Update conversation.py

conversation.py

@@ -1,10 +1,14 @@
 import dataclasses
 from enum import auto, Enum
 from typing import List, Tuple
+import base64
+from io import BytesIO
+from PIL import Image
 
 VOCAB_IMAGE_W = 1000  # 224
 VOCAB_IMAGE_H = 1000  # 224
 
+
 class SeparatorStyle(Enum):
     """Different separator style."""
     SINGLE = auto()
@@ -12,6 +16,7 @@ class SeparatorStyle(Enum):
     MPT = auto()
     PLAIN = auto()
     LLAMA_2 = auto()
+    GEMMA = auto()
 
 
 @dataclasses.dataclass
@@ -27,8 +32,6 @@ class Conversation:
     version: str = "Unknown"
 
     skip_next: bool = False
-    first_round: bool = True
-
 
     def get_prompt(self):
         messages = self.messages
@@ -72,7 +75,7 @@ class Conversation:
                 else:
                     ret += role
         elif self.sep_style == SeparatorStyle.LLAMA_2:
-            wrap_sys = lambda msg: f"<<SYS>>\n{msg}\n<</SYS>>\n\n"
+            wrap_sys = lambda msg: f"<<SYS>>\n{msg}\n<</SYS>>\n\n" if len(msg) > 0 else msg
             wrap_inst = lambda msg: f"[INST] {msg} [/INST]"
             ret = ""
 
@@ -92,6 +95,16 @@ class Conversation:
                 else:
                     ret += ""
             ret = ret.lstrip(self.sep)
+        elif self.sep_style == SeparatorStyle.GEMMA:
+            seps = [self.sep, self.sep2]
+            ret = self.system + seps[0]
+            for i, (role, message) in enumerate(messages):
+                if message:
+                    if type(message) is tuple:
+                        message, _, _ = message
+                    ret += "<start_of_turn>" + role + "\n" + message + "<end_of_turn>\n" + seps[i % 2]
+                else:
+                    ret += "<start_of_turn>" + role + "\n"
         elif self.sep_style == SeparatorStyle.PLAIN:
             seps = [self.sep, self.sep2]
             ret = self.system
@@ -133,7 +146,7 @@ class Conversation:
                                 result.paste(pil_img, ((height - width) // 2, 0))
                                 return result
                         image = expand2square(image)
-                    elif image_process_mode == "Crop":
+                    elif image_process_mode in ["Default", "Crop"]:
                         pass
                     elif image_process_mode == "Raw+Processor":
                         pass
@@ -230,15 +243,123 @@ class Conversation:
         }
 
 
+conv_vicuna_v0 = Conversation(
+    system="A chat between a curious human and an artificial intelligence assistant. "
+           "The assistant gives helpful, detailed, and polite answers to the human's questions.",
+    roles=("Human", "Assistant"),
+    messages=(
+        ("Human", "What are the key differences between renewable and non-renewable energy sources?"),
+        ("Assistant",
+            "Renewable energy sources are those that can be replenished naturally in a relatively "
+            "short amount of time, such as solar, wind, hydro, geothermal, and biomass. "
+            "Non-renewable energy sources, on the other hand, are finite and will eventually be "
+            "depleted, such as coal, oil, and natural gas. Here are some key differences between "
+            "renewable and non-renewable energy sources:\n"
+            "1. Availability: Renewable energy sources are virtually inexhaustible, while non-renewable "
+            "energy sources are finite and will eventually run out.\n"
+            "2. Environmental impact: Renewable energy sources have a much lower environmental impact "
+            "than non-renewable sources, which can lead to air and water pollution, greenhouse gas emissions, "
+            "and other negative effects.\n"
+            "3. Cost: Renewable energy sources can be more expensive to initially set up, but they typically "
+            "have lower operational costs than non-renewable sources.\n"
+            "4. Reliability: Renewable energy sources are often more reliable and can be used in more remote "
+            "locations than non-renewable sources.\n"
+            "5. Flexibility: Renewable energy sources are often more flexible and can be adapted to different "
+            "situations and needs, while non-renewable sources are more rigid and inflexible.\n"
+            "6. Sustainability: Renewable energy sources are more sustainable over the long term, while "
+            "non-renewable sources are not, and their depletion can lead to economic and social instability.\n")
+    ),
+    offset=2,
+    sep_style=SeparatorStyle.SINGLE,
+    sep="###",
+)
+
+conv_vicuna_v1 = Conversation(
+    system="A chat between a curious user and an artificial intelligence assistant. "
+    "The assistant gives helpful, detailed, and polite answers to the user's questions.",
+    roles=("USER", "ASSISTANT"),
+    version="v1",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.TWO,
+    sep=" ",
+    sep2="</s>",
+)
+
+conv_llama_2 = Conversation(
+    system="""You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
+
+If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.""",
+    roles=("USER", "ASSISTANT"),
+    version="llama_v2",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.LLAMA_2,
+    sep="<s>",
+    sep2="</s>",
+)
+
+conv_llava_llama_2 = Conversation(
+    system="You are a helpful language and vision assistant. "
+           "You are able to understand the visual content that the user provides, "
+           "and assist the user with a variety of tasks using natural language.",
+    roles=("USER", "ASSISTANT"),
+    version="llama_v2",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.LLAMA_2,
+    sep="<s>",
+    sep2="</s>",
+)
+
+conv_mpt = Conversation(
+    system="""<|im_start|>system
+A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""",
+    roles=("<|im_start|>user\n", "<|im_start|>assistant\n"),
+    version="mpt",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.MPT,
+    sep="<|im_end|>",
+)
+
+conv_llava_plain = Conversation(
+    system="",
+    roles=("", ""),
+    messages=(
+    ),
+    offset=0,
+    sep_style=SeparatorStyle.PLAIN,
+    sep="\n",
+)
+
+conv_llava_v0 = Conversation(
+    system="A chat between a curious human and an artificial intelligence assistant. "
+           "The assistant gives helpful, detailed, and polite answers to the human's questions.",
+    roles=("Human", "Assistant"),
+    messages=(
+    ),
+    offset=0,
+    sep_style=SeparatorStyle.SINGLE,
+    sep="###",
+)
+
+conv_llava_v0_mmtag = Conversation(
+    system="A chat between a curious user and an artificial intelligence assistant. "
+           "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language."
+           "The visual content will be provided with the following format: <Image>visual content</Image>.",
+    roles=("Human", "Assistant"),
+    messages=(
+    ),
+    offset=0,
+    sep_style=SeparatorStyle.SINGLE,
+    sep="###",
+    version="v0_mmtag",
+)
 
-ferret_conv_vicuna_v1_original_system = Conversation(
+conv_llava_v1 = Conversation(
     system="A chat between a curious human and an artificial intelligence assistant. "
-           "Assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language. "
-           "In images, points are represented by coordinates [x, y]. The top-left corner is [0, 0]. The bottom-right corner is [width-1, height-1]. "
-           "Increasing x moves right across the image while increasing y moves down. "
-           "A bounding box is marked by [x1, y1, x2, y2] with the top-left and bottom-right points being [x1, y1] and [x2, y2] respectively. "
-           f"The image size is assumed to be ({VOCAB_IMAGE_W}, {VOCAB_IMAGE_H}), i.e., width={VOCAB_IMAGE_W}, height={VOCAB_IMAGE_H}. "
-           "Follow the instructions carefully. ",
+           "The assistant gives helpful, detailed, and polite answers to the human's questions.",
     roles=("USER", "ASSISTANT"),
     version="v1",
     messages=(),
@@ -248,12 +369,68 @@ ferret_conv_vicuna_v1_original_system = Conversation(
     sep2="</s>",
 )
 
-ferret_conv_vicuna_v1 = Conversation(
+conv_llava_v1_mmtag = Conversation(
+    system="A chat between a curious user and an artificial intelligence assistant. "
+           "The assistant is able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language."
+           "The visual content will be provided with the following format: <Image>visual content</Image>.",
+    roles=("USER", "ASSISTANT"),
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.TWO,
+    sep=" ",
+    sep2="</s>",
+    version="v1_mmtag",
+)
+
+conv_mistral_instruct = Conversation(
+    system="",
+    roles=("USER", "ASSISTANT"),
+    version="llama_v2",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.LLAMA_2,
+    sep="",
+    sep2="</s>",
+)
+
+conv_chatml_direct = Conversation(
+    system="""<|im_start|>system
+Answer the questions.""",
+    roles=("<|im_start|>user\n", "<|im_start|>assistant\n"),
+    version="mpt",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.MPT,
+    sep="<|im_end|>",
+)
+
+conv_llava_llama_3 = Conversation(
+    system="<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.",
+    roles=("<|start_header_id|>user<|end_header_id|>\n\n",
+           "<|start_header_id|>assistant<|end_header_id|>\n\n"),
+    version="llama3",
+    messages=[],
+    offset=0,
+    sep_style=SeparatorStyle.MPT,
+    sep="<|eot_id|>",
+)
+
+conv_ferret_llama_plain = Conversation(
+    system="",
+    roles=("", ""),
+    messages=(
+    ),
+    offset=0,
+    sep_style=SeparatorStyle.PLAIN,
+    sep="\n",
+)
+
+conv_ferret_vicuna_v1 = Conversation(
     system="A chat between a human and an AI that understands visuals. "
            "In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. "
            "Increasing x moves right; y moves down. "
            f"Bounding box: [x1, y1, x2, y2]. Image size: {VOCAB_IMAGE_W}x{VOCAB_IMAGE_H}. "
-           "Follow instructions. ",
+           "Follow instructions.",
     roles=("USER", "ASSISTANT"),
     version="v1",
     messages=(),
@@ -263,11 +440,85 @@ ferret_conv_vicuna_v1 = Conversation(
     sep2="</s>",
 )
 
+conv_ferret_llama_3 = Conversation(
+    system="<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nA chat between a human and an AI that understands visuals. "
+            "In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. "
+            "Increasing x moves right; y moves down. "
+            f"Bounding box: [x1, y1, x2, y2]. Image size: {VOCAB_IMAGE_W}x{VOCAB_IMAGE_H}. "
+            "Follow instructions.",
+    roles=("<|start_header_id|>user<|end_header_id|>\n\n",
+           "<|start_header_id|>assistant<|end_header_id|>\n\n"),
+    version="llama3",
+    messages=[],
+    offset=0,
+    sep_style=SeparatorStyle.MPT,
+    sep="<|eot_id|>",
+)
+
+conv_ferret_gemma_plain = Conversation(
+    system="",
+    roles=("user", "model"),
+    version="gemma",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.GEMMA,
+    sep="",
+    sep2="<eos>",
+)
 
-default_conversation = ferret_conv_vicuna_v1
+conv_ferret_gemma_instruct = Conversation(
+    system="A chat between a human and an AI that understands visuals. "
+           "In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. "
+           "Increasing x moves right; y moves down. "
+           f"Bounding box: [x1, y1, x2, y2]. Image size: {VOCAB_IMAGE_W}x{VOCAB_IMAGE_H}. "
+           "Follow instructions.",
+    roles=("user", "model"),
+    version="gemma",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.GEMMA,
+    sep="",
+    sep2="<eos>",
+)
+
+conv_ferret_phi3_instruct = Conversation(
+    system="""<|system|>\nYou are a helpful AI assistant.""",
+    roles=("\n<|user|>\n", "\n<|assistant|>\n"),
+    version="phi3",
+    messages=(),
+    offset=0,
+    sep_style=SeparatorStyle.MPT,
+    sep="<|end|>",
+)
+
+default_conversation = conv_vicuna_v1
 conv_templates = {
-    "v1": ferret_conv_vicuna_v1,
-    "ferret_v1": ferret_conv_vicuna_v1,
+    "default": conv_vicuna_v0,
+    "v0": conv_vicuna_v0,
+    "v1": conv_vicuna_v1,
+    "vicuna_v1": conv_vicuna_v1,
+    "llama_2": conv_llama_2,
+    "mistral_instruct": conv_mistral_instruct,
+    "chatml_direct": conv_chatml_direct,
+    "mistral_direct": conv_chatml_direct,
+
+    "plain": conv_llava_plain,
+    "v0_plain": conv_llava_plain,
+    "llava_v0": conv_llava_v0,
+    "v0_mmtag": conv_llava_v0_mmtag,
+    "llava_v1": conv_llava_v1,
+    "v1_mmtag": conv_llava_v1_mmtag,
+    "llava_llama_2": conv_llava_llama_2,
+    "llava_llama_3": conv_llava_llama_3,
+
+    "ferret_llama_plain": conv_ferret_llama_plain,
+    "ferret_vicuna_v1": conv_ferret_vicuna_v1,
+    "ferret_llama_3": conv_ferret_llama_3,
+    "ferret_gemma_plain": conv_ferret_gemma_plain,
+    "ferret_gemma_instruct": conv_ferret_gemma_instruct,
+    "ferret_phi3_instruct": conv_ferret_phi3_instruct,
+
+    "mpt": conv_mpt,
 }