.v_proj(hidden_states)
+
+        query_states = query_states.view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
+        key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
+        value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
+
+        kv_seq_len = key_states.shape[-2]
+        if past_key_value is not None:
+            kv_seq_len += past_key_value[0].shape[-2]
+        cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
+
+        query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)
+
+        if past_key_value is not None:
+            # reuse k, v, self_attention
+            key_states = torch.cat([past_key_value[0], key_states], dim=2)
+            value_states = torch.cat([past_key_value[1], value_states], dim=2)
+
+        past_key_value = (key_states, value_states) if use_cache else None
+
+        # repeat k/v heads if n_kv_heads < n_heads
+        key_states = repeat_kv(key_states, self.num_key_value_groups)
+        value_states = repeat_kv(value_states, self.num_key_value_groups)
+        if is_decode:
+            if self.naive_attention_decode_batched and bsz > 1 or self.naive_attention_decode_single and bsz == 1:
+                attn_weights = (query_states @ key_states.transpose(-2, -1)) / math.sqrt(key_states.size(-1))
+                attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query_states.dtype)
+                if attention_mask is not None:
+                    if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
+                        raise ValueError(
+                            f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
+                        )
+                    attn_weights = attn_weights + attention_mask
+
+                attn_output = torch.matmul(attn_weights, value_states)
+            else:
+                attn_output = F.scaled_dot_product_attention(query_states, key_states, value_states, is_causal=False,
+                                                             dropout_p=0.0)
+            attn_output = attn_output.contiguous().view(bsz, q_len, self.hidden_size)
+
+        else:
+            if not self.naive_attention_prefill:
+                with torch.backends.cuda.sdp_kernel(enable_math=True, enable_flash=False, enable_mem_efficient=False):
+                    attn_output = F.scaled_dot_product_attention(query_states, key_states, value_states, is_causal=True,
+                                                                 dropout_p=0.0)
+            else:
+                attn_weights = torch.matmul(query_states, key_states.transpose(2, 3)) / math.sqrt(self.head_dim)
+                if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len):
+                    raise ValueError(
+                        f"Attention weights should be of size {(bsz, self.num_heads, q_len, kv_seq_len)}, but is"
+                        f" {attn_weights.size()}"
+                    )
+
+                if attention_mask is not None:
+                    if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
+                        raise ValueError(
+                            f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
+                        )
+                    attn_weights = attn_weights + attention_mask
+
+                # upcast attention to fp32
+                attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query_states.dtype)
+                attn_output = torch.matmul(attn_weights, value_states)
+
+            if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim):
+                raise ValueError(
+                    f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is"
+                    f" {attn_output.size()}"
+                )
+
+            attn_output = attn_output.transpose(1, 2).contiguous().view(bsz, q_len, self.hidden_size)
+
+        if self.pretraining_tp > 1:
+            attn_output = attn_output.split(self.hidden_size // self.pretraining_tp, dim=2)
+            o_proj_slices = self.o_proj.weight.split(self.hidden_size // self.pretraining_tp, dim=1)
+            attn_output = sum([F.linear(attn_output[i], o_proj_slices[i]) for i in range(self.pretraining_tp)])
+        else:
+            attn_output = self.o_proj(attn_output)
+
+        if not output_attentions:
+            attn_weights = None
+
+        return attn_output, attn_weights, past_key_value
+
+
+class DeciLMDecoderLayer(LlamaDecoderLayer):
+    def __init__(self, config: DeciLMConfig, layer_idx: int):
+        nn.Module.__init__(self)
+        self.hidden_size = config.hidden_size
+        self.layer_idx = layer_idx
+        self.self_attn = DeciLMAttention(config=config, layer_idx=layer_idx)
+        self.mlp = LlamaMLP(config)
+        self.input_layernorm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.post_attention_layernorm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+
+
+@add_start_docstrings(
+    "The bare DeciLM Model outputting raw hidden-states without any specific head on top.",
+    LLAMA_START_DOCSTRING,
+)
+class DeciLMPreTrainedModel(LlamaPreTrainedModel):
+    config_class = DeciLMConfig
+    _no_split_modules = ["DeciLMDecoderLayer"]
+    _keys_to_ignore_on_load_missing = ["self_attn.rotary_emb.inv_freq"]
+
+
+@add_start_docstrings(
+    "The bare DeciLM Model outputting raw hidden-states without any specific head on top.",
+    LLAMA_START_DOCSTRING,
+)
+class DeciLMModel(LlamaModel, DeciLMPreTrainedModel):
+    """
+    Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`DeciLMDecoderLayer`]
+
+    Args:
+        config: DeciLMConfig
+    """
+
+    def __init__(self, config: DeciLMConfig):
+        DeciLMPreTrainedModel.__init__(self, config)
+        self.padding_idx = config.pad_token_id
+        self.vocab_size = config.vocab_size
+
+        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
+        self.layers = nn.ModuleList([DeciLMDecoderLayer(config, layer_idx) for layer_idx
+                                     in range(config.num_hidden_layers)])
+        self.norm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+
+        self.gradient_checkpointing = False
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    def _prepare_decoder_attention_mask(self, attention_mask, input_shape, inputs_embeds, past_key_values_length):
+        self._validate_config_supports_attention_mask(attention_mask, input_shape, past_key_values_length)
+        return LlamaModel._prepare_decoder_attention_mask(
+            self, attention_mask, input_shape, inputs_embeds, past_key_values_length)
+
+    def _validate_config_supports_attention_mask(self, attention_mask, input_shape, past_key_values_length):
+        is_decode = past_key_values_length > 0
+        if not torch.all(torch.eq(attention_mask, 1)).item():
+            if is_decode:
+                if input_shape[0] == 1 and not self.config.naive_attention_decode_single:
+                    raise ValueError(
+                        "For support of custom attention masks please set naive_attention_decode_single to True in the "
+                        "config")
+                elif input_shape[0] > 1 and not self.config.naive_attention_decode_batched:
+                    raise ValueError(
+                        "For support of custom attention masks please set naive_attention_decode_batched to True in the"
+                        "config")
+            else:
+                if not self.config.naive_attention_prefill:
+                    raise ValueError("For support of custom attention masks please set naive_attention_prefill to "
+                                     "True in the config")
+
+
+class DeciLMForCausalLM(LlamaForCausalLM, DeciLMPreTrainedModel):
+    def __init__(self, config):
+        DeciLMPreTrainedModel.__init__(self, config)
+        self.model = DeciLMModel(config)
+        self.pretraining_tp = config.pretraining_tp
+        self.vocab_size = config.vocab_size
+        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
+
+        # Initialize weights and apply final processing
+        self.post_init()