chore: import upstream snapshot with attribution

tests/llm/data/alpaca.csv

@@ -0,0 +1,4 @@
+system,instruction,input,output
+00000,11111,22222,3.3
+,aaaaa,,ccccc
+,AAAAA,BBBBB,CCCCC

tests/llm/data/alpaca.jsonl

@@ -0,0 +1,3 @@
+{"instruction": "11111", "input": "22222", "output": "33333", "history": [["aaaaa", "bbbbb"]], "system": "system123"}
+{"instruction": "aaaaa", "output": "ccccc"}
+{"instruction": "AAAAA", "input": "BBBBB", "output": "CCCCC"}

tests/llm/data/alpaca2.csv

@@ -0,0 +1,4 @@
+instruction,output
+11111,33333
+aaaaa,ccccc
+AAAAA,CCCCC

tests/llm/data/chatml.jsonl

@@ -0,0 +1,3 @@
+{"messages": [{"role": "system", "content": "00000"}, {"role": "user", "content": "11111"}, {"role": "assistant", "content": "22222"}]}
+{"messages": [{"role": "user", "content": "aaaaa"}, {"role": "assistant", "content": "bbbbb"}, {"role": "user", "content": "ccccc"}, {"role": "assistant", "content": "ddddd"}]}
+{"messages": [{"role": "user", "content": "AAAAA"}, {"role": "assistant", "content": "BBBBB"}, {"role": "user", "content": "CCCCC"}, {"role": "assistant", "content": "DDDDD"}]}

tests/llm/data/conversations.jsonl

@@ -0,0 +1,3 @@
+{"conversations": [{"from": "system", "value": "00000"}, {"from": "user", "value": "11111"}, {"from": "assistant", "value": "22222"}]}
+{"conversations": [{"from": "user", "value": "aaaaa"}, {"from": "assistant", "value": "bbbbb"}, {"from": "user", "value": "ccccc"}, {"from": "assistant", "value": "ddddd"}]}
+{"conversations": [{"from": "user", "value": "AAAAA"}, {"from": "assistant", "value": "BBBBB"}, {"from": "user", "value": "CCCCC"}, {"from": "assistant", "value": "DDDDD"}]}

tests/llm/data/multi_modal_1.jsonl

@@ -0,0 +1,3 @@
+{"query": "<img>https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg</img>55555", "response": "66666"}
+{"query": "<img>https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg</img><img>https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg</img>eeeee", "response": "fffff", "history": [["hello", "123"]]}
+{"query": "EEEEE", "response": "FFFFF", "history": [["AAAAA", "BBBBB"], ["CCCCC", "DDDDD"]]}

tests/llm/data/multi_modal_2.jsonl

@@ -0,0 +1,3 @@
+{"query": "55555", "response": "66666", "images": ["https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"]}
+{"query": "eeeee", "response": "fffff", "history": [], "images": ["https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"]}
+{"query": "EEEEE", "response": "FFFFF", "history": [["AAAAA", "BBBBB"], ["CCCCC", "DDDDD"]], "images": ["https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg", "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg", "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"]}

tests/llm/data/multi_modal_3.jsonl

@@ -0,0 +1,3 @@
+{"query": "55555", "response": "66666", "images": ["https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"]}
+{"query": "eeeee", "response": "fffff", "history": [], "images": ["https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"]}
+{"query": "EEEEE", "response": "FFFFF", "history": [["AAAAA", "BBBBB"], ["CCCCC", "DDDDD"]], "images": ["https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"]}

tests/llm/data/sharegpt.jsonl

@@ -0,0 +1,3 @@
+{"system": "00000", "conversation": [{"human": "11111", "assistant": "22222"}]}
+{"conversation": [{"human": "aaaaa", "assistant": "bbbbb"}]}
+{"conversation": [{"human": "AAAAA", "assistant": "BBBBB"}, {"human": "CCCCC", "assistant": "DDDDD"}, {"human": "EEEEE", "assistant": "FFFFF"}]}

tests/llm/data/swift_multi.json

@@ -0,0 +1,3 @@
+[{"system": "00000", "query": "55555", "response": "66666"},
+{"query": "eeeee", "response": "fffff", "history": []},
+{"query": "EEEEE", "response": "FFFFF", "history": [["AAAAA", "BBBBB"], ["CCCCC", "DDDDD"]]}]

tests/llm/data/swift_multi.jsonl

@@ -0,0 +1,3 @@
+{"system": "00000", "query": "55555", "response": "66666"}
+{"query": "eeeee", "response": "fffff", "history": []}
+{"query": "EEEEE", "response": "FFFFF", "history": [["AAAAA", "BBBBB"], ["CCCCC", "DDDDD"]]}

tests/llm/data/swift_pre.csv

@@ -0,0 +1,4 @@
+response
+11111
+aaaaa
+AAAAA

tests/llm/data/swift_pre.jsonl

@@ -0,0 +1,3 @@
+{"response": "11111"}
+{"response": "aaaaa"}
+{"response": "AAAAA"}

tests/llm/data/swift_single.csv

@@ -0,0 +1,4 @@
+system,query,response
+00000,11111,22222
+,aaaaa,bbbbb
+,AAAAA,BBBBB

tests/llm/data/swift_single.jsonl

@@ -0,0 +1,3 @@
+{"system": "00000", "query": "11111", "response": "22222"}
+{"query": "aaaaa", "response": "bbbbb"}
+{"query": "AAAAA", "response": "BBBBB"}