Delete global_step_0

global_step_0/actor/huggingface/README.md

@@ -1,57 +0,0 @@
----
-license: apache-2.0
-library_name: transformers
----
-# Qwen3-8B-Base
-
-## Qwen3 Highlights
-
-Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. 
-Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the following key improvements over the previously released Qwen2.5:
-
-- **Expanded Higher-Quality Pre-training Corpus:** Qwen3 is pre-trained on 36 trillion tokens across 119 languages — tripling the language coverage of Qwen2.5 — with a much richer mix of high-quality data, including coding, STEM, reasoning, book, multilingual, and synthetic data. 
-- **Training Techniques and Model Architecture:** Qwen3 incorporates a series of training techiques and architectural refinements, including global-batch load balancing loss for MoE models and qk layernorm for all models, leading to improved stability and overall performance.
-- **Three-stage Pre-training:** Stage 1 focuses on broad language modeling and general knowledge acquisition, Stage 2 improves reasoning skills like STEM, coding, and logical reasoning, and Stage 3 enhances long-context comprehension by extending training sequence lengths up to 32k tokens.
-- **Scaling Law Guided Hyperparameter Tuning:** Through comprehensive scaling law studies across the three-stage pre-training pipeline, Qwen3 systematically tunes critical hyperparameters — such as learning rate scheduler and batch size — separately for dense and MoE models, resulting in better training dynamics and final performance across different model scales. 
-
-## Model Overview
-
-**Qwen3-8B-Base** has the following features:
-- Type: Causal Language Models
-- Training Stage: Pretraining
-- Number of Parameters: 8.2B
-- Number of Paramaters (Non-Embedding): 6.95B
-- Number of Layers: 36
-- Number of Attention Heads (GQA): 32 for Q and 8 for KV
-- Context Length: 32,768
-
-For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
-
-## Requirements
-
-The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`.
-
-With `transformers<4.51.0`, you will encounter the following error:
-```
-KeyError: 'qwen3'
-```
-
-## Evaluation & Performance
-
-Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen3/).
-
-### Citation
-
-If you find our work helpful, feel free to give us a cite.
-
-```
-@misc{qwen3technicalreport,
-      title={Qwen3 Technical Report}, 
-      author={Qwen Team},
-      year={2025},
-      eprint={2505.09388},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2505.09388}, 
-}
-```

global_step_0/actor/huggingface/config.json

@@ -1,30 +0,0 @@
-{
-  "architectures": [
-    "Qwen3ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 12288,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 36,
-  "model_type": "qwen3",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 36,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.0",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
-}

global_step_0/actor/huggingface/generation_config.json

@@ -1,7 +0,0 @@
-{
-  "bos_token_id": 151643,
-  "do_sample": false,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
-  "transformers_version": "4.37.0"
-}

global_step_0/actor/huggingface/model-00001-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9983f1b9ef2f60e7c3730d9bc11ada914e6ec630639b5b020a89bd158cd0446b
-size 3996250744

global_step_0/actor/huggingface/model-00002-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9aa12339835bf7a093d3d0b0a0d2d77f8538301cfc7f8e7ec7a585858ebf7a1f
-size 3993160032

global_step_0/actor/huggingface/model-00003-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c7dd5a191c8da555def0714550375b3c0117751add408fcdda0c2a79ac0186bc
-size 3959604768

global_step_0/actor/huggingface/model-00004-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad8b708792105133e03fe19e2d56c89c709f677f01285f8b3ede8947d59fd9fe
-size 3187841392

global_step_0/actor/huggingface/model-00005-of-00005.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fbf24915d47ea030bb68ab0b9488f4515a907185baa6dc26837c9c3f2326a550
-size 1244659840

global_step_0/actor/huggingface/model.safetensors.index.json

@@ -1,406 +0,0 @@
-{
-  "metadata": {
-    "total_size": 16383567872
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00005-of-00005.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.norm.weight": "model-00004-of-00005.safetensors"
-  }
-}

global_step_0/actor/huggingface/tokenizer_config.json

@@ -1,239 +0,0 @@
-{
-  "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,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}