初始化项目，由ModelHub XC社区提供模型

Model: SeongryongJung/Qwen3-8B-Material-RLSD-TR Source: Original Platform
2026-08-12 14:13:18 +08:00
commit 7f2f12b8da
42 changed files with 326692 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,38 @@
+*.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
+results/training_score.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/last/tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,116 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- qwen3
+- reinforcement-learning
+- rlsd-tr
+- text-generation
+- trust-region
+base_model: Qwen/Qwen3-8B
+---
+
+# Qwen3-8B-Material-RLSD-TR
+
+This repository contains the Qwen3-8B `material` `RLSD_TR` batch-size-32 run.
+
+The repository root contains the best validation checkpoint, selected by validation `mean@16`. `checkpoints/last/` contains the final checkpoint.
+
+## Performance
+
+| Dataset | Method | Base model | Train batch size | Best val mean@16 | Best checkpoint | Final val mean@16 | Final checkpoint |
+|---|---|---|---:|---:|---:|---:|---:|
+| Material / SciKnowEval material | RLSD_TR | Qwen3-8B | 32 | 76.46% | 100 | 76.46% | 100 |
+
+![Training and validation scores](results/training_score.png)
+
+## Validation Mean@16
+
+| step | val_mean16 | percent |
+|---:|---:|---:|
+| 10 | 0.655585106383 | 65.56% |
+| 20 | 0.688829787234 | 68.88% |
+| 30 | 0.697473404255 | 69.75% |
+| 40 | 0.734042553191 | 73.40% |
+| 50 | 0.746675531915 | 74.67% |
+| 60 | 0.751329787234 | 75.13% |
+| 70 | 0.751994680851 | 75.20% |
+| 80 | 0.744680851064 | 74.47% |
+| 90 | 0.753989361702 | 75.40% |
+| 100 | 0.764627659574 | 76.46% |
+
+## Detailed Training Hyperparameters
+
+| Section | Parameter | Value | Source |
+|---|---|---:|---|
+| Run identity | `Base model` | `Qwen/Qwen3-8B` | queue/script override |
+| Run identity | `Dataset` | `Material / SciKnowEval material` | run_qwen3_generalization.sh |
+| Run identity | `Method` | `RLSD_TR` | run_qwen3_generalization.sh |
+| Run identity | `Config` | `rlsd` | run_qwen3_generalization.sh |
+| Run identity | `Experiment` | `qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8` | run_qwen3_generalization.sh |
+| Run identity | `W&B run` | `run-20260703_115716-skza3cpu` | wandb |
+| Data | `Train file` | `datasets/sciknoweval/material/train.parquet` | script override |
+| Data | `Validation file` | `datasets/sciknoweval/material/test.parquet` | script override |
+| Data | `Train batch size` | `32` | queue/script override |
+| Data | `Train max samples` | `3200` | queue/script override |
+| Schedule | `Total training steps` | `100` | queue/script override |
+| Schedule | `Validation before train` | `False` | queue/script override |
+| Schedule | `Save frequency` | `10` | queue/script override |
+| Schedule | `Validation frequency` | `10` | queue/script override |
+| Sequence | `Max prompt length` | `2048` | queue/script override |
+| Sequence | `Max response length` | `8192` | queue/script override |
+| Sequence | `Max model length` | `10240` | queue/script override |
+| Rollout | `Train rollout n` | `8` | queue/script override |
+| Rollout | `Validation rollout n` | `16` | queue/script override |
+| Rollout | `vLLM GPU memory utilization` | `0.8` | queue/script override |
+| Optimization | `Learning rate` | `1e-6` | RLSD_TR method override |
+| Optimization | `Weight decay` | `0.01` | script override |
+| PPO/GRPO | `PPO mini batch size` | `8` | queue/script override |
+| PPO/GRPO | `Normalize GRPO advantages by std` | `False` | baseline_grpo.yaml / script override |
+| Rollout correction | `Importance sampling mode` | `token` | script override |
+| Rollout correction | `IS threshold` | `2.0` | script override |
+| Checkpoint/Logging | `Checkpoint root` | `checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8` | script override |
+| Checkpoint/Logging | `Latest checkpointed iteration` | `100` | latest_checkpointed_iteration.txt |
+| Checkpoint/Logging | `External actor archive` | `checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/_actor_archive` | preserve_actor_checkpoints.py |
+| Checkpoint/Logging | `Logger` | `console, wandb` | ppo_trainer.yaml |
+| RLSD_TR | `Policy loss mode` | `rlsd` | method override |
+| RLSD_TR | `Teacher regularization` | `trust-region` | method override |
+| RLSD_TR | `Trust-region mix / teacher update rate` | `0.1` | queue/script override |
+| RLSD_TR | `Token reweight lambda` | `0.5` | queue/script override |
+| RLSD_TR | `Token reweight eps_w` | `0.2` | queue/script override |
+| RLSD_TR | `Token reweight decay steps` | `0` | queue/script override |
+| RLSD_TR | `Fused kernels` | `False` | method override |
+
+Raw result and artifact files:
+
+- `results/validation_mean16.csv`
+- `results/training_scores.csv`
+- `results/hyperparameters.csv`
+- `results/training_score.png`
+- `results/training_score.svg`
+- `artifacts/output.log`
+- `artifacts/queue.log`
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo_id = "SeongryongJung/Qwen3-8B-Material-RLSD-TR"
+tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    repo_id,
+    torch_dtype="auto",
+    device_map="auto",
+    trust_remote_code=True,
+)
+```
+
+## Source
+
+- Checkpoint: `checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8`
+- Root actor checkpoint: `checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor`
+- Last actor checkpoint: `checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor`
+- W&B run: `run-20260703_115716-skza3cpu`
+- Queue log: `artifacts/queue.log`
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}
--- a/artifacts/config.yaml
+++ b/artifacts/config.yaml
@@ -0,0 +1,855 @@
+_wandb:
+    value:
+        cli_version: 0.23.1
+        e:
+            azg2qxmiak2ylnqr4q4n3cc7haftd9et:
+                args:
+                    - --node-ip-address=198.19.44.212
+                    - --node-manager-port=35629
+                    - --object-store-name=/tmp/ray_q3g_material_rlsd_tr_Qwen3_8B/session_2026-07-03_11-55-04_189737_2422949/sockets/plasma_store
+                    - --raylet-name=/tmp/ray_q3g_material_rlsd_tr_Qwen3_8B/session_2026-07-03_11-55-04_189737_2422949/sockets/raylet
+                    - --redis-address=None
+                    - --metrics-agent-port=55789
+                    - --logging-rotate-bytes=536870912
+                    - --logging-rotate-backup-count=5
+                    - --runtime-env-agent-port=61532
+                    - --gcs-address=198.19.44.212:55686
+                    - --session-name=session_2026-07-03_11-55-04_189737_2422949
+                    - --temp-dir=/tmp/ray_q3g_material_rlsd_tr_Qwen3_8B
+                    - --webui=
+                    - --cluster-id=81543ca1842e927772f37cb2a1df16065e73a33232aeb5ad7428724d
+                    - --startup-token=32
+                    - --worker-launch-time-ms=1783079707597
+                    - --node-id=dc013e7f74ede0ec1b004db70316bfcf07665a545c9c51d93d21b3d1
+                    - --runtime-env-hash=963742433
+                codePath: .venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py
+                codePathLocal: .venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py
+                cpu_count: 64
+                cpu_count_logical: 128
+                cudaVersion: "13.0"
+                disk:
+                    /:
+                        total: "46086056050688"
+                        used: "30851393007616"
+                email: jungsr1116@cau.ac.kr
+                executable: /mnt/mole/SDPO/L2T/.venv/bin/python
+                git:
+                    commit: ee6a667700697069b93db636aa937f970c1fb57a
+                    remote: https://github.com/jungseongryong/L2T.git
+                gpu: NVIDIA H200
+                gpu_count: 8
+                gpu_nvidia:
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-c0451621-891c-7169-976d-71d81958db34
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-e2a29dfa-7dad-6cd7-fb05-79d0060f27f0
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-d69bb741-f2a7-a375-7f56-5c0d09d797b2
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-1bbbea1e-7541-3126-1bfc-51b43a67577e
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-6e0055af-452d-3f46-ce21-0c71e347a608
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-317fdb5b-b280-71d8-398e-a843ad897437
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-f19d8161-d2dd-49a1-dcb8-5c341b5e4514
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-961f5ebf-4bf8-6855-828b-c065af57b87c
+                host: mole-workspace-rw
+                memory:
+                    total: "2163980390400"
+                os: Linux-6.8.0-71-generic-x86_64-with-glibc2.36
+                program: /mnt/mole/SDPO/L2T/.venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py
+                python: CPython 3.12.13
+                root: /mnt/mole/SDPO/L2T
+                startedAt: "2026-07-03T11:57:16.977672Z"
+                writerId: azg2qxmiak2ylnqr4q4n3cc7haftd9et
+        m: []
+        python_version: 3.12.13
+        t:
+            "1":
+                - 1
+                - 11
+                - 30
+                - 41
+                - 49
+                - 50
+                - 51
+                - 71
+                - 95
+                - 98
+                - 105
+            "2":
+                - 1
+                - 11
+                - 30
+                - 41
+                - 49
+                - 50
+                - 51
+                - 71
+                - 95
+                - 98
+                - 105
+            "3":
+                - 2
+                - 13
+                - 16
+                - 61
+            "4": 3.12.13
+            "5": 0.23.1
+            "6": 4.57.1
+            "12": 0.23.1
+            "13": linux-x86_64
+actor_rollout_ref:
+    value:
+        actor:
+            _target_: verl.workers.config.FSDPActorConfig
+            calculate_entropy: false
+            calculate_sum_pi_squared: false
+            checkpoint:
+                _target_: verl.trainer.config.CheckpointConfig
+                async_save: false
+                load_contents:
+                    - model
+                    - optimizer
+                    - extra
+                save_contents:
+                    - model
+                    - optimizer
+                    - extra
+            clip_ratio: 0.2
+            clip_ratio_c: 3
+            clip_ratio_high: 0.28
+            clip_ratio_low: 0.2
+            data_loader_seed: 42
+            entropy_checkpointing: false
+            entropy_coeff: 0
+            entropy_from_logits_with_chunking: false
+            freeze_vision_tower: false
+            fsdp_config:
+                _target_: verl.workers.config.FSDPEngineConfig
+                dtype: bfloat16
+                entropy_checkpointing: false
+                entropy_from_logits_with_chunking: false
+                forward_only: false
+                forward_prefetch: false
+                fsdp_size: -1
+                full_determinism: false
+                model_dtype: fp32
+                offload_policy: false
+                optimizer_offload: false
+                param_offload: false
+                reshard_after_forward: true
+                seed: 42
+                strategy: fsdp
+                ulysses_sequence_parallel_size: 1
+                use_orig_params: false
+                use_torch_compile: true
+                wrap_policy:
+                    min_num_params: 0
+            grad_clip: 1
+            kl_loss_coef: 0.001
+            kl_loss_type: low_var_kl
+            loss_agg_mode: token-mean
+            loss_scale_factor: null
+            optim:
+                _target_: verl.workers.config.FSDPOptimizerConfig
+                betas:
+                    - 0.9
+                    - 0.999
+                clip_grad: 1
+                lr: 1e-06
+                lr_scheduler_type: constant
+                lr_warmup_steps: 10
+                lr_warmup_steps_ratio: 0
+                min_lr_ratio: 0
+                num_cycles: 0.5
+                optimizer: AdamW
+                optimizer_impl: torch.optim
+                override_optimizer_config: null
+                total_training_steps: 100
+                warmup_style: null
+                weight_decay: 0.01
+            policy_loss:
+                _target_: verl.workers.config.PolicyLossConfig
+                clip_cov_lb: 1
+                clip_cov_ratio: 0.0002
+                clip_cov_ub: 5
+                kl_cov_ratio: 0.0002
+                loss_mode: rlsd
+                ppo_kl_coef: 0.1
+            ppo_epochs: 1
+            ppo_max_token_len_per_gpu: 10240
+            ppo_micro_batch_size: null
+            ppo_micro_batch_size_per_gpu: 1
+            ppo_mini_batch_size: 8
+            profiler:
+                _target_: verl.utils.profiler.ProfilerConfig
+                all_ranks: false
+                enable: false
+                ranks: []
+                save_path: outputs/profile
+                tool: null
+                tool_config:
+                    npu:
+                        _target_: verl.utils.profiler.config.NPUToolConfig
+                        analysis: true
+                        contents: []
+                        discrete: false
+                        level: level0
+                    nsys:
+                        _target_: verl.utils.profiler.config.NsightToolConfig
+                        discrete: false
+                    torch:
+                        _target_: verl.utils.profiler.config.TorchProfilerToolConfig
+                        step_end: null
+                        step_start: 0
+                    torch_memory:
+                        _target_: verl.utils.profiler.config.TorchMemoryToolConfig
+                        stack_depth: 32
+                        trace_alloc_max_entries: 100000
+            rollout_n: 8
+            router_replay:
+                _target_: verl.workers.config.RouterReplayConfig
+                mode: disabled
+                record_file: null
+                replay_file: null
+            self_distillation:
+                _target_: verl.workers.config.SelfDistillationConfig
+                alpha: 0.5
+                distillation_add_tail: true
+                distillation_topk: 100
+                dont_reprompt_on_self_success: true
+                environment_feedback_only_without_solution: true
+                evolving_teacher:
+                    _target_: verl.workers.config.EvolvingTeacherConfig
+                    enable: false
+                    loss_weight: 0
+                    mask: all
+                feedback_template: |4-
+                    The following is feedback from your unsuccessful earlier attempt:
+
+                    {feedback_raw}
+                full_logit_distillation: true
+                include_environment_feedback: true
+                is_clip: 2
+                max_reprompt_len: 10240
+                remove_thinking_from_demonstration: false
+                reprompt_template: |-
+                    {prompt}{solution}{feedback}
+
+                    Correctly solve the original question.
+                reprompt_truncation: right
+                solution_template: |4-
+                    Correct solution:
+
+                    {successful_previous_attempt}
+                srpo_dynamic_weighting: false
+                srpo_dynamic_weighting_temperature: 1
+                success_reward_threshold: 0.5
+                teacher_regularization: trust-region
+                teacher_update_rate: 0.1
+                token_reweight_decay_steps: 0
+                token_reweight_eps_w: 0.2
+                token_reweight_lambda: 0.5
+            shuffle: false
+            strategy: fsdp
+            sum_pi_squared_checkpointing: false
+            tau_neg: 1.05
+            tau_pos: 1
+            ulysses_sequence_parallel_size: 1
+            use_dynamic_bsz: false
+            use_fused_kernels: false
+            use_kl_loss: false
+            use_prefix_grouper: false
+            use_remove_padding: true
+            use_torch_compile: true
+        hybrid_engine: true
+        model:
+            _target_: verl.workers.config.HFModelConfig
+            custom_chat_template: null
+            enable_activation_offload: false
+            enable_gradient_checkpointing: true
+            exclude_modules: null
+            external_lib: null
+            fused_kernel_options:
+                impl_backend: torch
+            hf_config_path: null
+            lora_adapter_path: null
+            lora_alpha: 16
+            lora_rank: 0
+            path: Qwen/Qwen3-8B
+            target_modules: all-linear
+            tiled_mlp:
+                enabled: false
+                num_shards: 4
+            tokenizer_path: null
+            trust_remote_code: true
+            use_fused_kernels: false
+            use_liger: false
+            use_remove_padding: true
+            use_shm: false
+        nccl_timeout: 600
+        ref:
+            _target_: verl.workers.config.FSDPActorConfig
+            entropy_checkpointing: false
+            entropy_from_logits_with_chunking: false
+            fsdp_config:
+                _target_: verl.workers.config.FSDPEngineConfig
+                dtype: bfloat16
+                entropy_checkpointing: false
+                entropy_from_logits_with_chunking: false
+                forward_only: true
+                forward_prefetch: false
+                fsdp_size: -1
+                full_determinism: false
+                model_dtype: fp32
+                offload_policy: false
+                optimizer_offload: false
+                param_offload: false
+                reshard_after_forward: true
+                seed: 42
+                strategy: fsdp
+                ulysses_sequence_parallel_size: 1
+                use_orig_params: false
+                use_torch_compile: true
+                wrap_policy:
+                    min_num_params: 0
+            log_prob_max_token_len_per_gpu: 10240
+            log_prob_micro_batch_size: null
+            log_prob_micro_batch_size_per_gpu: 1
+            log_prob_use_dynamic_bsz: false
+            profiler:
+                _target_: verl.utils.profiler.ProfilerConfig
+                all_ranks: false
+                enable: false
+                ranks: []
+                save_path: outputs/profile
+                tool: null
+                tool_config:
+                    npu:
+                        _target_: verl.utils.profiler.config.NPUToolConfig
+                        analysis: true
+                        contents: []
+                        discrete: false
+                        level: level0
+                    nsys:
+                        _target_: verl.utils.profiler.config.NsightToolConfig
+                        discrete: false
+                    torch:
+                        _target_: verl.utils.profiler.config.TorchProfilerToolConfig
+                        step_end: null
+                        step_start: 0
+                    torch_memory:
+                        _target_: verl.utils.profiler.config.TorchMemoryToolConfig
+                        stack_depth: 32
+                        trace_alloc_max_entries: 100000
+            rollout_n: 8
+            router_replay:
+                _target_: verl.workers.config.RouterReplayConfig
+                mode: disabled
+                record_file: null
+                replay_file: null
+            strategy: fsdp
+            ulysses_sequence_parallel_size: 1
+            use_torch_compile: true
+        rollout:
+            _target_: verl.workers.config.RolloutConfig
+            agent:
+                _target_: verl.workers.config.AgentLoopConfig
+                agent_loop_config_path: null
+                custom_async_server:
+                    _target_: verl.workers.config.CustomAsyncServerConfig
+                    name: null
+                    path: null
+                default_agent_loop: single_turn_agent
+                num_workers: 8
+            calculate_log_probs: true
+            cudagraph_capture_sizes: null
+            data_parallel_size: 1
+            disable_log_stats: true
+            do_sample: true
+            dtype: bfloat16
+            enable_chunked_prefill: true
+            enable_prefix_caching: true
+            enable_rollout_routing_replay: false
+            enforce_eager: false
+            expert_parallel_size: 1
+            free_cache_engine: true
+            gpu_memory_utilization: 0.8
+            ignore_eos: false
+            layered_summon: false
+            load_format: dummy
+            log_prob_max_token_len_per_gpu: 10240
+            log_prob_micro_batch_size: null
+            log_prob_micro_batch_size_per_gpu: 1
+            log_prob_use_dynamic_bsz: false
+            logprobs_mode: processed_logprobs
+            max_model_len: 10240
+            max_num_batched_tokens: 10240
+            max_num_seqs: 1024
+            mode: async
+            multi_stage_wake_up: false
+            multi_turn:
+                _target_: verl.workers.config.MultiTurnConfig
+                enable: false
+                format: hermes
+                interaction_config_path: null
+                max_assistant_turns: null
+                max_parallel_calls: 1
+                max_tool_response_length: 256
+                max_user_turns: null
+                num_repeat_rollouts: null
+                tokenization_sanity_check_mode: strict
+                tool_config_path: null
+                tool_response_truncate_side: middle
+                use_inference_chat_template: false
+            "n": 8
+            name: vllm
+            over_sample_rate: 0
+            pipeline_model_parallel_size: 1
+            profiler:
+                _target_: verl.utils.profiler.ProfilerConfig
+                all_ranks: false
+                enable: false
+                ranks: []
+                save_path: outputs/profile
+                tool: null
+                tool_config:
+                    npu:
+                        _target_: verl.utils.profiler.config.NPUToolConfig
+                        analysis: true
+                        contents: []
+                        discrete: false
+                        level: level0
+                    nsys:
+                        _target_: verl.utils.profiler.config.NsightToolConfig
+                        discrete: false
+                    torch:
+                        _target_: verl.utils.profiler.config.TorchProfilerToolConfig
+                        step_end: null
+                        step_start: 0
+                    torch_memory:
+                        _target_: verl.utils.profiler.config.TorchMemoryToolConfig
+                        stack_depth: 32
+                        trace_alloc_max_entries: 100000
+            prometheus:
+                _target_: verl.workers.config.PrometheusConfig
+                enable: false
+                file: /tmp/ray/session_latest/metrics/prometheus/prometheus.yml
+                port: 9090
+                served_model_name: Qwen/Qwen3-8B
+            prompt_length: 2048
+            quantization: null
+            quantization_config_file: null
+            response_length: 8192
+            scheduling_policy: fcfs
+            skip_dump_dir: /tmp/rollout_dump
+            skip_rollout: false
+            skip_tokenizer_init: true
+            temperature: 1
+            tensor_model_parallel_size: 2
+            top_k: -1
+            top_p: 1
+            trace:
+                _target_: verl.workers.config.TraceConfig
+                backend: null
+                max_samples_per_step_per_worker: null
+                token2text: false
+            update_weights_bucket_megabytes: 512
+            val_kwargs:
+                _target_: verl.workers.config.SamplingConfig
+                do_sample: true
+                "n": 16
+                temperature: 0.6
+                top_k: -1
+                top_p: 0.95
+algorithm:
+    value:
+        _target_: verl.trainer.config.AlgoConfig
+        adv_estimator: grpo
+        gamma: 1
+        kl_ctrl:
+            _target_: verl.trainer.config.KLControlConfig
+            horizon: 10000
+            kl_coef: 0.001
+            target_kl: 0.1
+            type: fixed
+        kl_penalty: kl
+        lam: 1
+        norm_adv_by_std_in_grpo: false
+        pf_ppo:
+            reweight_method: pow
+            weight_pow: 2
+        rollout_correction:
+            bypass_mode: false
+            loss_type: ppo_clip
+            rollout_is: token
+            rollout_is_batch_normalize: false
+            rollout_is_threshold: 2
+            rollout_rs: null
+            rollout_rs_threshold: null
+        use_kl_in_reward: false
+        use_pf_ppo: false
+critic:
+    value:
+        _target_: verl.workers.config.FSDPCriticConfig
+        checkpoint:
+            _target_: verl.trainer.config.CheckpointConfig
+            async_save: false
+            load_contents:
+                - model
+                - optimizer
+                - extra
+            save_contents:
+                - model
+                - optimizer
+                - extra
+        cliprange_value: 0.5
+        data_loader_seed: 42
+        enable: null
+        forward_max_token_len_per_gpu: 32768
+        forward_micro_batch_size: null
+        forward_micro_batch_size_per_gpu: null
+        grad_clip: 1
+        loss_agg_mode: token-mean
+        model:
+            _target_: verl.workers.config.FSDPCriticModelCfg
+            enable_activation_offload: false
+            enable_gradient_checkpointing: true
+            external_lib: null
+            fsdp_config:
+                _target_: verl.workers.config.FSDPEngineConfig
+                dtype: bfloat16
+                entropy_checkpointing: false
+                entropy_from_logits_with_chunking: false
+                forward_only: false
+                forward_prefetch: false
+                fsdp_size: -1
+                full_determinism: false
+                model_dtype: fp32
+                offload_policy: false
+                optimizer_offload: false
+                param_offload: false
+                reshard_after_forward: true
+                seed: 42
+                strategy: fsdp
+                ulysses_sequence_parallel_size: 1
+                use_orig_params: false
+                use_torch_compile: true
+                wrap_policy:
+                    min_num_params: 0
+            lora_alpha: 16
+            lora_rank: 0
+            path: Qwen/Qwen3-8B
+            target_modules: all-linear
+            tiled_mlp:
+                enabled: false
+                num_shards: 4
+            tokenizer_path: Qwen/Qwen3-8B
+            trust_remote_code: true
+            use_remove_padding: false
+            use_shm: false
+        optim:
+            _target_: verl.workers.config.FSDPOptimizerConfig
+            betas:
+                - 0.9
+                - 0.999
+            clip_grad: 1
+            lr: 1e-05
+            lr_scheduler_type: constant
+            lr_warmup_steps: -1
+            lr_warmup_steps_ratio: 0
+            min_lr_ratio: 0
+            num_cycles: 0.5
+            optimizer: AdamW
+            optimizer_impl: torch.optim
+            override_optimizer_config: null
+            total_training_steps: 100
+            warmup_style: null
+            weight_decay: 0.01
+        ppo_epochs: 1
+        ppo_max_token_len_per_gpu: 32768
+        ppo_micro_batch_size: null
+        ppo_micro_batch_size_per_gpu: null
+        ppo_mini_batch_size: 8
+        profiler:
+            _target_: verl.utils.profiler.ProfilerConfig
+            all_ranks: false
+            enable: false
+            ranks: []
+            save_path: outputs/profile
+            tool: null
+            tool_config:
+                npu:
+                    _target_: verl.utils.profiler.config.NPUToolConfig
+                    analysis: true
+                    contents: []
+                    discrete: false
+                    level: level0
+                nsys:
+                    _target_: verl.utils.profiler.config.NsightToolConfig
+                    discrete: false
+                torch:
+                    _target_: verl.utils.profiler.config.TorchProfilerToolConfig
+                    step_end: null
+                    step_start: 0
+                torch_memory:
+                    _target_: verl.utils.profiler.config.TorchMemoryToolConfig
+                    stack_depth: 32
+                    trace_alloc_max_entries: 100000
+        rollout_n: 8
+        shuffle: false
+        strategy: fsdp
+        ulysses_sequence_parallel_size: 1
+        use_dynamic_bsz: false
+custom_reward_function:
+    value:
+        name: compute_score
+        path: /mnt/mole/SDPO/L2T/verl/utils/reward_score/feedback/__init__.py
+data:
+    value:
+        apply_chat_template_kwargs:
+            enable_thinking: false
+        custom_cls:
+            name: null
+            path: null
+        datagen:
+            name: null
+            path: null
+        dataloader_num_workers: 8
+        filter_overlong_prompts: true
+        filter_overlong_prompts_workers: 1
+        image_key: images
+        image_patch_size: 14
+        max_prompt_length: 2048
+        max_response_length: 8192
+        prompt_key: prompt
+        return_full_prompt: false
+        return_multi_modal_inputs: true
+        return_raw_chat: true
+        return_raw_input_ids: false
+        reward_fn_key: data_source
+        sampler:
+            class_name: null
+            class_path: null
+        seed: null
+        shuffle: true
+        tokenizer: null
+        tool_config_path: null
+        train_batch_size: 32
+        train_files:
+            - /mnt/mole/SDPO/L2T/datasets/sciknoweval/material/train.parquet
+        train_max_samples: 3200
+        truncation: error
+        trust_remote_code: true
+        use_shm: false
+        val_batch_size: null
+        val_files:
+            - /mnt/mole/SDPO/L2T/datasets/sciknoweval/material/test.parquet
+        val_max_samples: -1
+        validation_shuffle: false
+        video_key: videos
+global_profiler:
+    value:
+        _target_: verl.utils.profiler.ProfilerConfig
+        global_tool_config:
+            nsys:
+                _target_: verl.utils.profiler.config.NsightToolConfig
+                controller_nsight_options:
+                    cuda-graph-trace: graph
+                    cuda-memory-usage: "true"
+                    trace: cuda,nvtx,cublas,ucx
+                discrete: false
+                worker_nsight_options:
+                    capture-range: cudaProfilerApi
+                    capture-range-end: null
+                    cuda-graph-trace: graph
+                    cuda-memory-usage: "true"
+                    kill: none
+                    trace: cuda,nvtx,cublas,ucx
+            torch_memory:
+                context: all
+                stack_depth: 32
+                stacks: all
+                trace_alloc_max_entries: 100000
+        profile_continuous_steps: false
+        save_path: outputs/profile
+        steps: null
+        tool: null
+max_model_len:
+    value: 10240
+ray_kwargs:
+    value:
+        ray_init:
+            _temp_dir: /tmp/ray_q3g_material_rlsd_tr_Qwen3_8B
+            include_dashboard: false
+            num_cpus: null
+            runtime_env:
+                env_vars:
+                    EXPERIMENT: qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8
+                    TASK: datasets/sciknoweval/material
+                    USER: root
+        timeline_json_file: null
+reward_manager:
+    value:
+        _target_: verl.trainer.config.config.RewardManagerConfig
+        module:
+            _target_: verl.trainer.config.config.ModuleConfig
+            name: custom_reward_manager
+            path: null
+        name: naive
+        source: register
+reward_model:
+    value:
+        enable: false
+        enable_resource_pool: false
+        forward_max_token_len_per_gpu: 32768
+        launch_reward_fn_async: false
+        max_length: null
+        micro_batch_size: null
+        micro_batch_size_per_gpu: null
+        model:
+            external_lib: null
+            fsdp_config:
+                _target_: verl.workers.config.FSDPEngineConfig
+                forward_prefetch: false
+                fsdp_size: -1
+                param_offload: false
+                reshard_after_forward: true
+                wrap_policy:
+                    min_num_params: 0
+            input_tokenizer: Qwen/Qwen3-8B
+            path: ~/models/FsfairX-LLaMA3-RM-v0.1
+            trust_remote_code: false
+            use_fused_kernels: false
+            use_remove_padding: false
+            use_shm: false
+        n_gpus_per_node: 8
+        nnodes: 0
+        num_workers: 1
+        profiler:
+            _target_: verl.utils.profiler.ProfilerConfig
+            all_ranks: false
+            enable: false
+            ranks: []
+            save_path: outputs/profile
+            tool: null
+            tool_config:
+                npu:
+                    _target_: verl.utils.profiler.config.NPUToolConfig
+                    analysis: true
+                    contents: []
+                    discrete: false
+                    level: level0
+                nsys:
+                    _target_: verl.utils.profiler.config.NsightToolConfig
+                    discrete: false
+                torch:
+                    _target_: verl.utils.profiler.config.TorchProfilerToolConfig
+                    step_end: null
+                    step_start: 0
+                torch_memory:
+                    _target_: verl.utils.profiler.config.TorchMemoryToolConfig
+                    stack_depth: 32
+                    trace_alloc_max_entries: 100000
+        reward_loop_class_name: null
+        reward_loop_module_path: null
+        reward_loop_source: register
+        reward_manager: naive
+        rollout:
+            _target_: verl.workers.config.RolloutConfig
+            cudagraph_capture_sizes: null
+            data_parallel_size: 1
+            disable_log_stats: true
+            dtype: bfloat16
+            enable_chunked_prefill: true
+            enable_prefix_caching: true
+            enforce_eager: true
+            expert_parallel_size: 1
+            free_cache_engine: true
+            gpu_memory_utilization: 0.5
+            limit_images: null
+            load_format: auto
+            max_model_len: null
+            max_num_batched_tokens: 8192
+            max_num_seqs: 1024
+            name: ???
+            prompt_length: 2048
+            response_length: 2048
+            skip_tokenizer_init: false
+            tensor_model_parallel_size: 2
+        sandbox_fusion:
+            max_concurrent: 64
+            memory_limit_mb: 1024
+            url: null
+        strategy: fsdp
+        ulysses_sequence_parallel_size: 1
+        use_dynamic_bsz: false
+        use_reward_loop: false
+trainer:
+    value:
+        balance_batch: true
+        critic_warmup: 0
+        default_hdfs_dir: null
+        default_local_dir: /mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8
+        del_local_ckpt_after_load: false
+        device: cuda
+        esi_redundant_time: 0
+        experiment_name: qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8
+        group_name: QWEN3-RLSD-TR-GRPO-matched-generalization
+        log_val_generations: 0
+        logger:
+            - console
+            - wandb
+        max_actor_ckpt_to_keep: 100
+        max_critic_ckpt_to_keep: null
+        n_gpus_per_node: 8
+        nnodes: 1
+        project_name: SDPO-root
+        ray_wait_register_center_timeout: 300
+        resume_from_path: null
+        resume_mode: auto
+        rollout_data_dir: null
+        save_freq: 10
+        test_freq: 10
+        total_epochs: 30
+        total_training_steps: 100
+        use_legacy_worker_impl: auto
+        val_before_train: false
+        val_only: false
+        validation_data_dir: null
+transfer_queue:
+    value:
+        enable: false
+vars:
+    value:
+        ckpt_dir: /capstor/scratch/cscs/root/ttrl_runs/datasets/sciknoweval/material
+        dir: /users/root/SDPO
+        log_dir: /users/root/output
+        task: datasets/sciknoweval/material
--- a/artifacts/output.log
+++ b/artifacts/output.log
--- a/artifacts/queue.log
+++ b/artifacts/queue.log
--- a/artifacts/requirements.txt
+++ b/artifacts/requirements.txt
@@ -0,0 +1,286 @@
+colorama==0.4.6
+psutil==7.1.3
+wheel==0.47.0
+pip==26.1.2
+mpmath==1.3.0
+typing_extensions==4.15.0
+pillow==12.2.0
+nvidia-cuda-runtime-cu12==12.8.90
+nvidia-cuda-nvrtc-cu12==12.8.93
+nvidia-cusparse-cu12==12.5.8.93
+nvidia-cufft-cu12==11.3.3.83
+nvidia-cuda-cupti-cu12==12.8.90
+nvidia-cublas-cu12==12.8.4.1
+llguidance==1.3.0
+anthropic==0.71.0
+nodeenv==1.10.0
+networkx==3.6.1
+MarkupSafe==3.0.3
+filelock==3.29.0
+nvidia-cudnn-cu12==9.10.2.21
+transformers==4.57.1
+Jinja2==3.1.6
+nvidia-cusolver-cu12==11.7.3.90
+torch==2.9.0
+rich-toolkit==0.20.1
+z3-solver==4.15.4.0
+word2number==1.1
+pytz==2026.2
+pylatexenc==2.10
+py-spy==0.4.2
+opencensus-context==0.1.3
+distlib==0.4.3
+colorful==0.5.8
+antlr4-python3-runtime==4.9.3
+zipp==4.1.0
+xxhash==3.7.0
+wrapt==2.2.1
+Werkzeug==3.1.8
+urllib3==2.7.0
+tzdata==2026.2
+typing-inspection==0.4.2
+tqdm==4.68.2
+tensorboard-data-server==0.7.2
+smmap==5.0.3
+six==1.17.0
+safetensors==0.8.0
+rpds-py==2026.5.1
+regex==2026.5.9
+pyzmq==27.1.0
+PyYAML==6.0.3
+Pygments==2.20.0
+pydantic_core==2.46.4
+pycparser==3.0
+pybind11==3.0.1
+pyasn1==0.6.3
+pyarrow==22.0.0
+psutil==7.1.3
+protobuf==6.33.6
+propcache==0.5.2
+prometheus_client==0.25.0
+pluggy==1.6.0
+platformdirs==4.10.0
+httpcore==1.0.9
+packaging==25.0
+orjson==3.11.9
+opentelemetry-api==1.42.1
+numpy==2.1.0
+multidict==6.7.1
+msgpack==1.2.0
+Markdown==3.10.2
+iniconfig==2.3.0
+idna==3.18
+identify==2.6.19
+hf-xet==1.5.1
+h11==0.16.0
+grpcio==1.81.1
+gitdb==4.0.12
+fsspec==2025.10.0
+frozenlist==1.8.0
+dill==0.4.0
+codetiming==1.4.0
+cloudpickle==3.1.2
+click==8.4.1
+charset-normalizer==3.4.7
+cfgv==3.5.0
+certifi==2026.5.20
+attrs==26.1.0
+annotated-types==0.7.0
+annotated-doc==0.0.4
+aiohappyeyeballs==2.6.2
+absl-py==2.4.0
+yarl==1.24.2
+uvicorn==0.40.0
+tensorboard==2.20.0
+smart_open==7.6.1
+sentry-sdk==2.62.0
+requests==2.34.2
+referencing==0.37.0
+pyvers==0.1.0
+python-discovery==1.4.2
+python-dateutil==2.9.0.post0
+pytest==9.1.0
+pydantic==2.13.4
+pyasn1_modules==0.4.2
+proto-plus==1.28.0
+nvidia-nvjitlink-cu12==12.8.93
+nvidia-curand-cu12==10.3.9.90
+omegaconf==2.3.1
+multiprocess==0.70.18
+latex2sympy2_extended==1.10.2
+latex2sympy2==1.5.4
+googleapis-common-protos==1.75.0
+cffi==2.0.0
+anyio==4.13.0
+aiosignal==1.4.0
+virtualenv==21.5.0
+starlette==0.50.0
+pytest-rerunfailures==16.3
+pytest-asyncio==1.4.0
+pandas==2.3.3
+nvidia-nccl-cu12==2.27.5
+math-verify==0.8.0
+jsonschema-specifications==2025.9.1
+hydra-core==1.3.2
+huggingface_hub==0.36.2
+httpx==0.28.1
+GitPython==3.1.50
+cryptography==49.0.0
+aiohttp==3.14.1
+wandb==0.23.1
+torchdata==0.11.0
+numba==0.61.2
+tensordict==0.10.0
+pre_commit==4.6.0
+liger_kernel==0.8.0
+jsonschema==4.26.0
+google-auth==2.54.0
+fastapi==0.127.0
+aiohttp-cors==0.8.1
+accelerate==1.12.0
+llvmlite==0.44.0
+google-api-core==2.29.0
+datasets==4.4.2
+peft==0.18.0
+opencensus==0.11.4
+verl==0.7.0.dev0
+einops==0.8.2
+py-cpuinfo==9.0.0
+nvidia-cusparselt-cu12==0.7.1
+websockets==16.0
+uvloop==0.22.1
+sniffio==1.3.1
+shellingham==1.5.4
+sentencepiece==0.2.1
+scipy==1.17.1
+rignore==0.7.6
+python-multipart==0.0.32
+python-json-logger==4.1.0
+python-dotenv==1.2.2
+pycountry==26.2.16
+partial-json-parser==0.2.1.1.post7
+opentelemetry-semantic-conventions-ai==0.4.13
+opencv-python-headless==4.13.0.92
+ninja==1.13.0
+nest-asyncio==1.6.0
+msgspec==0.21.1
+mdurl==0.1.2
+lark==1.2.2
+jiter==0.15.0
+interegular==0.3.3
+importlib_metadata==8.0.0
+httptools==0.8.0
+fastar==0.11.0
+dnspython==2.8.0
+distro==1.9.0
+diskcache==5.6.3
+detect-installer==0.1.0
+Deprecated==1.3.1
+cuda-pathfinder==1.5.5
+cachetools==7.1.4
+blake3==1.0.8
+astor==0.8.1
+airportsdata==20260315
+watchfiles==1.2.0
+tiktoken==0.13.0
+tilelang==0.1.9
+markdown-it-py==4.2.0
+gguf==0.19.0
+email-validator==2.3.0
+cuda-tile==1.3.0
+cupy-cuda12x==14.1.1
+nvidia-ml-py==13.610.43
+rich==15.0.0
+pydantic-settings==2.14.1
+pydantic-extra-types==2.11.1
+prometheus-fastapi-instrumentator==7.1.0
+supervisor==4.3.0
+tokenspeed-mla==0.1.2
+outlines_core==0.2.11
+typer==0.26.7
+quack-kernels==0.5.0
+nvidia-nvvm==13.2.78
+torch_c_dlpack_ext==0.1.5
+mistral_common==1.11.3
+fastapi-cloud-cli==0.20.0
+fastapi-cli==0.0.24
+cuda-toolkit==13.0.2
+tabulate==0.10.0
+sympy==1.14.0
+setuptools==79.0.1
+pybase64==1.4.3
+nvidia-cufile-cu12==1.13.1.3
+humming-kernels==0.1.4
+setproctitle==1.3.7
+triton==3.5.0
+nvidia-nvtx-cu12==12.8.90
+nvidia-cusparselt-cu13==0.8.0
+tokenspeed-triton==3.7.10.post20260531
+PyJWT==2.13.0
+pyelftools==0.33
+nvidia-nvshmem-cu12==3.3.20
+nvidia-nvtx==13.0.85
+nvidia-nvshmem-cu13==3.4.5
+nvidia-nvjitlink==13.0.88
+nvidia-nccl-cu13==2.28.9
+nvidia-curand==10.4.0.35
+nvidia-cufile==1.15.1.6
+nvidia-cudnn-frontend==1.25.0
+nvidia-cuda-runtime==13.0.96
+nvidia-cuda-nvrtc==13.0.88
+nvidia-cuda-cupti==13.0.85
+nvidia-cuda-crt==13.3.33
+nvidia-cuda-cccl==13.3.3.3.1
+nvidia-cublas==13.1.0.3
+ml_dtypes==0.5.4
+loguru==0.7.3
+jmespath==1.1.0
+ijson==3.5.0
+httpx-sse==0.4.3
+docstring_parser==0.18.0
+depyf==0.20.0
+cuda-core==1.0.1
+cuda-bindings==13.3.1
+cbor2==6.1.2
+apache-tvm-ffi==0.1.9
+mcp==1.27.2
+opentelemetry-semantic-conventions==0.63b1
+opentelemetry-proto==1.42.1
+nvidia-cusparse==12.6.3.3
+nvidia-cufft==12.0.0.61
+nvidia-cudnn-cu13==9.19.0.56
+nvidia-cuda-nvcc==13.2.78
+cuda-python==13.3.1
+fastsafetensors==0.3.2
+tokenizers==0.22.2
+sse-starlette==3.4.4
+opentelemetry-sdk==1.42.1
+nvidia-cutlass-dsl==4.5.2
+opentelemetry-exporter-otlp-proto-common==1.42.1
+openai-harmony==0.0.8
+openai==2.41.1
+nvidia-cutlass-dsl-libs-base==4.5.2
+nvidia-cusolver==12.0.4.66
+nvidia-cuda-tileiras==13.2.78
+nvidia-cutlass-dsl-libs-cu13==4.5.2
+lm-format-enforcer==0.11.3
+ray==2.53.0
+model-hosting-container-standards==0.1.15
+opentelemetry-exporter-otlp-proto-http==1.42.1
+opentelemetry-exporter-otlp-proto-grpc==1.42.1
+opentelemetry-exporter-otlp==1.42.1
+opentelemetry-exporter-prometheus==0.63b1
+xgrammar==0.1.27
+torchvision==0.24.0
+torchaudio==2.9.0
+flashinfer-python==0.5.3
+compressed-tensors==0.12.2
+vllm==0.12.0
+flash_attn==2.8.3
+flashinfer-cubin==0.5.3
+pyparsing==3.3.2
+kiwisolver==1.5.0
+fonttools==4.63.0
+cycler==0.12.1
+contourpy==1.3.3
+matplotlib==3.11.0
--- a/artifacts/wandb-metadata.json
+++ b/artifacts/wandb-metadata.json
@@ -0,0 +1,109 @@
+{
+  "os":  "Linux-6.8.0-71-generic-x86_64-with-glibc2.36",
+  "python":  "CPython 3.12.13",
+  "startedAt":  "2026-07-03T11:57:16.977672Z",
+  "args":  [
+    "--node-ip-address=198.19.44.212",
+    "--node-manager-port=35629",
+    "--object-store-name=/tmp/ray_q3g_material_rlsd_tr_Qwen3_8B/session_2026-07-03_11-55-04_189737_2422949/sockets/plasma_store",
+    "--raylet-name=/tmp/ray_q3g_material_rlsd_tr_Qwen3_8B/session_2026-07-03_11-55-04_189737_2422949/sockets/raylet",
+    "--redis-address=None",
+    "--metrics-agent-port=55789",
+    "--logging-rotate-bytes=536870912",
+    "--logging-rotate-backup-count=5",
+    "--runtime-env-agent-port=61532",
+    "--gcs-address=198.19.44.212:55686",
+    "--session-name=session_2026-07-03_11-55-04_189737_2422949",
+    "--temp-dir=/tmp/ray_q3g_material_rlsd_tr_Qwen3_8B",
+    "--webui=",
+    "--cluster-id=81543ca1842e927772f37cb2a1df16065e73a33232aeb5ad7428724d",
+    "--startup-token=32",
+    "--worker-launch-time-ms=1783079707597",
+    "--node-id=dc013e7f74ede0ec1b004db70316bfcf07665a545c9c51d93d21b3d1",
+    "--runtime-env-hash=963742433"
+  ],
+  "program":  "/mnt/mole/SDPO/L2T/.venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py",
+  "codePath":  ".venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py",
+  "codePathLocal":  ".venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py",
+  "git":  {
+    "remote":  "https://github.com/jungseongryong/L2T.git",
+    "commit":  "ee6a667700697069b93db636aa937f970c1fb57a"
+  },
+  "email":  "jungsr1116@cau.ac.kr",
+  "root":  "/mnt/mole/SDPO/L2T",
+  "host":  "mole-workspace-rw",
+  "executable":  "/mnt/mole/SDPO/L2T/.venv/bin/python",
+  "cpu_count":  64,
+  "cpu_count_logical":  128,
+  "gpu":  "NVIDIA H200",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "46086056050688",
+      "used":  "30851393007616"
+    }
+  },
+  "memory":  {
+    "total":  "2163980390400"
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA H200",
+      "memoryTotal":  "150754820096",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-c0451621-891c-7169-976d-71d81958db34"
+    },
+    {
+      "name":  "NVIDIA H200",
+      "memoryTotal":  "150754820096",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-e2a29dfa-7dad-6cd7-fb05-79d0060f27f0"
+    },
+    {
+      "name":  "NVIDIA H200",
+      "memoryTotal":  "150754820096",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-d69bb741-f2a7-a375-7f56-5c0d09d797b2"
+    },
+    {
+      "name":  "NVIDIA H200",
+      "memoryTotal":  "150754820096",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-1bbbea1e-7541-3126-1bfc-51b43a67577e"
+    },
+    {
+      "name":  "NVIDIA H200",
+      "memoryTotal":  "150754820096",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-6e0055af-452d-3f46-ce21-0c71e347a608"
+    },
+    {
+      "name":  "NVIDIA H200",
+      "memoryTotal":  "150754820096",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-317fdb5b-b280-71d8-398e-a843ad897437"
+    },
+    {
+      "name":  "NVIDIA H200",
+      "memoryTotal":  "150754820096",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-f19d8161-d2dd-49a1-dcb8-5c341b5e4514"
+    },
+    {
+      "name":  "NVIDIA H200",
+      "memoryTotal":  "150754820096",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-961f5ebf-4bf8-6855-828b-c065af57b87c"
+    }
+  ],
+  "cudaVersion":  "13.0",
+  "writerId":  "azg2qxmiak2ylnqr4q4n3cc7haftd9et"
+}
--- a/artifacts/wandb-summary.json
+++ b/artifacts/wandb-summary.json
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
--- a/checkpoints/last/added_tokens.json
+++ b/checkpoints/last/added_tokens.json
@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}
--- a/checkpoints/last/chat_template.jinja
+++ b/checkpoints/last/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
--- a/checkpoints/last/config.json
+++ b/checkpoints/last/config.json
@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/checkpoints/last/generation_config.json
+++ b/checkpoints/last/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}
--- a/checkpoints/last/merges.txt
+++ b/checkpoints/last/merges.txt
--- a/checkpoints/last/model-00001-of-00004.safetensors
+++ b/checkpoints/last/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7f131cdf734d0c417367f4838e94b79e7d93fb361981108eb84ec03f2bfdb0
+size 4986142768
--- a/checkpoints/last/model-00002-of-00004.safetensors
+++ b/checkpoints/last/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:209dd659a0c0f94baf92a8340fa97d273fe8cf1928665267c681311143519af6
+size 4991493984
--- a/checkpoints/last/model-00003-of-00004.safetensors
+++ b/checkpoints/last/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780ca76971b625a038ea2d022e806cc9373bf9b0d77c72b55ebcc66dc71e3bdb
+size 4944233784
--- a/checkpoints/last/model-00004-of-00004.safetensors
+++ b/checkpoints/last/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ffb0cfd649006827d920c610be131987b119ba54d3f95867f1d93958f85653
+size 1459646240
--- a/checkpoints/last/model.safetensors.index.json
+++ b/checkpoints/last/model.safetensors.index.json
@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}
--- a/checkpoints/last/special_tokens_map.json
+++ b/checkpoints/last/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/checkpoints/last/tokenizer.json
+++ b/checkpoints/last/tokenizer.json
--- a/checkpoints/last/tokenizer_config.json
+++ b/checkpoints/last/tokenizer_config.json
@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/checkpoints/last/vocab.json
+++ b/checkpoints/last/vocab.json
--- a/config.json
+++ b/config.json
@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}
--- a/merges.txt
+++ b/merges.txt
--- a/model-00001-of-00004.safetensors
+++ b/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7f131cdf734d0c417367f4838e94b79e7d93fb361981108eb84ec03f2bfdb0
+size 4986142768
--- a/model-00002-of-00004.safetensors
+++ b/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:209dd659a0c0f94baf92a8340fa97d273fe8cf1928665267c681311143519af6
+size 4991493984
--- a/model-00003-of-00004.safetensors
+++ b/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780ca76971b625a038ea2d022e806cc9373bf9b0d77c72b55ebcc66dc71e3bdb
+size 4944233784
--- a/model-00004-of-00004.safetensors
+++ b/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94ffb0cfd649006827d920c610be131987b119ba54d3f95867f1d93958f85653
+size 1459646240
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}
--- a/results/hyperparameters.csv
+++ b/results/hyperparameters.csv
@@ -0,0 +1,38 @@
+section,parameter,value,source
+Run identity,Base model,Qwen/Qwen3-8B,queue/script override
+Run identity,Dataset,Material / SciKnowEval material,run_qwen3_generalization.sh
+Run identity,Method,RLSD_TR,run_qwen3_generalization.sh
+Run identity,Config,rlsd,run_qwen3_generalization.sh
+Run identity,Experiment,qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8,run_qwen3_generalization.sh
+Run identity,W&B run,run-20260703_115716-skza3cpu,wandb
+Data,Train file,datasets/sciknoweval/material/train.parquet,script override
+Data,Validation file,datasets/sciknoweval/material/test.parquet,script override
+Data,Train batch size,32,queue/script override
+Data,Train max samples,3200,queue/script override
+Schedule,Total training steps,100,queue/script override
+Schedule,Validation before train,False,queue/script override
+Schedule,Save frequency,10,queue/script override
+Schedule,Validation frequency,10,queue/script override
+Sequence,Max prompt length,2048,queue/script override
+Sequence,Max response length,8192,queue/script override
+Sequence,Max model length,10240,queue/script override
+Rollout,Train rollout n,8,queue/script override
+Rollout,Validation rollout n,16,queue/script override
+Rollout,vLLM GPU memory utilization,0.8,queue/script override
+Optimization,Learning rate,1e-6,RLSD_TR method override
+Optimization,Weight decay,0.01,script override
+PPO/GRPO,PPO mini batch size,8,queue/script override
+PPO/GRPO,Normalize GRPO advantages by std,False,baseline_grpo.yaml / script override
+Rollout correction,Importance sampling mode,token,script override
+Rollout correction,IS threshold,2.0,script override
+Checkpoint/Logging,Checkpoint root,checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8,script override
+Checkpoint/Logging,Latest checkpointed iteration,100,latest_checkpointed_iteration.txt
+Checkpoint/Logging,External actor archive,checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/_actor_archive,preserve_actor_checkpoints.py
+Checkpoint/Logging,Logger,"console, wandb",ppo_trainer.yaml
+RLSD_TR,Policy loss mode,rlsd,method override
+RLSD_TR,Teacher regularization,trust-region,method override
+RLSD_TR,Trust-region mix / teacher update rate,0.1,queue/script override
+RLSD_TR,Token reweight lambda,0.5,queue/script override
+RLSD_TR,Token reweight eps_w,0.2,queue/script override
+RLSD_TR,Token reweight decay steps,0,queue/script override
+RLSD_TR,Fused kernels,False,method override
--- a/results/summary.json
+++ b/results/summary.json
@@ -0,0 +1,29 @@
+{
+  "repo_id": "SeongryongJung/Qwen3-8B-Material-RLSD-TR",
+  "output_dir": "/mnt/mole/SDPO/L2T/hf_upload_tr/Qwen3-8B-Material-RLSD-TR",
+  "experiment": "qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8",
+  "best_step": 100,
+  "best_val_mean16": 0.7646276595744681,
+  "best_actor_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor",
+  "final_step": 100,
+  "final_val_mean16": 0.7646276595744681,
+  "final_actor_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor",
+  "train_rows": 90,
+  "val_rows": 10,
+  "hf_model_files": [
+    "added_tokens.json",
+    "chat_template.jinja",
+    "config.json",
+    "generation_config.json",
+    "merges.txt",
+    "model.safetensors.index.json",
+    "special_tokens_map.json",
+    "tokenizer.json",
+    "tokenizer_config.json",
+    "vocab.json",
+    "model-00001-of-00004.safetensors",
+    "model-00002-of-00004.safetensors",
+    "model-00003-of-00004.safetensors",
+    "model-00004-of-00004.safetensors"
+  ]
+}
--- a/results/training_score.png
+++ b/results/training_score.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b033785d929211e5f4e519e7c4a4bd294a8424ceceb6a979c4471637e0e5c16
+size 128191
--- a/results/training_score.svg
+++ b/results/training_score.svg
--- a/results/training_scores.csv
+++ b/results/training_scores.csv
@@ -0,0 +1,91 @@
+step,critic_score_mean
+1,0.53125
+2,0.38671875
+3,0.49609375
+4,0.51953125
+5,0.55078125
+6,0.46484375
+7,0.5703125
+8,0.54296875
+9,0.57421875
+11,0.5390625
+12,0.62890625
+13,0.5546875
+14,0.71875
+15,0.61328125
+16,0.66015625
+17,0.55078125
+18,0.62890625
+19,0.60546875
+21,0.54296875
+22,0.69140625
+23,0.73828125
+24,0.8515625
+25,0.625
+26,0.66796875
+27,0.81640625
+28,0.5859375
+29,0.6171875
+31,0.65234375
+32,0.65625
+33,0.7109375
+34,0.80859375
+35,0.81640625
+36,0.61328125
+37,0.8515625
+38,0.60546875
+39,0.7578125
+41,0.59765625
+42,0.59375
+43,0.515625
+44,0.72265625
+45,0.7734375
+46,0.703125
+47,0.6640625
+48,0.84375
+49,0.66796875
+51,0.66796875
+52,0.78515625
+53,0.64453125
+54,0.57421875
+55,0.7421875
+56,0.765625
+57,0.765625
+58,0.8046875
+59,0.7265625
+61,0.80859375
+62,0.8515625
+63,0.6953125
+64,0.80078125
+65,0.6171875
+66,0.69921875
+67,0.80078125
+68,0.78125
+69,0.796875
+71,0.7421875
+72,0.765625
+73,0.6796875
+74,0.8359375
+75,0.70703125
+76,0.703125
+77,0.55078125
+78,0.6640625
+79,0.8046875
+81,0.71875
+82,0.734375
+83,0.68359375
+84,0.8203125
+85,0.69140625
+86,0.83984375
+87,0.609375
+88,0.671875
+89,0.71484375
+91,0.84765625
+92,0.71875
+93,0.8046875
+94,0.69921875
+95,0.7109375
+96,0.58984375
+97,0.84375
+98,0.89453125
+99,0.765625
--- a/results/validation_mean16.csv
+++ b/results/validation_mean16.csv
@@ -0,0 +1,11 @@
+step,val_mean16
+10,0.6555851063829787
+20,0.6888297872340425
+30,0.6974734042553191
+40,0.7340425531914894
+50,0.7466755319148937
+60,0.7513297872340425
+70,0.7519946808510638
+80,0.7446808510638298
+90,0.7539893617021277
+100,0.7646276595744681
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/vocab.json
+++ b/vocab.json