NousResearch/atropos
1
0
Fork 0
mirror of https://github.com/NousResearch/atropos.git synced 2026-04-25 17:10:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge edmundman's UFC_FIGHT_PREDICTOR contribution

Browse source
This commit is contained in:
Shannon Sands 2025-05-23 15:33:02 +10:00
parent 0e660a7429
commit 606b917042
73 changed files with 25564 additions and 3223 deletions
Download patch file Download diff file Expand all files Collapse all files

10
environments/tool_calling_server.py
View file

@ -44,7 +44,7 @@ class SingleToolCallingEnv(BaseEnv):
def config_init(self) -> Tuple[BaseEnvConfig, List[APIServerConfig]]:
env_config = BaseEnvConfig(
tokenizer_name="NousResearch/DeepHermes-3-Llama-3-8B-Preview",
group_size=32,
group_size=16,
use_wandb=True,
rollout_server_url="http://localhost:8000",
total_steps=2000,
@ -64,13 +64,6 @@ class SingleToolCallingEnv(BaseEnv):
num_max_requests_at_once=32,
num_requests_for_eval=256,
),
APIServerConfig(
model_name="NousResearch/DeepHermes-3-Llama-3-8B-Preview",
base_url="http://localhost:9005/v1",
api_key="x",
num_max_requests_at_once=32,
num_requests_for_eval=256,
),
]
return env_config, server_configs
@ -301,7 +294,6 @@ class SingleToolCallingEnv(BaseEnv):
max_tokens=1024 * 15,
temperature=0.8, # Using temperature to get diverse responses
)
to_score = list()
for i, completion_choice in enumerate(completions.choices):