Upload folder using huggingface_hub

README.md

@@ -0,0 +1,57 @@
+---
+tags:
+- merge
+- task_wise
+- llm-adamerge
+base_model: deepseek-ai/deepseek-coder-7b-base-v1.5
+---
+
+# Merged Model using LLM-AdaMerge (task_wise)
+
+This model was created by merging multiple fine-tuned models using the LLM-AdaMerge approach with task_wise merging.
+
+## Merge Details
+
+- **Merge Type**: task_wise
+- **Base Model**: deepseek-ai/deepseek-coder-7b-base-v1.5
+- **Number of Models Merged**: 2
+- **Models Merged**: math, code
+- **Final Training Loss**: N/A
+- **Training Epochs**: 0
+
+## Lambda Coefficients
+
+The following lambda coefficients were learned during training:
+
+
+Task-wise lambda coefficients are stored in the `learned_lambdas.json` file.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("your-username/model-name")
+tokenizer = AutoTokenizer.from_pretrained("your-username/model-name")
+
+# Use the model
+inputs = tokenizer("Hello, how are you?", return_tensors="pt")
+outputs = model.generate(**inputs)
+print(tokenizer.decode(outputs[0]))
+```
+
+## Training Configuration
+
+See the uploaded `training_config.json` file for detailed training configuration.
+
+## Citation
+
+If you use this model, please cite the LLM-AdaMerge paper:
+
+```bibtex
+@article{llmadamerge2024,
+  title={LLM-AdaMerge: Adaptive Model Merging for Large Language Models},
+  author={...},
+  year={2024}
+}
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 102400
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "transformers_version": "4.52.4"
+}

learned_lambdas.json

@@ -0,0 +1,290 @@
+{
+  "lambdas": [
+    [
+      1.0090581178665161,
+      0.39679306745529175
+    ]
+  ],
+  "merge_type": "task_wise",
+  "model_names": [
+    "math",
+    "code"
+  ],
+  "num_models": 2,
+  "num_params": 273,
+  "param_names": [
+    "model.embed_tokens.weight",
+    "model.layers.0.self_attn.q_proj.weight",
+    "model.layers.0.self_attn.k_proj.weight",
+    "model.layers.0.self_attn.v_proj.weight",
+    "model.layers.0.self_attn.o_proj.weight",
+    "model.layers.0.mlp.gate_proj.weight",
+    "model.layers.0.mlp.up_proj.weight",
+    "model.layers.0.mlp.down_proj.weight",
+    "model.layers.0.input_layernorm.weight",
+    "model.layers.0.post_attention_layernorm.weight",
+    "model.layers.1.self_attn.q_proj.weight",
+    "model.layers.1.self_attn.k_proj.weight",
+    "model.layers.1.self_attn.v_proj.weight",
+    "model.layers.1.self_attn.o_proj.weight",
+    "model.layers.1.mlp.gate_proj.weight",
+    "model.layers.1.mlp.up_proj.weight",
+    "model.layers.1.mlp.down_proj.weight",
+    "model.layers.1.input_layernorm.weight",
+    "model.layers.1.post_attention_layernorm.weight",
+    "model.layers.2.self_attn.q_proj.weight",
+    "model.layers.2.self_attn.k_proj.weight",
+    "model.layers.2.self_attn.v_proj.weight",
+    "model.layers.2.self_attn.o_proj.weight",
+    "model.layers.2.mlp.gate_proj.weight",
+    "model.layers.2.mlp.up_proj.weight",
+    "model.layers.2.mlp.down_proj.weight",
+    "model.layers.2.input_layernorm.weight",
+    "model.layers.2.post_attention_layernorm.weight",
+    "model.layers.3.self_attn.q_proj.weight",
+    "model.layers.3.self_attn.k_proj.weight",
+    "model.layers.3.self_attn.v_proj.weight",
+    "model.layers.3.self_attn.o_proj.weight",
+    "model.layers.3.mlp.gate_proj.weight",
+    "model.layers.3.mlp.up_proj.weight",
+    "model.layers.3.mlp.down_proj.weight",
+    "model.layers.3.input_layernorm.weight",
+    "model.layers.3.post_attention_layernorm.weight",
+    "model.layers.4.self_attn.q_proj.weight",
+    "model.layers.4.self_attn.k_proj.weight",
+    "model.layers.4.self_attn.v_proj.weight",
+    "model.layers.4.self_attn.o_proj.weight",
+    "model.layers.4.mlp.gate_proj.weight",
+    "model.layers.4.mlp.up_proj.weight",
+    "model.layers.4.mlp.down_proj.weight",
+    "model.layers.4.input_layernorm.weight",
+    "model.layers.4.post_attention_layernorm.weight",
+    "model.layers.5.self_attn.q_proj.weight",
+    "model.layers.5.self_attn.k_proj.weight",
+    "model.layers.5.self_attn.v_proj.weight",
+    "model.layers.5.self_attn.o_proj.weight",
+    "model.layers.5.mlp.gate_proj.weight",
+    "model.layers.5.mlp.up_proj.weight",
+    "model.layers.5.mlp.down_proj.weight",
+    "model.layers.5.input_layernorm.weight",
+    "model.layers.5.post_attention_layernorm.weight",
+    "model.layers.6.self_attn.q_proj.weight",
+    "model.layers.6.self_attn.k_proj.weight",
+    "model.layers.6.self_attn.v_proj.weight",
+    "model.layers.6.self_attn.o_proj.weight",
+    "model.layers.6.mlp.gate_proj.weight",
+    "model.layers.6.mlp.up_proj.weight",
+    "model.layers.6.mlp.down_proj.weight",
+    "model.layers.6.input_layernorm.weight",
+    "model.layers.6.post_attention_layernorm.weight",
+    "model.layers.7.self_attn.q_proj.weight",
+    "model.layers.7.self_attn.k_proj.weight",
+    "model.layers.7.self_attn.v_proj.weight",
+    "model.layers.7.self_attn.o_proj.weight",
+    "model.layers.7.mlp.gate_proj.weight",
+    "model.layers.7.mlp.up_proj.weight",
+    "model.layers.7.mlp.down_proj.weight",
+    "model.layers.7.input_layernorm.weight",
+    "model.layers.7.post_attention_layernorm.weight",
+    "model.layers.8.self_attn.q_proj.weight",
+    "model.layers.8.self_attn.k_proj.weight",
+    "model.layers.8.self_attn.v_proj.weight",
+    "model.layers.8.self_attn.o_proj.weight",
+    "model.layers.8.mlp.gate_proj.weight",
+    "model.layers.8.mlp.up_proj.weight",
+    "model.layers.8.mlp.down_proj.weight",
+    "model.layers.8.input_layernorm.weight",
+    "model.layers.8.post_attention_layernorm.weight",
+    "model.layers.9.self_attn.q_proj.weight",
+    "model.layers.9.self_attn.k_proj.weight",
+    "model.layers.9.self_attn.v_proj.weight",
+    "model.layers.9.self_attn.o_proj.weight",
+    "model.layers.9.mlp.gate_proj.weight",
+    "model.layers.9.mlp.up_proj.weight",
+    "model.layers.9.mlp.down_proj.weight",
+    "model.layers.9.input_layernorm.weight",
+    "model.layers.9.post_attention_layernorm.weight",
+    "model.layers.10.self_attn.q_proj.weight",
+    "model.layers.10.self_attn.k_proj.weight",
+    "model.layers.10.self_attn.v_proj.weight",
+    "model.layers.10.self_attn.o_proj.weight",
+    "model.layers.10.mlp.gate_proj.weight",
+    "model.layers.10.mlp.up_proj.weight",
+    "model.layers.10.mlp.down_proj.weight",
+    "model.layers.10.input_layernorm.weight",
+    "model.layers.10.post_attention_layernorm.weight",
+    "model.layers.11.self_attn.q_proj.weight",
+    "model.layers.11.self_attn.k_proj.weight",
+    "model.layers.11.self_attn.v_proj.weight",
+    "model.layers.11.self_attn.o_proj.weight",
+    "model.layers.11.mlp.gate_proj.weight",
+    "model.layers.11.mlp.up_proj.weight",
+    "model.layers.11.mlp.down_proj.weight",
+    "model.layers.11.input_layernorm.weight",
+    "model.layers.11.post_attention_layernorm.weight",
+    "model.layers.12.self_attn.q_proj.weight",
+    "model.layers.12.self_attn.k_proj.weight",
+    "model.layers.12.self_attn.v_proj.weight",
+    "model.layers.12.self_attn.o_proj.weight",
+    "model.layers.12.mlp.gate_proj.weight",
+    "model.layers.12.mlp.up_proj.weight",
+    "model.layers.12.mlp.down_proj.weight",
+    "model.layers.12.input_layernorm.weight",
+    "model.layers.12.post_attention_layernorm.weight",
+    "model.layers.13.self_attn.q_proj.weight",
+    "model.layers.13.self_attn.k_proj.weight",
+    "model.layers.13.self_attn.v_proj.weight",
+    "model.layers.13.self_attn.o_proj.weight",
+    "model.layers.13.mlp.gate_proj.weight",
+    "model.layers.13.mlp.up_proj.weight",
+    "model.layers.13.mlp.down_proj.weight",
+    "model.layers.13.input_layernorm.weight",
+    "model.layers.13.post_attention_layernorm.weight",
+    "model.layers.14.self_attn.q_proj.weight",
+    "model.layers.14.self_attn.k_proj.weight",
+    "model.layers.14.self_attn.v_proj.weight",
+    "model.layers.14.self_attn.o_proj.weight",
+    "model.layers.14.mlp.gate_proj.weight",
+    "model.layers.14.mlp.up_proj.weight",
+    "model.layers.14.mlp.down_proj.weight",
+    "model.layers.14.input_layernorm.weight",
+    "model.layers.14.post_attention_layernorm.weight",
+    "model.layers.15.self_attn.q_proj.weight",
+    "model.layers.15.self_attn.k_proj.weight",
+    "model.layers.15.self_attn.v_proj.weight",
+    "model.layers.15.self_attn.o_proj.weight",
+    "model.layers.15.mlp.gate_proj.weight",
+    "model.layers.15.mlp.up_proj.weight",
+    "model.layers.15.mlp.down_proj.weight",
+    "model.layers.15.input_layernorm.weight",
+    "model.layers.15.post_attention_layernorm.weight",
+    "model.layers.16.self_attn.q_proj.weight",
+    "model.layers.16.self_attn.k_proj.weight",
+    "model.layers.16.self_attn.v_proj.weight",
+    "model.layers.16.self_attn.o_proj.weight",
+    "model.layers.16.mlp.gate_proj.weight",
+    "model.layers.16.mlp.up_proj.weight",
+    "model.layers.16.mlp.down_proj.weight",
+    "model.layers.16.input_layernorm.weight",
+    "model.layers.16.post_attention_layernorm.weight",
+    "model.layers.17.self_attn.q_proj.weight",
+    "model.layers.17.self_attn.k_proj.weight",
+    "model.layers.17.self_attn.v_proj.weight",
+    "model.layers.17.self_attn.o_proj.weight",
+    "model.layers.17.mlp.gate_proj.weight",
+    "model.layers.17.mlp.up_proj.weight",
+    "model.layers.17.mlp.down_proj.weight",
+    "model.layers.17.input_layernorm.weight",
+    "model.layers.17.post_attention_layernorm.weight",
+    "model.layers.18.self_attn.q_proj.weight",
+    "model.layers.18.self_attn.k_proj.weight",
+    "model.layers.18.self_attn.v_proj.weight",
+    "model.layers.18.self_attn.o_proj.weight",
+    "model.layers.18.mlp.gate_proj.weight",
+    "model.layers.18.mlp.up_proj.weight",
+    "model.layers.18.mlp.down_proj.weight",
+    "model.layers.18.input_layernorm.weight",
+    "model.layers.18.post_attention_layernorm.weight",
+    "model.layers.19.self_attn.q_proj.weight",
+    "model.layers.19.self_attn.k_proj.weight",
+    "model.layers.19.self_attn.v_proj.weight",
+    "model.layers.19.self_attn.o_proj.weight",
+    "model.layers.19.mlp.gate_proj.weight",
+    "model.layers.19.mlp.up_proj.weight",
+    "model.layers.19.mlp.down_proj.weight",
+    "model.layers.19.input_layernorm.weight",
+    "model.layers.19.post_attention_layernorm.weight",
+    "model.layers.20.self_attn.q_proj.weight",
+    "model.layers.20.self_attn.k_proj.weight",
+    "model.layers.20.self_attn.v_proj.weight",
+    "model.layers.20.self_attn.o_proj.weight",
+    "model.layers.20.mlp.gate_proj.weight",
+    "model.layers.20.mlp.up_proj.weight",
+    "model.layers.20.mlp.down_proj.weight",
+    "model.layers.20.input_layernorm.weight",
+    "model.layers.20.post_attention_layernorm.weight",
+    "model.layers.21.self_attn.q_proj.weight",
+    "model.layers.21.self_attn.k_proj.weight",
+    "model.layers.21.self_attn.v_proj.weight",
+    "model.layers.21.self_attn.o_proj.weight",
+    "model.layers.21.mlp.gate_proj.weight",
+    "model.layers.21.mlp.up_proj.weight",
+    "model.layers.21.mlp.down_proj.weight",
+    "model.layers.21.input_layernorm.weight",
+    "model.layers.21.post_attention_layernorm.weight",
+    "model.layers.22.self_attn.q_proj.weight",
+    "model.layers.22.self_attn.k_proj.weight",
+    "model.layers.22.self_attn.v_proj.weight",
+    "model.layers.22.self_attn.o_proj.weight",
+    "model.layers.22.mlp.gate_proj.weight",
+    "model.layers.22.mlp.up_proj.weight",
+    "model.layers.22.mlp.down_proj.weight",
+    "model.layers.22.input_layernorm.weight",
+    "model.layers.22.post_attention_layernorm.weight",
+    "model.layers.23.self_attn.q_proj.weight",
+    "model.layers.23.self_attn.k_proj.weight",
+    "model.layers.23.self_attn.v_proj.weight",
+    "model.layers.23.self_attn.o_proj.weight",
+    "model.layers.23.mlp.gate_proj.weight",
+    "model.layers.23.mlp.up_proj.weight",
+    "model.layers.23.mlp.down_proj.weight",
+    "model.layers.23.input_layernorm.weight",
+    "model.layers.23.post_attention_layernorm.weight",
+    "model.layers.24.self_attn.q_proj.weight",
+    "model.layers.24.self_attn.k_proj.weight",
+    "model.layers.24.self_attn.v_proj.weight",
+    "model.layers.24.self_attn.o_proj.weight",
+    "model.layers.24.mlp.gate_proj.weight",
+    "model.layers.24.mlp.up_proj.weight",
+    "model.layers.24.mlp.down_proj.weight",
+    "model.layers.24.input_layernorm.weight",
+    "model.layers.24.post_attention_layernorm.weight",
+    "model.layers.25.self_attn.q_proj.weight",
+    "model.layers.25.self_attn.k_proj.weight",
+    "model.layers.25.self_attn.v_proj.weight",
+    "model.layers.25.self_attn.o_proj.weight",
+    "model.layers.25.mlp.gate_proj.weight",
+    "model.layers.25.mlp.up_proj.weight",
+    "model.layers.25.mlp.down_proj.weight",
+    "model.layers.25.input_layernorm.weight",
+    "model.layers.25.post_attention_layernorm.weight",
+    "model.layers.26.self_attn.q_proj.weight",
+    "model.layers.26.self_attn.k_proj.weight",
+    "model.layers.26.self_attn.v_proj.weight",
+    "model.layers.26.self_attn.o_proj.weight",
+    "model.layers.26.mlp.gate_proj.weight",
+    "model.layers.26.mlp.up_proj.weight",
+    "model.layers.26.mlp.down_proj.weight",
+    "model.layers.26.input_layernorm.weight",
+    "model.layers.26.post_attention_layernorm.weight",
+    "model.layers.27.self_attn.q_proj.weight",
+    "model.layers.27.self_attn.k_proj.weight",
+    "model.layers.27.self_attn.v_proj.weight",
+    "model.layers.27.self_attn.o_proj.weight",
+    "model.layers.27.mlp.gate_proj.weight",
+    "model.layers.27.mlp.up_proj.weight",
+    "model.layers.27.mlp.down_proj.weight",
+    "model.layers.27.input_layernorm.weight",
+    "model.layers.27.post_attention_layernorm.weight",
+    "model.layers.28.self_attn.q_proj.weight",
+    "model.layers.28.self_attn.k_proj.weight",
+    "model.layers.28.self_attn.v_proj.weight",
+    "model.layers.28.self_attn.o_proj.weight",
+    "model.layers.28.mlp.gate_proj.weight",
+    "model.layers.28.mlp.up_proj.weight",
+    "model.layers.28.mlp.down_proj.weight",
+    "model.layers.28.input_layernorm.weight",
+    "model.layers.28.post_attention_layernorm.weight",
+    "model.layers.29.self_attn.q_proj.weight",
+    "model.layers.29.self_attn.k_proj.weight",
+    "model.layers.29.self_attn.v_proj.weight",
+    "model.layers.29.self_attn.o_proj.weight",
+    "model.layers.29.mlp.gate_proj.weight",
+    "model.layers.29.mlp.up_proj.weight",
+    "model.layers.29.mlp.down_proj.weight",
+    "model.layers.29.input_layernorm.weight",
+    "model.layers.29.post_attention_layernorm.weight",
+    "model.norm.weight",
+    "lm_head.weight"
+  ]
+}

logs/save_merged_model_20251009_191904.log

@@ -0,0 +1,74 @@
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO - Starting merged model save process
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO - Arguments: {'lambdas_path': '/work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/task-wise/cross_entropy-ep3-lr0001-10%dataset-lambda07_wo_scheduler/llm_adamerge_lambdas.json', 'model_config': '/work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/task-wise/cross_entropy-ep3-lr0001-10%dataset-lambda07_wo_scheduler/model_config.yaml', 'output_dir': '/work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler', 'model_name': 'merged-model', 'push_to_hub': False, 'hub_repo_id': 'lejelly/deepseek-ep3-10%dataset-taskwise-lambda07', 'private': False, 'device': 'cuda', 'debug': False}
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO - Loading lambdas from /work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/task-wise/cross_entropy-ep3-lr0001-10%dataset-lambda07_wo_scheduler/llm_adamerge_lambdas.json
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO - Auto-detected parameter-wise merge from JSON structure
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO - Merge type: parameter_wise
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO - [Initial] Memory Usage:
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO -   Process: 0.45 GB (0.2%)
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO -   System: 7.62 GB / 212.49 GB (8.2%)
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO -   Available: 195.05 GB
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:19:04 - experiment_save_merged_model - INFO - Loading models
+2025-10-09 19:19:21 - experiment_save_merged_model - INFO - [After loading models] Memory Usage:
+2025-10-09 19:19:21 - experiment_save_merged_model - INFO -   Process: 38.81 GB (18.3%)
+2025-10-09 19:19:21 - experiment_save_merged_model - INFO -   System: 46.75 GB / 212.49 GB (29.9%)
+2025-10-09 19:19:21 - experiment_save_merged_model - INFO -   Available: 148.94 GB
+2025-10-09 19:19:21 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:19:21 - experiment_save_merged_model - INFO - Initializing parameter_wise AdaMerge
+2025-10-09 19:20:30 - experiment_save_merged_model - INFO - Loading learned lambdas
+2025-10-09 19:20:30 - experiment_save_merged_model - INFO - Deleting original models to free memory (task vectors already computed)
+2025-10-09 19:20:30 - experiment_save_merged_model - INFO - [Before deleting models] Memory Usage:
+2025-10-09 19:20:30 - experiment_save_merged_model - INFO -   Process: 64.60 GB (30.4%)
+2025-10-09 19:20:30 - experiment_save_merged_model - INFO -   System: 72.42 GB / 212.49 GB (42.0%)
+2025-10-09 19:20:30 - experiment_save_merged_model - INFO -   Available: 123.23 GB
+2025-10-09 19:20:30 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:20:30 - experiment_save_merged_model - INFO - Clearing model_loader references
+2025-10-09 19:20:30 - experiment_save_merged_model - INFO - Deleting model variables
+2025-10-09 19:20:30 - experiment_save_merged_model - INFO - Running garbage collection
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO - [After deleting models and GC] Memory Usage:
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO -   Process: 38.84 GB (18.3%)
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO -   System: 47.01 GB / 212.49 GB (30.1%)
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO -   Available: 148.63 GB
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO - [After loading lambdas] Memory Usage:
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO -   Process: 38.84 GB (18.3%)
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO -   System: 47.01 GB / 212.49 GB (30.1%)
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO -   Available: 148.63 GB
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO - Creating merged model with learned lambdas
+2025-10-09 19:20:31 - experiment_save_merged_model - INFO - Using merge_models_for_save()
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO - [After merging models] Memory Usage:
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO -   Process: 38.85 GB (18.3%)
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO -   System: 72.65 GB / 212.49 GB (42.1%)
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO -   Available: 123.00 GB
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 12.87 GB, Reserved: 25.74 GB, Total: 94.50 GB
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO - Freeing memory from AdaMerge object (task vectors and base params no longer needed)
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO - Deleting task vectors
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO - Deleting base params
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO - Deleting functional model
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO - [After freeing AdaMerge memory] Memory Usage:
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO -   Process: 0.20 GB (0.1%)
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO -   System: 21.06 GB / 212.49 GB (17.8%)
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO -   Available: 174.58 GB
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 12.87 GB, Reserved: 12.87 GB, Total: 94.50 GB
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO - Saving merged model to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler
+2025-10-09 19:22:25 - experiment_save_merged_model - INFO - Moving merged model to CPU for saving
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO - Successfully saved 3 safetensors files:
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO -   - model-00003-of-00003.safetensors (3674.14 MB)
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO -   - model-00002-of-00003.safetensors (4750.20 MB)
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO -   - model-00001-of-00003.safetensors (4756.17 MB)
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO - [After saving model] Memory Usage:
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO -   Process: 13.09 GB (6.2%)
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO -   System: 21.23 GB / 212.49 GB (17.9%)
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO -   Available: 174.42 GB
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO - Saving tokenizer
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO - Copied lambdas file to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler/learned_lambdas.json
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO - Creating model card
+2025-10-09 19:23:17 - experiment_save_merged_model - INFO - Cleaning up models
+2025-10-09 19:23:18 - experiment_save_merged_model - INFO - [After cleanup] Memory Usage:
+2025-10-09 19:23:18 - experiment_save_merged_model - INFO -   Process: 13.09 GB (6.2%)
+2025-10-09 19:23:18 - experiment_save_merged_model - INFO -   System: 21.23 GB / 212.49 GB (17.9%)
+2025-10-09 19:23:18 - experiment_save_merged_model - INFO -   Available: 174.41 GB
+2025-10-09 19:23:18 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:23:18 - experiment_save_merged_model - INFO - Model saved successfully to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler

logs/save_merged_model_20251009_192735.log

@@ -0,0 +1,74 @@
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO - Starting merged model save process
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO - Arguments: {'lambdas_path': '/work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/task-wise/cross_entropy-ep3-lr0001-10%dataset-lambda07_wo_scheduler/llm_adamerge_lambdas.json', 'model_config': '/work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/task-wise/cross_entropy-ep3-lr0001-10%dataset-lambda07_wo_scheduler/model_config.yaml', 'output_dir': '/work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler', 'model_name': 'merged-model', 'push_to_hub': False, 'hub_repo_id': 'lejelly/deepseek-ep310%data-taskwise-lambda07', 'private': False, 'device': 'cuda', 'debug': False}
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO - Loading lambdas from /work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/task-wise/cross_entropy-ep3-lr0001-10%dataset-lambda07_wo_scheduler/llm_adamerge_lambdas.json
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO - Auto-detected parameter-wise merge from JSON structure
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO - Merge type: parameter_wise
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO - [Initial] Memory Usage:
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO -   Process: 0.51 GB (0.2%)
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO -   System: 7.65 GB / 212.49 GB (8.2%)
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO -   Available: 195.05 GB
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:27:35 - experiment_save_merged_model - INFO - Loading models
+2025-10-09 19:27:57 - experiment_save_merged_model - INFO - [After loading models] Memory Usage:
+2025-10-09 19:27:57 - experiment_save_merged_model - INFO -   Process: 38.82 GB (18.3%)
+2025-10-09 19:27:57 - experiment_save_merged_model - INFO -   System: 53.32 GB / 212.49 GB (33.0%)
+2025-10-09 19:27:57 - experiment_save_merged_model - INFO -   Available: 142.38 GB
+2025-10-09 19:27:57 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:27:57 - experiment_save_merged_model - INFO - Initializing parameter_wise AdaMerge
+2025-10-09 19:29:06 - experiment_save_merged_model - INFO - Loading learned lambdas
+2025-10-09 19:29:06 - experiment_save_merged_model - INFO - Deleting original models to free memory (task vectors already computed)
+2025-10-09 19:29:06 - experiment_save_merged_model - INFO - [Before deleting models] Memory Usage:
+2025-10-09 19:29:06 - experiment_save_merged_model - INFO -   Process: 64.58 GB (30.4%)
+2025-10-09 19:29:06 - experiment_save_merged_model - INFO -   System: 74.07 GB / 212.49 GB (42.8%)
+2025-10-09 19:29:06 - experiment_save_merged_model - INFO -   Available: 121.59 GB
+2025-10-09 19:29:06 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:29:06 - experiment_save_merged_model - INFO - Clearing model_loader references
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO - Deleting model variables
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO - Running garbage collection
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO - [After deleting models and GC] Memory Usage:
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO -   Process: 38.81 GB (18.3%)
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO -   System: 48.34 GB / 212.49 GB (30.7%)
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO -   Available: 147.32 GB
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO - [After loading lambdas] Memory Usage:
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO -   Process: 38.81 GB (18.3%)
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO -   System: 48.34 GB / 212.49 GB (30.7%)
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO -   Available: 147.32 GB
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO - Creating merged model with learned lambdas
+2025-10-09 19:29:07 - experiment_save_merged_model - INFO - Using merge_models_for_save()
+2025-10-09 19:31:01 - experiment_save_merged_model - INFO - [After merging models] Memory Usage:
+2025-10-09 19:31:01 - experiment_save_merged_model - INFO -   Process: 38.81 GB (18.3%)
+2025-10-09 19:31:01 - experiment_save_merged_model - INFO -   System: 79.82 GB / 212.49 GB (45.5%)
+2025-10-09 19:31:01 - experiment_save_merged_model - INFO -   Available: 115.83 GB
+2025-10-09 19:31:01 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 12.87 GB, Reserved: 25.74 GB, Total: 94.50 GB
+2025-10-09 19:31:01 - experiment_save_merged_model - INFO - Freeing memory from AdaMerge object (task vectors and base params no longer needed)
+2025-10-09 19:31:01 - experiment_save_merged_model - INFO - Deleting task vectors
+2025-10-09 19:31:02 - experiment_save_merged_model - INFO - Deleting base params
+2025-10-09 19:31:02 - experiment_save_merged_model - INFO - Deleting functional model
+2025-10-09 19:31:02 - experiment_save_merged_model - INFO - [After freeing AdaMerge memory] Memory Usage:
+2025-10-09 19:31:02 - experiment_save_merged_model - INFO -   Process: 0.16 GB (0.1%)
+2025-10-09 19:31:02 - experiment_save_merged_model - INFO -   System: 27.78 GB / 212.49 GB (21.0%)
+2025-10-09 19:31:02 - experiment_save_merged_model - INFO -   Available: 167.87 GB
+2025-10-09 19:31:02 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 12.87 GB, Reserved: 12.87 GB, Total: 94.50 GB
+2025-10-09 19:31:02 - experiment_save_merged_model - INFO - Saving merged model to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler
+2025-10-09 19:31:02 - experiment_save_merged_model - INFO - Moving merged model to CPU for saving
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO - Successfully saved 3 safetensors files:
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   - model-00003-of-00003.safetensors (3674.14 MB)
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   - model-00002-of-00003.safetensors (4750.20 MB)
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   - model-00001-of-00003.safetensors (4756.17 MB)
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO - [After saving model] Memory Usage:
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   Process: 13.04 GB (6.1%)
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   System: 22.41 GB / 212.49 GB (18.5%)
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   Available: 173.24 GB
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO - Saving tokenizer
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO - Copied lambdas file to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler/learned_lambdas.json
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO - Creating model card
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO - Cleaning up models
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO - [After cleanup] Memory Usage:
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   Process: 13.05 GB (6.1%)
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   System: 22.03 GB / 212.49 GB (18.3%)
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   Available: 173.62 GB
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:31:55 - experiment_save_merged_model - INFO - Model saved successfully to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler

logs/save_merged_model_20251009_193429.log

@@ -0,0 +1,74 @@
+2025-10-09 19:34:29 - experiment_save_merged_model - INFO - Starting merged model save process
+2025-10-09 19:34:29 - experiment_save_merged_model - INFO - Arguments: {'lambdas_path': '/work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/task-wise/cross_entropy-ep3-lr0001-10%dataset-lambda07_wo_scheduler/llm_adamerge_lambdas.json', 'model_config': '/work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/task-wise/cross_entropy-ep3-lr0001-10%dataset-lambda07_wo_scheduler/model_config.yaml', 'output_dir': '/work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler', 'model_name': 'merged-model', 'push_to_hub': False, 'hub_repo_id': 'lejelly/deepseek-ep3-data10-taskwise-lambda07', 'private': False, 'device': 'cuda', 'debug': False}
+2025-10-09 19:34:29 - experiment_save_merged_model - INFO - Loading lambdas from /work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/task-wise/cross_entropy-ep3-lr0001-10%dataset-lambda07_wo_scheduler/llm_adamerge_lambdas.json
+2025-10-09 19:34:29 - experiment_save_merged_model - INFO - Auto-detected parameter-wise merge from JSON structure
+2025-10-09 19:34:29 - experiment_save_merged_model - INFO - Merge type: parameter_wise
+2025-10-09 19:34:30 - experiment_save_merged_model - INFO - [Initial] Memory Usage:
+2025-10-09 19:34:30 - experiment_save_merged_model - INFO -   Process: 0.45 GB (0.2%)
+2025-10-09 19:34:30 - experiment_save_merged_model - INFO -   System: 7.58 GB / 212.49 GB (8.2%)
+2025-10-09 19:34:30 - experiment_save_merged_model - INFO -   Available: 195.10 GB
+2025-10-09 19:34:30 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:34:30 - experiment_save_merged_model - INFO - Loading models
+2025-10-09 19:34:47 - experiment_save_merged_model - INFO - [After loading models] Memory Usage:
+2025-10-09 19:34:47 - experiment_save_merged_model - INFO -   Process: 38.80 GB (18.3%)
+2025-10-09 19:34:47 - experiment_save_merged_model - INFO -   System: 48.73 GB / 212.49 GB (30.8%)
+2025-10-09 19:34:47 - experiment_save_merged_model - INFO -   Available: 146.96 GB
+2025-10-09 19:34:47 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:34:47 - experiment_save_merged_model - INFO - Initializing parameter_wise AdaMerge
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO - Loading learned lambdas
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO - Deleting original models to free memory (task vectors already computed)
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO - [Before deleting models] Memory Usage:
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   Process: 64.61 GB (30.4%)
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   System: 73.23 GB / 212.49 GB (42.4%)
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   Available: 122.42 GB
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO - Clearing model_loader references
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO - Deleting model variables
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO - Running garbage collection
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO - [After deleting models and GC] Memory Usage:
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   Process: 38.85 GB (18.3%)
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   System: 47.78 GB / 212.49 GB (30.4%)
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   Available: 147.86 GB
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO - [After loading lambdas] Memory Usage:
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   Process: 38.85 GB (18.3%)
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   System: 47.78 GB / 212.49 GB (30.4%)
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   Available: 147.86 GB
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO - Creating merged model with learned lambdas
+2025-10-09 19:35:57 - experiment_save_merged_model - INFO - Using merge_models_for_save()
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO - [After merging models] Memory Usage:
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO -   Process: 38.80 GB (18.3%)
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO -   System: 72.57 GB / 212.49 GB (42.1%)
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO -   Available: 123.07 GB
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 12.87 GB, Reserved: 25.74 GB, Total: 94.50 GB
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO - Freeing memory from AdaMerge object (task vectors and base params no longer needed)
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO - Deleting task vectors
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO - Deleting base params
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO - Deleting functional model
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO - [After freeing AdaMerge memory] Memory Usage:
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO -   Process: 0.14 GB (0.1%)
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO -   System: 21.03 GB / 212.49 GB (17.8%)
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO -   Available: 174.61 GB
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 12.87 GB, Reserved: 12.87 GB, Total: 94.50 GB
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO - Saving merged model to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler
+2025-10-09 19:37:52 - experiment_save_merged_model - INFO - Moving merged model to CPU for saving
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO - Successfully saved 3 safetensors files:
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   - model-00003-of-00003.safetensors (3674.14 MB)
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   - model-00002-of-00003.safetensors (4750.20 MB)
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   - model-00001-of-00003.safetensors (4756.17 MB)
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO - [After saving model] Memory Usage:
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   Process: 13.02 GB (6.1%)
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   System: 21.25 GB / 212.49 GB (17.9%)
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   Available: 174.39 GB
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO - Saving tokenizer
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO - Copied lambdas file to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler/learned_lambdas.json
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO - Creating model card
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO - Cleaning up models
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO - [After cleanup] Memory Usage:
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   Process: 13.03 GB (6.1%)
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   System: 21.26 GB / 212.49 GB (17.9%)
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   Available: 174.38 GB
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO -   GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB
+2025-10-09 19:38:45 - experiment_save_merged_model - INFO - Model saved successfully to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/llmadamerge/task-wise-cross_entropy-lr0001-ep3-10%dataset/lambda07_wo_scheduler

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716299e68d13d4307ae782120983bf5421f68b4829ae27399906b2828dcd951e
+size 4987202112

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33578069f24de58a8de312ed2c46890a81297f93237231100299646c1c504ad2
+size 4980945328

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74789c74dbad1a0da08ad61ec7606847bec8b267f71502664fe215aaeba3922
+size 3852615456

model.safetensors.index.json

@@ -0,0 +1,280 @@
+{
+  "metadata": {
+    "total_size": 13820731392
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,146 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100015": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}