From f3e4e26e2f095e1f0d3b5faeaec23fde2b0b33a0 Mon Sep 17 00:00:00 2001 From: dackdawn Date: Mon, 19 Jun 2023 21:40:26 +0800 Subject: [PATCH] =?UTF-8?q?=E6=B7=BB=E5=8A=A00613=E6=A8=A1=E5=9E=8B?= =?UTF-8?q?=E7=9A=84=E5=A3=B0=E6=98=8E?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit openai对gpt-3.5-turbo的RPM限制是3，而gpt-3.5-turbo-0613的RPM是60，虽然两个模型的内容是一致的，但是选定特定模型可以获得更高的RPM和TPM --- config.py | 2 +- request_llm/bridge_all.py | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/config.py b/config.py index 87e0ec9..917c268 100644 --- a/config.py +++ b/config.py @@ -46,7 +46,7 @@ MAX_RETRY = 2 # 模型选择是 (注意: LLM_MODEL是默认选中的模型, 同时它必须被包含在AVAIL_LLM_MODELS切换列表中 ) LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓ -AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "newbing-free", "stack-claude"] +AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0613", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "newbing-free", "stack-claude"] # P.S. 其他可用的模型还包括 ["newbing-free", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"] # 本地LLM模型如ChatGLM的执行方式 CPU/GPU diff --git a/request_llm/bridge_all.py b/request_llm/bridge_all.py index a27407c..22fa04b 100644 --- a/request_llm/bridge_all.py +++ b/request_llm/bridge_all.py @@ -93,6 +93,24 @@ model_info = { "token_cnt": get_token_num_gpt35, }, + "gpt-3.5-turbo-0613": { + "fn_with_ui": chatgpt_ui, + "fn_without_ui": chatgpt_noui, + "endpoint": openai_endpoint, + "max_token": 4096, + "tokenizer": tokenizer_gpt35, + "token_cnt": get_token_num_gpt35, + }, + + "gpt-3.5-turbo-16k-0613": { + "fn_with_ui": chatgpt_ui, + "fn_without_ui": chatgpt_noui, + "endpoint": openai_endpoint, + "max_token": 1024 * 16, + "tokenizer": tokenizer_gpt35, + "token_cnt": get_token_num_gpt35, + }, + "gpt-4": { "fn_with_ui": chatgpt_ui, "fn_without_ui": chatgpt_noui,