Add Physics, Chemistry, Biology specialist LoRA weights and fix model info

.gitattributes

@@ -1,36 +1,3 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
 grogu-lora/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -114,9 +114,9 @@ The system achieves state-of-the-art results on graduate-level science benchmark
 │  │  GROGU   │  │ PHYSICS  │  │CHEMISTRY │  │ BIOLOGY  │        │
 │  │ (General)│  │ Expert   │  │  Expert  │  │  Expert  │        │
 │  │          │  │          │  │          │  │          │        │
-│  │ Nemotron │  │ QwQ-32B  │  │ QwQ-32B  │  │ QwQ-32B  │        │
-│  │ Qwen 1.5B│  │ Physics  │  │ Chemistry│  │ Biology  │        │
-│  │ + LoRA   │  │ LoRA     │  │ LoRA     │  │ LoRA     │        │
+│  │ Nemotron │  │Qwen2.5   │  │Qwen2.5   │  │ Nemotron │        │
+│  │ Qwen 1.5B│  │  1.5B    │  │  1.5B    │  │ Qwen 1.5B│        │
+│  │ + LoRA   │  │ + LoRA   │  │ + LoRA   │  │ + LoRA   │        │
 │  └────┬─────┘  └────┬─────┘  └────┬─────┘  └────┬─────┘        │
 │       │             │             │             │               │
 │       └─────────────┴──────┬──────┴─────────────┘               │
@@ -140,10 +140,12 @@ The system achieves state-of-the-art results on graduate-level science benchmark
 
 | Component | Base Model | Training Method | Parameters |
 |-----------|------------|-----------------|------------|
-| **Grogu (Generalist)** | Nemotron-Qwen-1.5B | LoRA (r=16, α=32) | ~1.5B + 2.4M LoRA |
-| **Physics Expert** | QwQ-32B | LoRA fine-tuning | ~32B + adapters |
-| **Chemistry Expert** | QwQ-32B | LoRA fine-tuning | ~32B + adapters |
-| **Biology Expert** | QwQ-32B | LoRA fine-tuning | ~32B + adapters |
+| **Grogu (Generalist)** | nvidia/nemotron-qwen-1.5b | LoRA (r=16, α=32) | ~1.5B + 2.4M LoRA |
+| **Physics Expert** | Qwen/Qwen2.5-1.5B-Instruct | LoRA fine-tuning | ~1.5B + adapters |
+| **Chemistry Expert** | Qwen/Qwen2.5-1.5B-Instruct | LoRA fine-tuning | ~1.5B + adapters |
+| **Biology Expert** | nvidia/nemotron-qwen-1.5b | LoRA fine-tuning (ProRL) | ~1.5B + adapters |
+
+> **Note**: All 4 agents use efficient 1.5B parameter models, allowing the entire system to run on a single 12GB GPU.
 
 ---
 

biology-lora/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "nvidia/nemotron-qwen-1.5b",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

biology-lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997da1c27c7778fc89ccfc7a268637666d054d713502231909e8d4ba72dfce38
+size 17462432

chemistry-lora/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

chemistry-lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63566a15f8b707a90e953896cf3691bde5d85d9b8ed800d43249815ff3d7b4e
+size 17462432

configs/debate_config.yaml

@@ -8,31 +8,31 @@ system:
   version: "1.0.0"
   organization: "Zenith Global AI Ltd"
 
-# Model Paths (update with your HuggingFace paths after upload)
+# Model Paths
 models:
   grogu:
     base_model: "nvidia/nemotron-qwen-1.5b"
-    lora_path: "zenith-global/grogu-science-moe/grogu-lora"
+    lora_path: "RhinoWithAcape/grogu-science-moe/grogu-lora"
     weight: 1.0
-    description: "General reasoning agent with curriculum-trained LoRA"
+    description: "General reasoning agent with curriculum-trained LoRA (1.5B)"
 
   physics:
-    base_model: "Qwen/QwQ-32B-Preview"
-    lora_path: null  # Add path if releasing physics specialist
+    base_model: "Qwen/Qwen2.5-1.5B-Instruct"
+    lora_path: "RhinoWithAcape/grogu-science-moe/physics-lora"
     weight: 1.2
-    description: "Physics domain specialist"
+    description: "Physics domain specialist (1.5B)"
 
   chemistry:
-    base_model: "Qwen/QwQ-32B-Preview"
-    lora_path: null  # Add path if releasing chemistry specialist
+    base_model: "Qwen/Qwen2.5-1.5B-Instruct"
+    lora_path: "RhinoWithAcape/grogu-science-moe/chemistry-lora"
     weight: 1.2
-    description: "Chemistry domain specialist"
+    description: "Chemistry domain specialist (1.5B)"
 
   biology:
-    base_model: "Qwen/QwQ-32B-Preview"
-    lora_path: null  # Add path if releasing biology specialist
+    base_model: "nvidia/nemotron-qwen-1.5b"
+    lora_path: "RhinoWithAcape/grogu-science-moe/biology-lora"
     weight: 1.2
-    description: "Biology domain specialist"
+    description: "Biology domain specialist - Nemotron ProRL (1.5B)"
 
 # Debate Configuration
 debate:
@@ -140,8 +140,8 @@ hardware:
     description: "Grogu alone (1.5B parameters)"
 
   full_system:
-    gpu_memory: "80GB+"
-    description: "All 4 agents (32B specialists require significant VRAM)"
+    gpu_memory: "12GB"
+    description: "All 4 agents (4x 1.5B = ~6B total, fits on single GPU)"
 
   recommended:
     device: "cuda"

physics-lora/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

physics-lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa38957390b839969f90818c4883a3436ad4a2772547c8b9fb013f6ceb44f638
+size 17462432