SeongryongJung commited on Jul 2

Commit

7cb6e68

verified ·

1 Parent(s): b13e05c

Add files using upload-large-folder tool

Browse files

Files changed (21) hide show

.gitattributes +2 -0
README.md +65 -0
added_tokens.json +28 -0
artifacts/config.yaml +843 -0
artifacts/wandb-summary.json +1 -0
chat_template.jinja +89 -0
config.json +68 -0
generation_config.json +13 -0
merges.txt +0 -0
model-00001-of-00004.safetensors +3 -0
model-00002-of-00004.safetensors +3 -0
model-00003-of-00004.safetensors +3 -0
model-00004-of-00004.safetensors +3 -0
model.safetensors.index.json +407 -0
results/training_score.png +3 -0
results/training_scores.csv +91 -0
results/validation_mean16.csv +11 -0
special_tokens_map.json +31 -0
tokenizer.json +3 -0
tokenizer_config.json +239 -0
vocab.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,5 @@ saved_model/**/* 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

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+results/training_score.png filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,65 @@

+---
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
+library_name: transformers
+tags:
+- qwen3
+- reinforcement-learning
+- sdpo
+- srpo
+- ema
+---
+# qwen3-8b-material-srpo-ema005
+This repository contains the **last checkpoint** (`global_step_100`) for `qwen3gen-material-SRPO-Qwen-Qwen3-8B-mbs32-ema0.05-dwtrue-train64-rollout8-lr5e-6-vllm0.8`,
+converted to Hugging Face Transformers format.
+## Evaluation
+The reported headline score is the **best validation `mean@16` observed during training**.
+It is not necessarily the score of the uploaded last checkpoint.
+| Dataset | Method | Model | Uploaded checkpoint | Best val mean@16 | Best step | Final val mean@16 |
+|---|---|---|---|---:|---:|---:|
+| material | SRPO | Qwen3-8B | global_step_100 | 75.00% | 20 | 69.81% |
+![Training and validation scores](results/training_score.png)
+Raw result files:
+- `results/validation_mean16.csv`
+- `results/training_scores.csv`
+- `artifacts/config.yaml`
+- `artifacts/wandb-summary.json`
+## Training Setup
+- Base model: `Qwen/Qwen3-8B`
+- Dataset: `material`
+- Method: `SRPO`
+- EMA teacher update rate: `0.05`
+- Uploaded weights: last checkpoint, `global_step_100`
+- Validation metric used for headline score: `val-aux/*/mean@16`
+- Validation sampling: `n=16`
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+repo_id = "SeongryongJung/qwen3-8b-material-srpo-ema005"
+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,
+)
+```
+## Notes
+Most best-validation intermediate checkpoints were not retained as full actor checkpoints because
+training kept only the latest actor checkpoint. Therefore, this repository publishes the last
+checkpoint and records the best validation score separately.

added_tokens.json ADDED Viewed

	@@ -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
+}

artifacts/config.yaml ADDED Viewed

	@@ -0,0 +1,843 @@

+_wandb:
+    value:
+        cli_version: 0.23.1
+        e:
+            1lmdvk4dtxhi01fx1iikg1tfx310a8ke:
+                args:
+                    - --node-ip-address=198.19.35.151
+                    - --node-manager-port=36979
+                    - --object-store-name=/tmp/ray_q3g_material_srpo_Qwen3_8B/session_2026-07-01_00-32-44_056849_1012345/sockets/plasma_store
+                    - --raylet-name=/tmp/ray_q3g_material_srpo_Qwen3_8B/session_2026-07-01_00-32-44_056849_1012345/sockets/raylet
+                    - --redis-address=None
+                    - --metrics-agent-port=64451
+                    - --logging-rotate-bytes=536870912
+                    - --logging-rotate-backup-count=5
+                    - --runtime-env-agent-port=55805
+                    - --gcs-address=198.19.35.151:64548
+                    - --session-name=session_2026-07-01_00-32-44_056849_1012345
+                    - --temp-dir=/tmp/ray_q3g_material_srpo_Qwen3_8B
+                    - --webui=
+                    - --cluster-id=b6d231d69c87c706612b85f8f5c888b5524b9211dc6063eef0b1ad69
+                    - --startup-token=32
+                    - --worker-launch-time-ms=1782865967579
+                    - --node-id=4ef1edb881b5e79f0038566ddd1573aa6d31a9322a8e7e24245aec26
+                    - --runtime-env-hash=-1580796864
+                cpu_count: 64
+                cpu_count_logical: 128
+                cudaVersion: "13.0"
+                disk:
+                    /:
+                        total: "46086056050688"
+                        used: "5895417995264"
+                email: jungsr1116@cau.ac.kr
+                executable: /workspace/SIPO/.venv/bin/python
+                git:
+                    commit: c237ec221cb7566d5f85232708425314a6ffc926
+                    remote: https://github.com/jungseongryong/L2T
+                gpu: NVIDIA H200
+                gpu_count: 8
+                gpu_nvidia:
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-b897a6c4-7996-e2f1-0cc0-7b02d6a38587
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-f7cf7fff-d108-62cb-498a-225bffd6d151
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-5a9f5a22-0fdb-36cc-c516-0b618776d8ca
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-d547a11f-7fca-c74b-76fb-73993c30f136
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-ac3cb18b-d562-1d58-725e-10738ff5694c
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-e8484200-8103-548e-6421-89d2884c6d32
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-83471bd2-f389-d36d-63de-d4759c4435d3
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "150754820096"
+                      name: NVIDIA H200
+                      uuid: GPU-885aa58c-6341-2956-85d4-ca01897dd4a2
+                host: mole-gpu-2
+                memory:
+                    total: "2163980390400"
+                os: Linux-6.8.0-71-generic-x86_64-with-glibc2.36
+                program: /workspace/SIPO/.venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py
+                python: CPython 3.12.13
+                root: /workspace/L2T
+                startedAt: "2026-07-01T00:34:58.766732Z"
+                writerId: 1lmdvk4dtxhi01fx1iikg1tfx310a8ke
+        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: 5e-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: srpo
+                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: 32
+            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
+                feedback_template: |4-
+                    The following is feedback from your unsuccessful earlier attempt:
+                    {feedback_raw}
+                full_logit_distillation: true
+                include_environment_feedback: false
+                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: true
+                srpo_dynamic_weighting_temperature: 1
+                success_reward_threshold: 0.5
+                teacher_regularization: ema
+                teacher_update_rate: 0.05
+                token_reweight_decay_steps: null
+                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: 32
+        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: /workspace/SIPO/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: 64
+        train_files:
+            - /workspace/SIPO/datasets/sciknoweval/material/train.parquet
+        train_max_samples: 6400
+        truncation: error
+        trust_remote_code: true
+        use_shm: false
+        val_batch_size: null
+        val_files:
+            - /workspace/SIPO/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_srpo_Qwen3_8B
+            include_dashboard: false
+            num_cpus: null
+        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: /workspace/L2T/checkpoints/datasets/sciknoweval/material/qwen3gen-material-SRPO-Qwen-Qwen3-8B-mbs32-ema0.05-dwtrue-train64-rollout8-lr5e-6-vllm0.8
+        del_local_ckpt_after_load: false
+        device: cuda
+        esi_redundant_time: 0
+        experiment_name: qwen3gen-material-SRPO-Qwen-Qwen3-8B-mbs32-ema0.05-dwtrue-train64-rollout8-lr5e-6-vllm0.8
+        group_name: QWEN3-SRPO-GRPO-matched-generalization
+        log_val_generations: 0
+        logger:
+            - console
+            - wandb
+        max_actor_ckpt_to_keep: 1
+        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

artifacts/wandb-summary.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"timing_s/step":62.19280698150396,"rollout_corr/log_ppl_diff_max":0.11017386615276337,"val-aux/sciknoweval/score/worst@8/mean":0.6048829787234042,"training/global_step":100,"val-aux/sciknoweval/score/maj@2/std":0.09197891813317514,"val-aux/sciknoweval/score/maj@2/mean":0.6978510638297871,"srpo/routed_token_count":313.4921875,"val-aux/sciknoweval/acc/best@4/std":0.05041684887491364,"training/epoch":7,"actor/lr":5e-06,"timing_s/gen":15.533823166042566,"self_distillation/correct_sample_fraction":0.751953125,"val-aux/sciknoweval/score/mean@16":0.6981382978723404,"actor/entropy":0.01662192866206169,"val-aux/sciknoweval/incorrect_format/maj@2/std":0,"val-aux/sciknoweval/reward/worst@2/mean":0.6599148936170213,"critic/rewards/min":0,"timing_s/adv":1.1427462883293629,"srpo/sdpo_loss":0.00020309918932071014,"srpo/grpo_actor/pg_clipfrac_lower":0,"val-aux/sciknoweval/incorrect_format/std@16":0,"val-aux/sciknoweval/score/worst@16/std":0.034095613279772403,"val-aux/sciknoweval/score/maj@8/std":0.05610907033175666,"val-aux/sciknoweval/score/best@2/std":0.07351696810537442,"val-aux/sciknoweval/score/worst@2/mean":0.6599148936170213,"val-aux/sciknoweval/score/best@8/mean":0.785468085106383,"val-aux/sciknoweval/incorrect_format/worst@16/mean":1,"val-aux/sciknoweval/score/best@4/std":0.05041684887491364,"val-aux/sciknoweval/acc/maj@4/mean":0.6983723404255319,"timing_s/agent_loop/slowest/prompt_length":279,"val-aux/sciknoweval/reward/best@2/std":0.07351696810537442,"val-aux/sciknoweval/score/maj@8/mean":0.6965212765957447,"val-aux/sciknoweval/acc/best@8/std":0.027325802385658172,"self_distillation/reprompt_sample_fraction":0.810546875,"critic/score/mean":0.751953125,"timing_s/update_actor":39.46628168784082,"global_seqlen/balanced_min":44276,"srpo/correct_sample_fraction":0.751953125,"self_distillation/dynamic_weight_max":1.0661888122558594,"val-aux/sciknoweval/score/maj@16/mean":0.6939893617021277,"val-aux/sciknoweval/incorrect_format/maj@16/std":0,"rollout_corr/rollout_is_std":0.015230931341648102,"rollout_corr/chi2_seq":0.4488186005037278,"critic/returns/max":0.875,"rollout_corr/rollout_is_mean":1.0000052452087402,"perf/max_memory_reserved_gb":161,"critic/returns/mean":-0.00013862237392459065,"actor/pg_loss":-0.05863602465205986,"srpo/routed_loss":-0.02931801232602993,"self_distillation/dynamic_weight_entropy_mean":0.0011489073399388872,"val-aux/sciknoweval/reward/best@8/std":0.027325802385658172,"rollout_corr/rollout_is_seq_min":0.9939368367195129,"val-aux/sciknoweval/reward/maj@8/std":0.05610907033175666,"val-aux/sciknoweval/acc/std@16":0.09168350265348742,"rollout_corr/log_ppl_diff":0.0009017629418082151,"perf/mfu/actor":0.05811259814047357,"val-aux/sciknoweval/score/worst@16/mean":0.5850957446808511,"prompt_length/clip_ratio":0,"critic/rewards/mean":0.751953125,"val-aux/sciknoweval/reward/maj@4/std":0.07461535615884214,"training/rollout_actor_probs_pearson_corr":0.9960340857505798,"val-aux/sciknoweval/score/worst@2/std":0.08168762968989612,"val-aux/sciknoweval/reward/worst@8/std":0.04649000772134289,"val-aux/sciknoweval/incorrect_format/best@16/std":0,"val-aux/sciknoweval/incorrect_format/worst@8/std":0,"rollout_corr/rollout_is_eff_sample_size":0.9997681916793804,"timing_per_token_ms/adv":0.003226164806187715,"rollout_corr/kl":0.0009017628440166348,"perf/max_memory_allocated_gb":146.6214051246643,"global_seqlen/balanced_max":44277,"val-aux/sciknoweval/reward/best@4/std":0.05041684887491364,"val-aux/sciknoweval/incorrect_format/best@8/mean":1,"timing_s/reward":0.09846976771950722,"timing_s/save_checkpoint":12.74902163259685,"timing_s/start_profile":0.00012683309614658356,"val-aux/sciknoweval/acc/worst@8/std":0.04649000772134289,"global_seqlen/mean":44276.5,"val-aux/sciknoweval/reward/worst@2/std":0.08168762968989612,"val-aux/sciknoweval/reward/worst@16/mean":0.5850957446808511,"timing_s/agent_loop/tool_calls/mean":0,"val-aux/sciknoweval/reward/maj@16/std":0.03941687933094451,"val-core/sciknoweval/acc/maj@16/std":0.03941687933094451,"self_distillation/success_sample_fraction":0.810546875,"rollout_corr/rollout_is_seq_fraction_high":0,"val-aux/sciknoweval/score/maj@4/std":0.07461535615884214,"val-aux/sciknoweval/incorrect_format/mean@16":1,"response_length_non_aborted/mean":313.4921875,"global_seqlen/minmax_diff":12381,"actor/grad_norm":0.03198811877518892,"perf/cpu_memory_used_gb":209.00598764419556,"val-aux/sciknoweval/incorrect_format/best@2/mean":1,"critic/returns/min":-0.875,"val-aux/sciknoweval/acc/best@4/mean":0.7663297872340425,"critic/score/min":0,"num_turns/max":2,"srpo/grpo_sample_fraction":0.939453125,"_step":100,"val-aux/sciknoweval/incorrect_format/maj@8/mean":1,"val-aux/sciknoweval/acc/best@2/std":0.07351696810537442,"timing_s/stop_profile":0.00016197003424167633,"self_distillation/success_group_fraction":0.8125,"val-aux/sciknoweval/score/maj@4/mean":0.6983723404255319,"rollout_corr/training_log_ppl":0.017575562679986945,"val-aux/sciknoweval/acc/worst@2/mean":0.6599148936170213,"timing_s/agent_loop/generate_sequences/max":8.521741507574916,"val-aux/sciknoweval/incorrect_format/worst@2/std":0,"val-aux/sciknoweval/reward/best@8/mean":0.785468085106383,"_timestamp":1.782873094133226e+09,"val-aux/sciknoweval/incorrect_format/best@16/mean":1,"response_length_non_aborted/min":153,"training/rollout_probs_diff_valid":1,"num_turns/min":2,"self_distillation/empty_target_batch":0.189453125,"actor/kl_loss":0,"timing_s/agent_loop/tool_calls/max":0,"response_length/mean":313.4921875,"val-aux/sciknoweval/acc/maj@8/mean":0.6965212765957447,"val-aux/sciknoweval/incorrect_format/maj@4/std":0,"rollout_corr/rollout_is_max":1.8164042234420776,"val-aux/sciknoweval/incorrect_format/worst@16/std":0,"rollout_corr/rollout_is_ratio_fraction_low":9.968350786948577e-05,"response_length_non_aborted/clip_ratio":0,"val-aux/sciknoweval/incorrect_format/maj@8/std":0,"prompt_length/min":196,"val-aux/sciknoweval/reward/worst@16/std":0.034095613279772403,"rollout_corr/log_ppl_diff_min":-0.0061856480315327644,"global_seqlen/min":35738,"response/aborted_ratio":0,"self_distillation/dynamic_weight_mean":0.06054687628056854,"val-aux/sciknoweval/acc/best@8/mean":0.785468085106383,"timing_s/agent_loop/generate_sequences/min":3.0229121800512075,"rollout_corr/chi2_token":0.0012098137522116303,"val-aux/sciknoweval/score/std@16":0.09168350265348742,"val-aux/sciknoweval/score/best@16/mean":0.7933085106382979,"timing_s/testing":39.936076236888766,"val-core/sciknoweval/acc/best@16/mean":0.7933085106382979,"val-aux/sciknoweval/incorrect_format/maj@4/mean":1,"val-aux/sciknoweval/incorrect_format/maj@16/mean":1,"_wandb":{"runtime":6994},"critic/rewards/max":1,"training/rollout_probs_diff_std":0.006381065119057894,"val-aux/sciknoweval/incorrect_format/worst@4/mean":1,"val-aux/sciknoweval/reward/maj@4/mean":0.6983723404255319,"val-aux/sciknoweval/reward/best@2/mean":0.736340425531915,"val-aux/sciknoweval/score/worst@8/std":0.04649000772134289,"val-aux/sciknoweval/score/best@2/mean":0.736340425531915,"val-aux/sciknoweval/score/best@8/std":0.027325802385658172,"self_distillation/feedback_available_fraction":0,"perf/total_num_tokens":354212,"srpo/grpo_actor/ppo_kl":0.0004732500672419704,"rollout_corr/rollout_is_seq_max_deviation":0.0060631632804870605,"rollout_corr/rollout_is_seq_std":0.000991877052001655,"val-aux/sciknoweval/reward/best@16/std":0.010758500257960827,"perf/time_per_step":62.19280698150396,"timing_s/old_log_prob":5.8706168588250875,"response_length/max":621,"global_seqlen/max":48119,"training/rollout_probs_diff_max":0.38766512274742126,"critic/advantages/min":-0.875,"val-aux/sciknoweval/acc/worst@8/mean":0.6048829787234042,"val-aux/sciknoweval/reward/maj@2/mean":0.6978510638297871,"val-aux/sciknoweval/reward/maj@2/std":0.09197891813317514,"self_distillation/dynamic_weighting_enabled":1,"val-core/sciknoweval/acc/maj@16/mean":0.6939893617021277,"response_length_non_aborted/max":621,"training/rollout_probs_diff_mean":0.0005968448240309954,"val-aux/sciknoweval/acc/maj@4/std":0.07461535615884214,"val-aux/sciknoweval/acc/worst@4/std":0.06311354539605504,"val-aux/sciknoweval/incorrect_format/maj@2/mean":1,"val-aux/num_turns/min":2,"val-aux/sciknoweval/incorrect_format/best@4/std":0,"val-aux/sciknoweval/reward/mean@16":0.6981382978723404,"val-aux/sciknoweval/incorrect_format/worst@4/std":0,"val-aux/sciknoweval/reward/std@16":0.09168350265348742,"val-aux/sciknoweval/acc/maj@8/std":0.05610907033175666,"val-aux/sciknoweval/score/best@4/mean":0.7663297872340425,"prompt_length/mean":378.328125,"prompt_length/max":481,"rollout_corr/log_ppl_abs_diff":0.0014645587026365092,"self_distillation/feedback_used_fraction":0,"_runtime":6994.178938758,"val-aux/sciknoweval/acc/worst@16/std":0.034095613279772403,"critic/advantages/mean":-0.00013862237392459065,"rollout_corr/rollout_is_ratio_fraction_high":0,"critic/score/max":1,"val-aux/sciknoweval/acc/maj@2/std":0.09197891813317514,"val-aux/sciknoweval/acc/best@2/mean":0.736340425531915,"val-aux/sciknoweval/acc/worst@2/std":0.08168762968989612,"rollout_corr/rollout_log_ppl":0.016673799738150308,"num_turns/mean":2,"timing_per_token_ms/gen":0.0967791210783423,"val-core/sciknoweval/acc/best@16/std":0.010758500257960827,"timing_per_token_ms/update_actor":0.11141994536560257,"val-aux/sciknoweval/reward/worst@4/mean":0.6292021276595745,"val-aux/sciknoweval/acc/worst@16/mean":0.5850957446808511,"srpo/grpo_actor/pg_clipfrac":8.258612342615379e-05,"timing_s/agent_loop/tool_calls/min":0,"response_length/min":153,"rollout_corr/ppl_ratio":1.0009211474098265,"timing_s/agent_loop/slowest/response_length":620,"val-aux/sciknoweval/incorrect_format/worst@2/mean":1,"val-aux/sciknoweval/score/maj@16/std":0.03941687933094451,"srpo/grpo_loss":-0.02952111151535064,"critic/advantages/max":0.875,"rollout_corr/rollout_is_seq_max":1.0036133527755737,"timing_s/agent_loop/slowest/generate_sequences":8.521741507574916,"val-aux/sciknoweval/reward/best@16/mean":0.7933085106382979,"rollout_corr/training_ppl":1.0178639336954802,"rollout_corr/rollout_is_seq_fraction_low":0,"perf/mfu/actor_infer":0,"val-aux/sciknoweval/reward/worst@4/std":0.06311354539605504,"val-aux/sciknoweval/incorrect_format/best@4/mean":1,"srpo/sdpo_sample_fraction":0.060546875,"response_length/clip_ratio":0,"val-aux/num_turns/max":2,"val-aux/sciknoweval/reward/best@4/mean":0.7663297872340425,"rollout_corr/rollout_is_min":0.06320670247077942,"timing_s/agent_loop/generate_sequences/mean":5.69180674393283,"val-aux/sciknoweval/incorrect_format/best@2/std":0,"val-aux/sciknoweval/score/best@16/std":0.010758500257960827,"val-aux/sciknoweval/reward/worst@8/mean":0.6048829787234042,"val-aux/sciknoweval/reward/maj@16/mean":0.6939893617021277,"rollout_corr/k3_kl":0.0007186645261806462,"perf/throughput":711.923165216964,"val-aux/sciknoweval/incorrect_format/best@8/std":0,"timing_s/agent_loop/slowest/tool_calls":0,"val-aux/num_turns/mean":2,"val-aux/sciknoweval/reward/maj@8/mean":0.6965212765957447,"val-aux/sciknoweval/acc/maj@2/mean":0.6978510638297871,"rollout_corr/rollout_ppl":1.0169175930786878,"val-aux/sciknoweval/score/worst@4/mean":0.6292021276595745,"rollout_corr/rollout_is_seq_mean":0.9999901652336121,"val-aux/sciknoweval/score/worst@4/std":0.06311354539605504,"val-core/sciknoweval/acc/mean@16":0.6981382978723404,"val-aux/sciknoweval/acc/worst@4/mean":0.6292021276595745,"val-aux/sciknoweval/incorrect_format/worst@8/mean":1}

chat_template.jinja ADDED Viewed

	@@ -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 %}

config.json ADDED Viewed

	@@ -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
+}

generation_config.json ADDED Viewed

	@@ -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"
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model-00001-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2b311c2daf93fcabf01af01fe1f371d4f9f3bedc77efe0e5f952dbb418317e
+size 4999893984

model-00002-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:37b61225939882ccb8878b888a974978bc9a638328c0dfe229662df46df928a9
+size 4994484440

model-00003-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:83fefa5b534873c89566bc00f56d2627f161ea2ab07c004a9d58867faba98589
+size 4977771672

model-00004-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:45ad8ef0c6ad224f1e1a0bb33a0c7ef8436bf8a4e7090d81fca31e70805a21df
+size 1409366712

model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,407 @@

+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00003-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-00004-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-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-00004-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-00003-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-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-00004-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-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-00001-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-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-00001-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-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-00004-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-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-00001-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-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-00001-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-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-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-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-00001-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-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-00004-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-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-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-00001-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-00002-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-00002-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00001-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-00001-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00001-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-00002-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-00002-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-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-00002-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00001-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-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00003-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-00001-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-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-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-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-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-00002-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-00004-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.norm.weight": "model-00002-of-00004.safetensors"
+  }
+}

results/training_score.png ADDED Viewed

Git LFS Details

SHA256: e051fd5f946f01357b3a9fdc68f0ac6dcd3a4c45f2499cafc40aa3dbdcb283c5
Pointer size: 131 Bytes
Size of remote file: 115 kB

results/training_scores.csv ADDED Viewed

	@@ -0,0 +1,91 @@

+step,critic_score_mean
+1,0.484375
+2,0.484375
+3,0.482421875
+4,0.546875
+5,0.564453125
+6,0.59375
+7,0.65625
+8,0.634765625
+9,0.6015625
+11,0.623046875
+12,0.818359375
+13,0.6875
+14,0.72265625
+15,0.65234375
+16,0.638671875
+17,0.783203125
+18,0.75
+19,0.697265625
+21,0.642578125
+22,0.666015625
+23,0.7578125
+24,0.771484375
+25,0.693359375
+26,0.712890625
+27,0.599609375
+28,0.73046875
+29,0.794921875
+31,0.7890625
+32,0.736328125
+33,0.654296875
+34,0.79296875
+35,0.8203125
+36,0.755859375
+37,0.77734375
+38,0.74609375
+39,0.625
+41,0.71484375
+42,0.76171875
+43,0.76171875
+44,0.68359375
+45,0.76953125
+46,0.76953125
+47,0.68359375
+48,0.673828125
+49,0.8359375
+51,0.77734375
+52,0.681640625
+53,0.787109375
+54,0.734375
+55,0.80859375
+56,0.76171875
+57,0.708984375
+58,0.70703125
+59,0.716796875
+61,0.724609375
+62,0.765625
+63,0.75
+64,0.7578125
+65,0.72265625
+66,0.7734375
+67,0.73046875
+68,0.798828125
+69,0.68359375
+71,0.759765625
+72,0.791015625
+73,0.755859375
+74,0.748046875
+75,0.740234375
+76,0.7578125
+77,0.845703125
+78,0.734375
+79,0.763671875
+81,0.748046875
+82,0.8203125
+83,0.833984375
+84,0.845703125
+85,0.859375
+86,0.75
+87,0.755859375
+88,0.734375
+89,0.814453125
+91,0.693359375
+92,0.787109375
+93,0.720703125
+94,0.71484375
+95,0.703125
+96,0.806640625
+97,0.751953125
+98,0.75
+99,0.837890625

results/validation_mean16.csv ADDED Viewed

	@@ -0,0 +1,11 @@

+step,val_mean16
+10,0.683510638298
+20,0.75
+30,0.742686170213
+40,0.745345744681
+50,0.749335106383
+60,0.736037234043
+70,0.71210106383
+80,0.71875
+90,0.71875
+100,0.698138297872

special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json ADDED Viewed

	@@ -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
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff