Commit b7c2ffc
authored
- .gitignore+3
- berkeley-function-call-leaderboard/README.md+1-1
- berkeley-function-call-leaderboard/SUPPORTED_MODELS.md+9-9
- berkeley-function-call-leaderboard/bfcl_eval/_llm_response_generation.py+16-9
- berkeley-function-call-leaderboard/bfcl_eval/constants/eval_config.py+3
- berkeley-function-call-leaderboard/bfcl_eval/constants/model_config.py+31-31
- berkeley-function-call-leaderboard/bfcl_eval/constants/supported_models.py+9-9
- berkeley-function-call-leaderboard/bfcl_eval/data/BFCL_v4_irrelevance.json+1-1
- berkeley-function-call-leaderboard/bfcl_eval/data/BFCL_v4_live_multiple.json+1-1
- berkeley-function-call-leaderboard/bfcl_eval/data/BFCL_v4_live_simple.json+2-2
- berkeley-function-call-leaderboard/bfcl_eval/data/BFCL_v4_multi_turn_base.json+120-120
- berkeley-function-call-leaderboard/bfcl_eval/data/BFCL_v4_multi_turn_long_context.json+121-121
- berkeley-function-call-leaderboard/bfcl_eval/data/BFCL_v4_multi_turn_miss_func.json+122-122
- berkeley-function-call-leaderboard/bfcl_eval/data/BFCL_v4_multi_turn_miss_param.json+122-122
- berkeley-function-call-leaderboard/bfcl_eval/data/BFCL_v4_parallel.json+2-2
- berkeley-function-call-leaderboard/bfcl_eval/data/multi_turn_func_doc/gorilla_file_system.json+3-3
- berkeley-function-call-leaderboard/bfcl_eval/data/multi_turn_func_doc/message_api.json+1-1
- berkeley-function-call-leaderboard/bfcl_eval/data/multi_turn_func_doc/ticket_api.json+2-2
- berkeley-function-call-leaderboard/bfcl_eval/data/multi_turn_func_doc/trading_bot.json+3-5
- berkeley-function-call-leaderboard/bfcl_eval/data/multi_turn_func_doc/travel_booking.json+3-2
- berkeley-function-call-leaderboard/bfcl_eval/data/multi_turn_func_doc/vehicle_control.json+1-1
- berkeley-function-call-leaderboard/bfcl_eval/data/possible_answer/BFCL_v4_live_simple.json+2-2
- berkeley-function-call-leaderboard/bfcl_eval/data/possible_answer/BFCL_v4_multi_turn_base.json+80-80
- berkeley-function-call-leaderboard/bfcl_eval/data/possible_answer/BFCL_v4_multi_turn_long_context.json+75-75
- berkeley-function-call-leaderboard/bfcl_eval/data/possible_answer/BFCL_v4_multi_turn_miss_func.json+75-75
- berkeley-function-call-leaderboard/bfcl_eval/data/possible_answer/BFCL_v4_multi_turn_miss_param.json+79-79
- berkeley-function-call-leaderboard/bfcl_eval/data/possible_answer/BFCL_v4_parallel.json+2-2
- berkeley-function-call-leaderboard/bfcl_eval/eval_checker/eval_runner.py+2-1
- berkeley-function-call-leaderboard/bfcl_eval/eval_checker/multi_turn_eval/func_source_code/gorilla_file_system.py+37-17
- berkeley-function-call-leaderboard/bfcl_eval/eval_checker/multi_turn_eval/func_source_code/message_api.py+4-5
- berkeley-function-call-leaderboard/bfcl_eval/eval_checker/multi_turn_eval/func_source_code/posting_api.py+3-3
- berkeley-function-call-leaderboard/bfcl_eval/eval_checker/multi_turn_eval/func_source_code/ticket_api.py+4-4
- berkeley-function-call-leaderboard/bfcl_eval/eval_checker/multi_turn_eval/func_source_code/trading_bot.py+41-92
- berkeley-function-call-leaderboard/bfcl_eval/eval_checker/multi_turn_eval/func_source_code/travel_booking.py+62-25
- berkeley-function-call-leaderboard/bfcl_eval/eval_checker/multi_turn_eval/func_source_code/vehicle_control.py+1-1
- berkeley-function-call-leaderboard/bfcl_eval/model_handler/api_inference/claude.py+2-2
- berkeley-function-call-leaderboard/bfcl_eval/model_handler/api_inference/deepseek.py+8-22
- berkeley-function-call-leaderboard/bfcl_eval/model_handler/api_inference/grok.py+1-1
- berkeley-function-call-leaderboard/bfcl_eval/model_handler/api_inference/kimi.py+2-2
- berkeley-function-call-leaderboard/bfcl_eval/model_handler/utils.py+2-8
- berkeley-function-call-leaderboard/bfcl_eval/scripts/visualize_multi_turn_ground_truth_conversation.py+15-7
- berkeley-function-call-leaderboard/bfcl_eval/utils.py+71-63
- berkeley-function-call-leaderboard/pyproject.toml+2-1
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
12 | 12 | | |
13 | 13 | | |
14 | 14 | | |
| 15 | + | |
15 | 16 | | |
16 | 17 | | |
| 18 | + | |
17 | 19 | | |
18 | 20 | | |
19 | 21 | | |
20 | 22 | | |
21 | 23 | | |
22 | | - | |
23 | | - | |
24 | | - | |
25 | | - | |
| 24 | + | |
| 25 | + | |
| 26 | + | |
| 27 | + | |
26 | 28 | | |
27 | | - | |
28 | | - | |
29 | | - | |
30 | | - | |
31 | 29 | | |
| 30 | + | |
| 31 | + | |
32 | 32 | | |
33 | | - | |
34 | | - | |
35 | | - | |
36 | | - | |
37 | | - | |
38 | | - | |
39 | | - | |
40 | | - | |
41 | | - | |
42 | | - | |
43 | | - | |
44 | | - | |
45 | | - | |
46 | | - | |
47 | | - | |
48 | | - | |
| 33 | + | |
| 34 | + | |
| 35 | + | |
| 36 | + | |
| 37 | + | |
| 38 | + | |
| 39 | + | |
| 40 | + | |
| 41 | + | |
| 42 | + | |
| 43 | + | |
| 44 | + | |
| 45 | + | |
| 46 | + | |
| 47 | + | |
| 48 | + | |
| 49 | + | |
| 50 | + | |
| 51 | + | |
| 52 | + | |
| 53 | + | |
| 54 | + | |
| 55 | + | |
| 56 | + | |
| 57 | + | |
| 58 | + | |
| 59 | + | |
| 60 | + | |
| 61 | + | |
| 62 | + | |
| 63 | + | |
| 64 | + | |
| 65 | + | |
| 66 | + | |
| 67 | + | |
| 68 | + | |
| 69 | + | |
| 70 | + | |
| 71 | + | |
| 72 | + | |
| 73 | + | |
| 74 | + | |
| 75 | + | |
| 76 | + | |
| 77 | + | |
| 78 | + | |
| 79 | + | |
| 80 | + | |
| 81 | + | |
| 82 | + | |
| 83 | + | |
| 84 | + | |
| 85 | + | |
| 86 | + | |
| 87 | + | |
| 88 | + | |
| 89 | + | |
49 | 90 | | |
50 | 91 | | |
51 | 92 | | |
52 | 93 | | |
53 | 94 | | |
54 | 95 | | |
55 | 96 | | |
56 | | - | |
57 | 97 | | |
58 | 98 | | |
59 | | - | |
| 99 | + | |
60 | 100 | | |
61 | | - | |
62 | | - | |
| 101 | + | |
| 102 | + | |
63 | 103 | | |
64 | 104 | | |
65 | 105 | | |
66 | | - | |
67 | | - | |
68 | | - | |
| 106 | + | |
| 107 | + | |
| 108 | + | |
69 | 109 | | |
70 | | - | |
71 | | - | |
72 | | - | |
73 | | - | |
74 | | - | |
75 | | - | |
76 | | - | |
| 110 | + | |
| 111 | + | |
| 112 | + | |
| 113 | + | |
77 | 114 | | |
78 | | - | |
79 | | - | |
| 115 | + | |
| 116 | + | |
80 | 117 | | |
81 | | - | |
82 | | - | |
| 118 | + | |
| 119 | + | |
| 120 | + | |
| 121 | + | |
83 | 122 | | |
84 | 123 | | |
85 | 124 | | |
86 | | - | |
| 125 | + | |
| 126 | + | |
| 127 | + | |
87 | 128 | | |
88 | 129 | | |
89 | 130 | | |
| |||
0 commit comments