rebased hymba multipack

This commit is contained in:
bursteratom
2024-12-11 14:52:05 -05:00
committed by Sunny Liu
parent 42bd32a233
commit cce7007bf8
8 changed files with 278 additions and 2 deletions

View File

@@ -25,6 +25,7 @@ SUPPORTED_MULTIPACK_MODEL_TYPES = [
"gemmoe",
"starcoder2",
"deepseek_v2",
"hymba",
]

View File

@@ -31,6 +31,7 @@ _CHAT_TEMPLATES = {
"qwen_25": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"exaone": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '[|system|][|endofturn|]\n' }}{% endif %}{{ '[|' + message['role'] + '|]' + message['content'] }}{% if message['role'] == 'user' %}{{ '\n' }}{% else %}{{ '[|endofturn|]\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '[|assistant|]' }}{% endif %}",
"metharme": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'Enter RP mode. You shall reply to the user while staying in character. Your responses must be detailed, creative, immersive, and drive the scenario forward.' %}{% endif %}{{ '<|system|>' + system_message }}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>' + content.strip() }}{% elif message['role'] == 'assistant' %}{{ '<|model|>' + content.strip() }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|model|>' }}{% else %}{{ eos_token }}{% endif %}",
"hymba": "{{'<extra_id_0>System'}}{% for message in messages %}{% if message['role'] == 'system' %}{{'\n' + message['content'].strip()}}{% if tools or contexts %}{{'\n'}}{% endif %}{% endif %}{% endfor %}{% if tools %}{% for tool in tools %}{{ '\n<tool> ' + tool|tojson + ' </tool>' }}{% endfor %}{% endif %}{% if contexts %}{% if tools %}{{'\n'}}{% endif %}{% for context in contexts %}{{ '\n<context> ' + context.strip() + ' </context>' }}{% endfor %}{% endif %}{{'\n\n'}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<extra_id_1>User\n' + message['content'].strip() + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<extra_id_1>Assistant\n' + message['content'].strip() + '\n' }}{% elif message['role'] == 'tool' %}{{ '<extra_id_1>Tool\n' + message['content'].strip() + '\n' }}{% endif %}{% endfor %}{%- if add_generation_prompt %}{{'<extra_id_1>Assistant\n'}}{%- endif %}",
}

View File

@@ -1627,3 +1627,19 @@ class AxolotlConfigWCapabilities(AxolotlInputConfig):
else:
data["torch_compile"] = False
return data
@model_validator(mode="before")
@classmethod
def check_hymba_torch_version(cls, data):
if "hymba" in data.get("base_model", {}).lower():
env_capabilities = data.get("env_capabilities", {})
torch_version = env_capabilities.get("torch_version")
if torch_version is None:
import torch
torch_version = str(torch.__version__).split("+", maxsplit=1)[0]
if version.parse(torch_version) < version.parse("2.5.0"):
raise ValueError("Hymba requires torch version >= 2.5")
return data

View File

@@ -409,6 +409,7 @@ class ModelLoader:
and self.cfg.sample_packing
):
if "auto_map" in self.model_config:
# some model config objects are not subscriptable
try:
auto_map_config = self.model_config["auto_map"]
except TypeError: