verl GRPO trained model at step 55

README.md

@@ -0,0 +1,9 @@
+---
+base_model: thejaminator/gemma-introspection-20250821-merged
+library_name: peft
+tags:
+- lora
+- peft
+pipeline_tag: text-generation
+---
+

adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "task_type": "CAUSAL_LM",
+  "peft_type": "LORA",
+  "auto_mapping": null,
+  "base_model_name_or_path": "thejaminator/gemma-introspection-20250821-merged",
+  "revision": null,
+  "inference_mode": false,
+  "r": 64,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "exclude_modules": null,
+  "lora_alpha": 128.0,
+  "lora_dropout": 0.0,
+  "fan_in_fan_out": false,
+  "bias": "none",
+  "use_rslora": false,
+  "modules_to_save": null,
+  "init_lora_weights": true,
+  "layers_to_transform": null,
+  "layers_pattern": null,
+  "rank_pattern": {},
+  "alpha_pattern": {},
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "trainable_token_indices": null,
+  "loftq_config": {},
+  "eva_config": null,
+  "corda_config": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "qalora_group_size": 16,
+  "layer_replication": null,
+  "runtime_config": {
+    "ephemeral_gpu_offload": false
+  },
+  "lora_bias": false,
+  "target_parameters": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5130cb3ebb0617e56b3464818ec218ad3e1f0be0e1eae1f9b4d4b280678971c7
+size 864368248