Hugging Face's logo

LLMnegotiation
/
tas_rps_vanilla_ad_align_seed1111

Safetensors
Model card Files
xet
 Community
Muqeeth commited on
Commit
6f09deb
·
verified ·
1 Parent(s): f5289bc

Add files using upload-large-folder tool

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. run.log +3 -0
  3. seed_1111/Qwen/Qwen2.5-7B-Instruct/adapters/agent_adapter/adapter_model.safetensors +3 -0
  4. seed_1111/Qwen/Qwen2.5-7B-Instruct/adapters/critic_adapter/adapter_model.safetensors +3 -0
  5. seed_1111/agent_trainer/critic_optimizer_state.pt +3 -0
  6. seed_1111/agent_trainer/policy_optimizer_state.pt +3 -0
  7. seed_1111/agent_trainer/trainer_annealing_state.pkl +3 -0
  8. seed_1111/random_state.pkl +3 -0
  9. src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_agent.rst +7 -0
  10. src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_game.rst +7 -0
  11. src_code_for_reproducibility/docs/source/src.models.new_local_llm.rst +7 -0
  12. src_code_for_reproducibility/docs/source/src.training.reinforce_training.rst +7 -0
  13. src_code_for_reproducibility/docs/source/src.utils.parallel_shuffle.rst +7 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ run.log filter=lfs diff=lfs merge=lfs -text
run.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d7f5fb9fb8e400ac72c67ddcb2e47410d67def12d342cd22c6d2a3da939caf
3
+ size 18304419
seed_1111/Qwen/Qwen2.5-7B-Instruct/adapters/agent_adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e595e1194596a9a2832585f85a37117729599b43604e2532d95d425ab0ec6b2
3
+ size 323014168
seed_1111/Qwen/Qwen2.5-7B-Instruct/adapters/critic_adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c990983fc8fae67d5cab961c03f7c68cb799470378d58c1ec8e42789cbc620
3
+ size 323014168
seed_1111/agent_trainer/critic_optimizer_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1574fdb90735a922b09c67d07f7abdbd51181f00dc7bed878cb80adb5f50c1d
3
+ size 2631
seed_1111/agent_trainer/policy_optimizer_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75880d583004e565d16d94bca58e48e24d3504d8354fbc4baa8e98d375a6e58c
3
+ size 139325440
seed_1111/agent_trainer/trainer_annealing_state.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350f03fb2b3c4cc87211d397d2937ac89d5bd4064f2e98a75cfd3c3e6a73f014
3
+ size 104
seed_1111/random_state.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78fd6ec06d4dad2e553fa5d4237cd3eea88e70b5a3f508348f67fe7bfa8f61ae
3
+ size 12174
src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_agent.rst ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ src.environments.ipd.ipd\_agent module
2
+ ======================================
3
+
4
+ .. automodule:: src.environments.ipd.ipd_agent
5
+ :members:
6
+ :undoc-members:
7
+ :show-inheritance:
src_code_for_reproducibility/docs/source/src.environments.ipd.ipd_game.rst ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ src.environments.ipd.ipd\_game module
2
+ =====================================
3
+
4
+ .. automodule:: src.environments.ipd.ipd_game
5
+ :members:
6
+ :undoc-members:
7
+ :show-inheritance:
src_code_for_reproducibility/docs/source/src.models.new_local_llm.rst ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ src.models.new\_local\_llm module
2
+ =================================
3
+
4
+ .. automodule:: src.models.new_local_llm
5
+ :members:
6
+ :undoc-members:
7
+ :show-inheritance:
src_code_for_reproducibility/docs/source/src.training.reinforce_training.rst ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ src.training.reinforce\_training module
2
+ =======================================
3
+
4
+ .. automodule:: src.training.reinforce_training
5
+ :members:
6
+ :undoc-members:
7
+ :show-inheritance:
src_code_for_reproducibility/docs/source/src.utils.parallel_shuffle.rst ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ src.utils.parallel\_shuffle module
2
+ ==================================
3
+
4
+ .. automodule:: src.utils.parallel_shuffle
5
+ :members:
6
+ :undoc-members:
7
+ :show-inheritance: