iomgaa/Minimind
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update some config

Browse Source
This commit is contained in:
gongjy 2024-09-15 15:12:47 +08:00
parent aa5d70321f
commit 16928c1231
5 changed files with 7 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
chat_openai_api.py
View File

@ -2,7 +2,7 @@ from openai import OpenAI
client = OpenAI( client = OpenAI(
api_key="none", api_key="none",
base_url="http://202.195.167.142:8000/v1" base_url="http://202.195.167.206:8000/v1"
) )
# 初始化对话历史列表 # 初始化对话历史列表

8
fast_infenence.py
View File

@ -4,8 +4,8 @@ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig from transformers.generation.utils import GenerationConfig
st.set_page_config(page_title="MiniMind-V1 Demo(无历史上文)") st.set_page_config(page_title="MiniMind-V1 108M(无历史上文)")
st.title("MiniMind-V1 Demo(无历史上文)") st.title("MiniMind-V1 108M(无历史上文)")
model_id = "minimind-v1" model_id = "minimind-v1"
@ -15,7 +15,6 @@ top_k = 8
max_seq_len = 1 * 1024 max_seq_len = 1 * 1024
# ----------------------------------------------------------------------------- # -----------------------------------------------------------------------------
@st.cache_resource @st.cache_resource
def load_model_tokenizer(): def load_model_tokenizer():
model = AutoModelForCausalLM.from_pretrained( model = AutoModelForCausalLM.from_pretrained(
@ -31,7 +30,6 @@ def load_model_tokenizer():
generation_config = GenerationConfig.from_pretrained(model_id) generation_config = GenerationConfig.from_pretrained(model_id)
return model, tokenizer, generation_config return model, tokenizer, generation_config
def clear_chat_messages(): def clear_chat_messages():
del st.session_state.messages del st.session_state.messages
@ -50,7 +48,6 @@ def init_chat_messages():
return st.session_state.messages return st.session_state.messages
# max_new_tokens = st.sidebar.slider("max_new_tokens", 0, 1024, 512, step=1) # max_new_tokens = st.sidebar.slider("max_new_tokens", 0, 1024, 512, step=1)
# top_p = st.sidebar.slider("top_p", 0.0, 1.0, 0.8, step=0.01) # top_p = st.sidebar.slider("top_p", 0.0, 1.0, 0.8, step=0.01)
# top_k = st.sidebar.slider("top_k", 0, 100, 0, step=1) # top_k = st.sidebar.slider("top_k", 0, 100, 0, step=1)
@ -119,7 +116,6 @@ def main():
# messages.append({"role": "assistant", "content": assistant_answer}) # messages.append({"role": "assistant", "content": assistant_answer})
messages.append({"role": "assistant", "content": response}) messages.append({"role": "assistant", "content": response})
# print("messages: ", json.dumps(response, ensure_ascii=False), flush=True)
st.button("清空对话", on_click=clear_chat_messages) st.button("清空对话", on_click=clear_chat_messages)

2
model/LMConfig.py
View File

@ -17,7 +17,7 @@ class LMConfig(PretrainedConfig):
norm_eps: float = 1e-5, norm_eps: float = 1e-5,
max_seq_len: int = 512, max_seq_len: int = 512,
dropout: float = 0.0, dropout: float = 0.0,
flash_attn: bool = True, flash_attn: bool = False,
#################################################### ####################################################
# Here are the specific configurations of MOE # Here are the specific configurations of MOE
# When use_moe is false, the following is invalid # When use_moe is false, the following is invalid

4
train_tokenizer.py
View File

@ -56,10 +56,10 @@ def train_tokenizer():
assert tokenizer.token_to_id("</s>") == 2 assert tokenizer.token_to_id("</s>") == 2
# 保存tokenizer # 保存tokenizer
tokenizer_dir = "./minimind_tokenizer" tokenizer_dir = "./model/minimind_tokenizer"
os.makedirs(tokenizer_dir, exist_ok=True) os.makedirs(tokenizer_dir, exist_ok=True)
tokenizer.save(os.path.join(tokenizer_dir, "tokenizer.json")) tokenizer.save(os.path.join(tokenizer_dir, "tokenizer.json"))
tokenizer.model.save("./minimind_tokenizer") tokenizer.model.save("./model/minimind_tokenizer")
# 手动创建配置文件 # 手动创建配置文件
config = { config = {