dale_yxc/ragflow_python
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add support for PerfXCloud (#1883)

Browse Source 
### What problem does this PR solve?

#1853  add support for PerfXCloud

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
This commit is contained in:
黄腾
2024-08-12 10:11:50 +08:00
committed by GitHub
parent fdd5b1b8cf
commit 9a6dc89156
6 changed files with 184 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

154
conf/llm_factories.json
View File

@@ -2442,6 +2442,158 @@
"model_type": "chat"
}
]
}
},
{
"name": "PerfXCloud",
"logo": "",
"tags": "LLM,TEXT EMBEDDING",
"status": "1",
"llm": [
{
"llm_name": "deepseek-v2-chat",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "llama3.1:405b",
"tags": "LLM,CHAT,128k",
"max_tokens": 131072,
"model_type": "chat"
},
{
"llm_name": "Qwen2-72B-Instruct",
"tags": "LLM,CHAT,128k",
"max_tokens": 131072,
"model_type": "chat"
},
{
"llm_name": "Qwen2-72B-Instruct-GPTQ-Int4",
"tags": "LLM,CHAT,2k",
"max_tokens": 2048,
"model_type": "chat"
},
{
"llm_name": "Qwen2-72B-Instruct-awq-int4",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Llama3-Chinese_v2",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "Yi-1_5-9B-Chat-16K",
"tags": "LLM,CHAT,16k",
"max_tokens": 16384,
"model_type": "chat"
},
{
"llm_name": "Qwen1.5-72B-Chat-GPTQ-Int4",
"tags": "LLM,CHAT,2k",
"max_tokens": 2048,
"model_type": "chat"
},
{
"llm_name": "Meta-Llama-3.1-8B-Instruct",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "Qwen2-7B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "deepseek-v2-lite-chat",
"tags": "LLM,CHAT,2k",
"max_tokens": 2048,
"model_type": "chat"
},
{
"llm_name": "Qwen2-7B",
"tags": "LLM,CHAT,128k",
"max_tokens": 131072,
"model_type": "chat"
},
{
"llm_name": "chatglm3-6b",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "Meta-Llama-3-70B-Instruct-GPTQ-Int4",
"tags": "LLM,CHAT,1k",
"max_tokens": 1024,
"model_type": "chat"
},
{
"llm_name": "Meta-Llama-3-8B-Instruct",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "Mistral-7B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "MindChat-Qwen-7B-v2",
"tags": "LLM,CHAT,2k",
"max_tokens": 2048,
"model_type": "chat"
},
{
"llm_name": "phi-2",
"tags": "LLM,CHAT,2k",
"max_tokens": 2048,
"model_type": "chat"
},
{
"llm_name": "SOLAR-10_7B-Instruct",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "Mixtral-8x7B-Instruct-v0.1-GPTQ",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Qwen1.5-7B",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "BAAI/bge-large-en-v1.5",
"tags": "TEXT EMBEDDING",
"max_tokens": 512,
"model_type": "embedding"
},
{
"llm_name": "BAAI/bge-large-zh-v1.5",
"tags": "TEXT EMBEDDING",
"max_tokens": 1024,
"model_type": "embedding"
},
{
"llm_name": "BAAI/bge-m3",
"tags": "TEXT EMBEDDING",
"max_tokens": 8192,
"model_type": "embedding"
}
]
}
]
}