提交 3a6a6fa8 作者: imClumsyPanda

update model_config.py

上级 74800058
......@@ -27,7 +27,6 @@ EMBEDDING_MODEL = "text2vec"
# Embedding running device
EMBEDDING_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
# supported LLM models
# llm_model_dict 处理了loader的一些预设行为,如加载位置,模型名称,模型处理器实例
# 在以下字典中修改属性值,以指定本地 LLM 模型存储位置
......@@ -98,8 +97,8 @@ llm_model_dict = {
# 下载模型,如果snapshot_download还是返回网络错误,多试几次,一般是可以的,
# 如果仍然不行,则应该是网络加了防火墙(在服务器上这种情况比较常见),基本只能从别的设备上下载,
# 然后转移到目标设备了.
"bloomz-7b1":{
"name" : "bloomz-7b1",
"bloomz-7b1": {
"name": "bloomz-7b1",
"pretrained_model_name": "bigscience/bloomz-7b1",
"local_model_path": None,
"provides": "MOSSLLM"
......@@ -107,21 +106,21 @@ llm_model_dict = {
},
# 实测加载bigscience/bloom-3b需要170秒左右,暂不清楚为什么这么慢
# 应与它要加载专有token有关
"bloom-3b":{
"name" : "bloom-3b",
"bloom-3b": {
"name": "bloom-3b",
"pretrained_model_name": "bigscience/bloom-3b",
"local_model_path": None,
"provides": "MOSSLLM"
},
"baichuan-7b":{
"name":"baichuan-7b",
"pretrained_model_name":"baichuan-inc/baichuan-7B",
"local_model_path":None,
"provides":"MOSSLLM"
"baichuan-7b": {
"name": "baichuan-7b",
"pretrained_model_name": "baichuan-inc/baichuan-7B",
"local_model_path": None,
"provides": "MOSSLLM"
},
# llama-cpp模型的兼容性问题参考https://github.com/abetlen/llama-cpp-python/issues/204
"ggml-vicuna-13b-1.1-q5":{
"ggml-vicuna-13b-1.1-q5": {
"name": "ggml-vicuna-13b-1.1-q5",
"pretrained_model_name": "lmsys/vicuna-13b-delta-v1.1",
# 这里需要下载好模型的路径,如果下载模型是默认路径则它会下载到用户工作区的
......@@ -131,7 +130,7 @@ llm_model_dict = {
# 此外不同时期的ggml格式并不兼容,因此不同时期的ggml需要安装不同的llama-cpp-python库,且实测pip install 不好使
# 需要手动从https://github.com/abetlen/llama-cpp-python/releases/tag/下载对应的wheel安装
# 实测v0.1.63与本模型的vicuna/ggml-vicuna-13b-1.1/ggml-vic13b-q5_1.bin可以兼容
"local_model_path":f'''{"/".join(os.path.abspath(__file__).split("/")[:3])}/.cache/huggingface/hub/models--vicuna--ggml-vicuna-13b-1.1/blobs/''',
"local_model_path": f'''{"/".join(os.path.abspath(__file__).split("/")[:3])}/.cache/huggingface/hub/models--vicuna--ggml-vicuna-13b-1.1/blobs/''',
"provides": "LLamaLLM"
},
......@@ -161,10 +160,10 @@ llm_model_dict = {
"api_base_url": "http://localhost:8000/v1", # "name"修改为fastchat服务中的"api_base_url"
"api_key": "EMPTY"
},
"openai-chatgpt-3.5":{
"openai-chatgpt-3.5": {
"name": "gpt-3.5-turbo",
"pretrained_model_name": "gpt-3.5-turbo",
"provides":"FastChatOpenAILLM",
"provides": "FastChatOpenAILLM",
"local_model_path": None,
"api_base_url": "https://api.openapi.com/v1",
"api_key": ""
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论