Skip to content

Commit c3b61ba

Browse files
authored
Merge branch 'dev' into dask-dependencies
2 parents a922678 + f6ac587 commit c3b61ba

File tree

3 files changed

+17
-3
lines changed

3 files changed

+17
-3
lines changed

reproducibility_journal.csv

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -27,3 +27,15 @@ ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l1,0.4.1,20
2727
ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.279,0.025,0,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724,
2828
ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,workarena_l1,0.4.1,2024-10-23_22-30-06,2024-10-23_14-17-40,0.567,0.027,4,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,4cd1e2d4189ddfbeb94129f7b0c9a00c3400ebac,,0.9.0,f25bdcd6b946fc4a79cdbee5fbcad53548af8724,
2929
recursix,GenericAgent-anthropic_claude-3.5-sonnet:beta,webarena,0.11.3,2024-11-02_23-50-17,22a9d3f5-9d86-455e-b451-3ea17690ce8a,0.329,0.016,0,812/812,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.6,1.39.0,0.2.3,418a05d90c74800cd66371b7846ef861185b8c47,,0.11.3,160167ff0d2631826f0131e8e30b92ef448d6881,
30+
ThibaultLSDC,GenericAgent-gpt-4o-mini,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.013,0.007,2,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None,
31+
ThibaultLSDC,GenericAgent-gpt-4o,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.085,0.018,3,233/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None,
32+
ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.391,0.032,3,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None,
33+
ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.021,0.009,2,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None,
34+
ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,workarena_l2_agent_curriculum_eval,0.4.1,2024-10-24_17-08-53,2024-10-23_17-10-46,0.149,0.023,1,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,827d847995f19dc337f3899427340bdddbd81cd5,,0.10.0,None,
35+
ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,workarena_l3_agent_curriculum_eval,0.4.1,2024-10-24_23-03-30,2024-10-24_18-06-57,0.004,0.004,1,235/235,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,de67ed8ad4321740ff05cf26ab889978be706460,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca,
36+
ThibaultLSDC,GenericAgent-gpt-4o-mini,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.566,0.02,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca,
37+
ThibaultLSDC,GenericAgent-gpt-4o,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.638,0.019,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca,
38+
ThibaultLSDC,GenericAgent-anthropic_claude-3.5-sonnet:beta,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.698,0.018,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca,
39+
ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-70b-instruct,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.576,0.02,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca,
40+
ThibaultLSDC,GenericAgent-openai_o1-mini-2024-09-12,miniwob,0.10.2,2024-10-25_17-16-23,2024-10-25_06-08-16,0.678,0.019,0,625/625,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,f12887f776525bcad6a0c42cb49651ff4f65af43,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca,
41+
ThibaultLSDC,GenericAgent-meta-llama_llama-3.1-405b-instruct,workarena_l1,0.4.1,2024-10-25_20-32-26,2024-10-25_17-34-45,0.433,0.027,1,330/330,None,Linux (#66-Ubuntu SMP Fri Aug 30 13:56:20 UTC 2024),3.12.7,1.39.0,0.2.3,177ba72a7469e5610e6b615adf1bdcde58cb0298,,0.10.2,a9e44a88139798543ba53fc8c45d44997665ccca,

src/agentlab/llm/llm_configs.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -151,6 +151,7 @@
151151
max_input_tokens=40_000,
152152
max_new_tokens=4000,
153153
temperature=1e-1,
154+
vision_support=True,
154155
),
155156
"openrouter/qwen/qwen-2-72b-instruct": OpenRouterModelArgs(
156157
model_name="qwen/qwen-2-72b-instruct",

src/agentlab/llm/llm_utils.py

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,8 @@
88
import time
99
from copy import deepcopy
1010
from functools import cache
11-
from typing import TYPE_CHECKING, Any, Union
11+
from typing import TYPE_CHECKING
12+
from typing import Any, Union
1213
from warnings import warn
1314

1415
import numpy as np
@@ -353,9 +354,9 @@ def add_image(self, image: np.ndarray | Image.Image | str, detail: str = None):
353354
else:
354355
image_url = image
355356
if detail:
356-
self.add_content("image", {"url": image_url, "detail": detail})
357+
self.add_content("image_url", {"url": image_url, "detail": detail})
357358
else:
358-
self.add_content("image", image_url)
359+
self.add_content("image_url", image_url)
359360

360361
def to_markdown(self):
361362
if isinstance(self["content"], str):

0 commit comments

Comments
 (0)