Upload folder using huggingface_hub

config.json

@@ -1,8 +1,7 @@
 {
-  "_attn_implementation_autoset": true,
   "_name_or_path": "lilmeaty/testing_semifinal",
   "architectures": [
-    "LlamaForCausalLM"
+    "PartiallySharedLayerModel"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -35,7 +34,7 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 128256

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.47.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ababbc023c6adae7e8ed6a34fa4effb2dc6258333a823a34ab6c10e7a46508f
+size 4838750476

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd846cda54994ae32f75c0becad4dd838f25eadd1dcac8553e20ffddeef17070
+size 4964730768

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272bdf83f181c1e1077065b05c1dec1194530b08cb5a9bf5066437c0b50ff74d
+size 679702024

model.safetensors.index.json

@@ -0,0 +1,206 @@
+{
+  "metadata": {
+    "total_size": 10483163276
+  },
+  "weight_map": {
+    "ability_weights": "model-00001-of-00003.safetensors",
+    "ability_weights_v2": "model-00001-of-00003.safetensors",
+    "accountability_head.bias": "model-00002-of-00003.safetensors",
+    "accountability_head.weight": "model-00002-of-00003.safetensors",
+    "action_head.bias": "model-00002-of-00003.safetensors",
+    "action_head.weight": "model-00002-of-00003.safetensors",
+    "adaptability_head.bias": "model-00002-of-00003.safetensors",
+    "adaptability_head.weight": "model-00002-of-00003.safetensors",
+    "agreeableness_head.bias": "model-00002-of-00003.safetensors",
+    "agreeableness_head.weight": "model-00002-of-00003.safetensors",
+    "altruism_head.bias": "model-00002-of-00003.safetensors",
+    "altruism_head.weight": "model-00002-of-00003.safetensors",
+    "assessment_head.bias": "model-00002-of-00003.safetensors",
+    "assessment_head.weight": "model-00002-of-00003.safetensors",
+    "capacity_head.bias": "model-00002-of-00003.safetensors",
+    "capacity_head.weight": "model-00002-of-00003.safetensors",
+    "capacity_predictions": "model-00001-of-00003.safetensors",
+    "civic_engagement_head.bias": "model-00003-of-00003.safetensors",
+    "civic_engagement_head.weight": "model-00003-of-00003.safetensors",
+    "cognitive_head.bias": "model-00002-of-00003.safetensors",
+    "cognitive_head.weight": "model-00002-of-00003.safetensors",
+    "collaboration_head.bias": "model-00002-of-00003.safetensors",
+    "collaboration_head.weight": "model-00002-of-00003.safetensors",
+    "communication_head.bias": "model-00002-of-00003.safetensors",
+    "communication_head.weight": "model-00002-of-00003.safetensors",
+    "compassion_head.bias": "model-00003-of-00003.safetensors",
+    "compassion_head.weight": "model-00003-of-00003.safetensors",
+    "conscientiousness_head.bias": "model-00002-of-00003.safetensors",
+    "conscientiousness_head.weight": "model-00002-of-00003.safetensors",
+    "courage_head.bias": "model-00002-of-00003.safetensors",
+    "courage_head.weight": "model-00002-of-00003.safetensors",
+    "creativity_head.bias": "model-00002-of-00003.safetensors",
+    "creativity_head.weight": "model-00002-of-00003.safetensors",
+    "critical_thinking_head.bias": "model-00002-of-00003.safetensors",
+    "critical_thinking_head.weight": "model-00002-of-00003.safetensors",
+    "cultural_sensitivity_head.bias": "model-00003-of-00003.safetensors",
+    "cultural_sensitivity_head.weight": "model-00003-of-00003.safetensors",
+    "curiosity_head.bias": "model-00002-of-00003.safetensors",
+    "curiosity_head.weight": "model-00002-of-00003.safetensors",
+    "decision_head.bias": "model-00002-of-00003.safetensors",
+    "decision_head.weight": "model-00002-of-00003.safetensors",
+    "digital_literacy_head.bias": "model-00003-of-00003.safetensors",
+    "digital_literacy_head.weight": "model-00003-of-00003.safetensors",
+    "draft_model.embed_tokens.weight": "model-00002-of-00003.safetensors",
+    "draft_model.emotion_vector": "model-00001-of-00003.safetensors",
+    "draft_model.lm_head.weight": "model-00002-of-00003.safetensors",
+    "draft_model.memory_keys": "model-00001-of-00003.safetensors",
+    "draft_model.memory_values": "model-00001-of-00003.safetensors",
+    "draft_model.norm.bias": "model-00002-of-00003.safetensors",
+    "draft_model.norm.weight": "model-00002-of-00003.safetensors",
+    "draft_model.prediction_head.bias": "model-00002-of-00003.safetensors",
+    "draft_model.prediction_head.weight": "model-00002-of-00003.safetensors",
+    "draft_model.response_selector.bias": "model-00002-of-00003.safetensors",
+    "draft_model.response_selector.weight": "model-00002-of-00003.safetensors",
+    "draft_model.shared_layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "draft_model.shared_layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.shared_layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.shared_layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.shared_layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "draft_model.shared_layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.shared_layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.shared_layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.shared_layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.simulation_head.bias": "model-00002-of-00003.safetensors",
+    "draft_model.simulation_head.weight": "model-00002-of-00003.safetensors",
+    "draft_model.stimuli_vector": "model-00001-of-00003.safetensors",
+    "draft_model.unique_layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "draft_model.unique_layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.unique_layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.unique_layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.unique_layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "draft_model.unique_layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.unique_layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.unique_layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "draft_model.unique_layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "emotion_vector": "model-00001-of-00003.safetensors",
+    "emotional_head.bias": "model-00002-of-00003.safetensors",
+    "emotional_head.weight": "model-00002-of-00003.safetensors",
+    "emotional_regulation_head.bias": "model-00003-of-00003.safetensors",
+    "emotional_regulation_head.weight": "model-00003-of-00003.safetensors",
+    "empathy_head.bias": "model-00002-of-00003.safetensors",
+    "empathy_head.weight": "model-00002-of-00003.safetensors",
+    "environmental_awareness_head.bias": "model-00003-of-00003.safetensors",
+    "environmental_awareness_head.weight": "model-00003-of-00003.safetensors",
+    "extraversion_head.bias": "model-00002-of-00003.safetensors",
+    "extraversion_head.weight": "model-00002-of-00003.safetensors",
+    "fairness_head.bias": "model-00002-of-00003.safetensors",
+    "fairness_head.weight": "model-00002-of-00003.safetensors",
+    "feedback_head.bias": "model-00002-of-00003.safetensors",
+    "feedback_head.weight": "model-00002-of-00003.safetensors",
+    "financial_literacy_head.bias": "model-00003-of-00003.safetensors",
+    "financial_literacy_head.weight": "model-00003-of-00003.safetensors",
+    "foresight_head.bias": "model-00002-of-00003.safetensors",
+    "foresight_head.weight": "model-00002-of-00003.safetensors",
+    "forgiveness_head.bias": "model-00003-of-00003.safetensors",
+    "forgiveness_head.weight": "model-00003-of-00003.safetensors",
+    "goal_head.bias": "model-00002-of-00003.safetensors",
+    "goal_head.weight": "model-00002-of-00003.safetensors",
+    "gratitude_head.bias": "model-00003-of-00003.safetensors",
+    "gratitude_head.weight": "model-00003-of-00003.safetensors",
+    "health_consciousness_head.bias": "model-00003-of-00003.safetensors",
+    "health_consciousness_head.weight": "model-00003-of-00003.safetensors",
+    "honesty_head.bias": "model-00002-of-00003.safetensors",
+    "honesty_head.weight": "model-00002-of-00003.safetensors",
+    "humility_head.bias": "model-00003-of-00003.safetensors",
+    "humility_head.weight": "model-00003-of-00003.safetensors",
+    "imagination_head.bias": "model-00002-of-00003.safetensors",
+    "imagination_head.weight": "model-00002-of-00003.safetensors",
+    "intuition_head.bias": "model-00002-of-00003.safetensors",
+    "intuition_head.weight": "model-00002-of-00003.safetensors",
+    "kindness_head.bias": "model-00002-of-00003.safetensors",
+    "kindness_head.weight": "model-00002-of-00003.safetensors",
+    "leadership_head.bias": "model-00002-of-00003.safetensors",
+    "leadership_head.weight": "model-00002-of-00003.safetensors",
+    "learning_head.bias": "model-00002-of-00003.safetensors",
+    "learning_head.weight": "model-00002-of-00003.safetensors",
+    "lifelong_learning_head.bias": "model-00003-of-00003.safetensors",
+    "lifelong_learning_head.weight": "model-00003-of-00003.safetensors",
+    "lm_head.weight": "model-00001-of-00003.safetensors",
+    "memory_keys": "model-00001-of-00003.safetensors",
+    "memory_values": "model-00001-of-00003.safetensors",
+    "moral_reasoning_head.bias": "model-00002-of-00003.safetensors",
+    "moral_reasoning_head.weight": "model-00002-of-00003.safetensors",
+    "morality_head.bias": "model-00002-of-00003.safetensors",
+    "morality_head.weight": "model-00002-of-00003.safetensors",
+    "negotiation_head.bias": "model-00002-of-00003.safetensors",
+    "negotiation_head.weight": "model-00002-of-00003.safetensors",
+    "neuroticism_head.bias": "model-00002-of-00003.safetensors",
+    "neuroticism_head.weight": "model-00002-of-00003.safetensors",
+    "norm.bias": "model-00001-of-00003.safetensors",
+    "norm.weight": "model-00001-of-00003.safetensors",
+    "novelty_vector": "model-00001-of-00003.safetensors",
+    "openness_head.bias": "model-00002-of-00003.safetensors",
+    "openness_head.weight": "model-00002-of-00003.safetensors",
+    "optimism_head.bias": "model-00003-of-00003.safetensors",
+    "optimism_head.weight": "model-00003-of-00003.safetensors",
+    "patience_head.bias": "model-00002-of-00003.safetensors",
+    "patience_head.weight": "model-00002-of-00003.safetensors",
+    "perseverance_head.bias": "model-00002-of-00003.safetensors",
+    "perseverance_head.weight": "model-00002-of-00003.safetensors",
+    "planning_head.bias": "model-00002-of-00003.safetensors",
+    "planning_head.weight": "model-00002-of-00003.safetensors",
+    "prediction_head.bias": "model-00001-of-00003.safetensors",
+    "prediction_head.weight": "model-00001-of-00003.safetensors",
+    "problem_solving_head.bias": "model-00002-of-00003.safetensors",
+    "problem_solving_head.weight": "model-00002-of-00003.safetensors",
+    "questioning_head.bias": "model-00002-of-00003.safetensors",
+    "questioning_head.weight": "model-00002-of-00003.safetensors",
+    "reflection_head.bias": "model-00002-of-00003.safetensors",
+    "reflection_head.weight": "model-00002-of-00003.safetensors",
+    "resilience_head.bias": "model-00002-of-00003.safetensors",
+    "resilience_head.weight": "model-00002-of-00003.safetensors",
+    "response_selector.bias": "model-00001-of-00003.safetensors",
+    "response_selector.weight": "model-00001-of-00003.safetensors",
+    "self_awareness_head.bias": "model-00003-of-00003.safetensors",
+    "self_awareness_head.weight": "model-00003-of-00003.safetensors",
+    "self_awareness_vector": "model-00001-of-00003.safetensors",
+    "self_control_head.bias": "model-00002-of-00003.safetensors",
+    "self_control_head.weight": "model-00002-of-00003.safetensors",
+    "self_efficacy_head.bias": "model-00003-of-00003.safetensors",
+    "self_efficacy_head.weight": "model-00003-of-00003.safetensors",
+    "self_esteem_head.bias": "model-00003-of-00003.safetensors",
+    "self_esteem_head.weight": "model-00003-of-00003.safetensors",
+    "self_improvement_head.bias": "model-00002-of-00003.safetensors",
+    "self_improvement_head.weight": "model-00002-of-00003.safetensors",
+    "shaman_head.bias": "model-00002-of-00003.safetensors",
+    "shaman_head.weight": "model-00002-of-00003.safetensors",
+    "shared_layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "shared_layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "shared_layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "shared_layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "shared_layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "shared_layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "shared_layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "shared_layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "shared_layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "simulation_head.bias": "model-00001-of-00003.safetensors",
+    "simulation_head.weight": "model-00001-of-00003.safetensors",
+    "stimuli_vector": "model-00001-of-00003.safetensors",
+    "strategy_head.bias": "model-00002-of-00003.safetensors",
+    "strategy_head.weight": "model-00002-of-00003.safetensors",
+    "stress_management_head.bias": "model-00003-of-00003.safetensors",
+    "stress_management_head.weight": "model-00003-of-00003.safetensors",
+    "sustainability_head.bias": "model-00002-of-00003.safetensors",
+    "sustainability_head.weight": "model-00002-of-00003.safetensors",
+    "time_management_head.bias": "model-00003-of-00003.safetensors",
+    "time_management_head.weight": "model-00003-of-00003.safetensors",
+    "unique_layer.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "unique_layer.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "unique_layer.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "unique_layer.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "unique_layer.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "unique_layer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "unique_layer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "unique_layer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "unique_layer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "wisdom_head.bias": "model-00002-of-00003.safetensors",
+    "wisdom_head.weight": "model-00002-of-00003.safetensors"
+  }
+}