LLM: improve transformers style API doc (#9113)

docs/readthedocs/source/doc/PythonAPI/LLM/optimize.rst

@@ -1,7 +1,7 @@
 BigDL-LLM PyTorch API
 =====================
 
-llm.optimize
+optimize model
 ----------------------------------------
 
 .. automodule:: bigdl.llm.optimize

docs/readthedocs/source/doc/PythonAPI/LLM/transformers.rst

@@ -1,10 +1,16 @@
-BigDL-LLM `transformers`-style API
-=====================
+BigDL-LLM ``transformers``-style API
+====================================
 
-llm.transformers.model
----------------------------
+Hugging Face ``transformers`` AutoModel
+------------------------------------
 
-.. autoclass:: bigdl.llm.transformers.model.AutoModelForCausalLM
+You can apply BigDL-LLM optimizations on any Hugging Face Transformers models by using the standard AutoModel APIs.
+
+
+AutoModelForCausalLM
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: bigdl.llm.transformers.AutoModelForCausalLM
     :members:
     :undoc-members:
     :show-inheritance:
@@ -13,8 +19,10 @@ llm.transformers.model
     .. automethod:: load_convert
     .. automethod:: load_low_bit
 
+AutoModel
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: bigdl.llm.transformers.model.AutoModel
+.. autoclass:: bigdl.llm.transformers.AutoModel
     :members:
     :undoc-members:
     :show-inheritance:
@@ -23,8 +31,10 @@ llm.transformers.model
     .. automethod:: load_convert
     .. automethod:: load_low_bit
 
+AutoModelForSpeechSeq2Seq
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: bigdl.llm.transformers.model.AutoModelForSpeechSeq2Seq
+.. autoclass:: bigdl.llm.transformers.AutoModelForSpeechSeq2Seq
     :members:
     :undoc-members:
     :show-inheritance:
@@ -33,8 +43,10 @@ llm.transformers.model
     .. automethod:: load_convert
     .. automethod:: load_low_bit
 
+AutoModelForSeq2SeqLM
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: bigdl.llm.transformers.model.AutoModelForSeq2SeqLM
+.. autoclass:: bigdl.llm.transformers.AutoModelForSeq2SeqLM
     :members:
     :undoc-members:
     :show-inheritance:
@@ -45,10 +57,17 @@ llm.transformers.model
 
 
 
-llm.transformers.modelling_bigdl
+Native Model
 ----------------------------------------
 
-.. autoclass:: bigdl.llm.transformers.modelling_bigdl.LlamaForCausalLM
+For ``llama``/``chatglm``/``bloom``/``gptneox``/``starcoder`` model families, you may also convert and run LLM using the native (cpp) implementation for maximum performance.
+
+
+.. tabs::
+
+    .. tab:: Llama
+
+        .. autoclass:: bigdl.llm.transformers.LlamaForCausalLM
             :members:
             :undoc-members:
             :show-inheritance:
@@ -56,8 +75,9 @@ llm.transformers.modelling_bigdl
 
             .. automethod:: from_pretrained
 
+    .. tab:: ChatGLM
 
-.. autoclass:: bigdl.llm.transformers.modelling_bigdl.ChatGLMForCausalLM
+        .. autoclass:: bigdl.llm.transformers.ChatGLMForCausalLM
             :members:
             :undoc-members:
             :show-inheritance:
@@ -65,8 +85,9 @@ llm.transformers.modelling_bigdl
 
             .. automethod:: from_pretrained
 
+    .. tab:: Gptneox
 
-.. autoclass:: bigdl.llm.transformers.modelling_bigdl.GptneoxForCausalLM
+        .. autoclass:: bigdl.llm.transformers.GptneoxForCausalLM
             :members:
             :undoc-members:
             :show-inheritance:
@@ -74,8 +95,8 @@ llm.transformers.modelling_bigdl
 
             .. automethod:: from_pretrained
 
-
-.. autoclass:: bigdl.llm.transformers.modelling_bigdl.BloomForCausalLM
+    .. tab:: Bloom
+        .. autoclass:: bigdl.llm.transformers.BloomForCausalLM
             :members:
             :undoc-members:
             :show-inheritance:
@@ -83,7 +104,9 @@ llm.transformers.modelling_bigdl
 
             .. automethod:: from_pretrained
 
-.. autoclass:: bigdl.llm.transformers.modelling_bigdl.StarcoderForCausalLM
+    .. tab:: Starcoder
+
+        .. autoclass:: bigdl.llm.transformers.StarcoderForCausalLM
             :members:
             :undoc-members:
             :show-inheritance:

python/llm/src/bigdl/llm/utils/lazy_load_torch.py

@@ -46,7 +46,7 @@ from torch.serialization import StorageType
 import pickle
 import zipfile
 import io
-from typing import Dict, IO, Any, Callable
+from typing import Dict, IO, Any, Callable, List
 from dataclasses import dataclass
 from .common import invalidInputError
 
@@ -69,7 +69,7 @@ class LazyStorage:
 @dataclass
 class LazyTensor:
     _load: Callable[[], torch.Tensor]
-    shape: list[int]
+    shape: List[int]
     data_type: torch.dtype
     description: str