Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

args.json

@@ -0,0 +1,467 @@
+{
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "zai-org/GLM-4.5-Air",
+  "model_type": "glm4_5",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "glm4_5",
+  "system": null,
+  "max_length": 10280,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_free": true,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [
+    "/workspace/joined_dataset_cleaned_modified.jsonl"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.01,
+  "data_seed": 42,
+  "dataset_num_proc": 8,
+  "load_from_cache_file": true,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "remove_unused_columns": true,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": null,
+  "temperature": null,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": "/workspace/glm-4.5-air-mcore",
+  "lora_modules": [],
+  "tuner_backend": "peft",
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "seed": 42,
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": true,
+  "packing_length": 10280,
+  "lazy_tokenize": false,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "hub_token": null,
+  "ddp_timeout": 18000000,
+  "ddp_backend": null,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "adapter_load": null,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 256,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "use_rslora": true,
+  "rlhf_type": null,
+  "ref_load": null,
+  "ref_adapter_load": null,
+  "beta": 0.1,
+  "rpo_alpha": null,
+  "reference_free": false,
+  "label_smoothing": 0.0,
+  "f_divergence_type": "reverse_kl",
+  "loss_type": null,
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
+  "calculate_KL": null,
+  "center_rewards_coefficient": null,
+  "padded_vocab_size": 151552,
+  "initialize_embedding": false,
+  "mlp_padding_free": false,
+  "dataloader_persistent_workers": true,
+  "dataloader_prefetch_factor": 10,
+  "architectures": "Glm4MoeForCausalLM",
+  "llm_architectures": null,
+  "max_epochs": 2,
+  "enable_dft_loss": false,
+  "enable_channel_loss": false,
+  "original_max_position_embeddings": null,
+  "partial_rotary_factor": 0.5,
+  "use_shared_expert_gate": false,
+  "vit_gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "linear_num_value_heads": null,
+  "linear_num_key_heads": null,
+  "linear_key_head_dim": null,
+  "linear_value_head_dim": null,
+  "linear_conv_kernel_dim": null,
+  "layer_types": null,
+  "mrope_interleaved": false,
+  "micro_batch_size": 4,
+  "global_batch_size": 32,
+  "recompute_granularity": "full",
+  "recompute_method": "uniform",
+  "recompute_num_layers": 1,
+  "recompute_modules": [
+    "core_attn"
+  ],
+  "use_cpu_initialization": false,
+  "deterministic_mode": false,
+  "train_iters": null,
+  "log_interval": 5,
+  "tensorboard_dir": "/workspace/megatron_output/Iceblink-v3-SFT-1/v0-20251101-193922/runs",
+  "no_masked_softmax_fusion": false,
+  "no_bias_dropout_fusion": false,
+  "no_bias_swiglu_fusion": false,
+  "no_rope_fusion": false,
+  "no_gradient_accumulation_fusion": false,
+  "cross_entropy_loss_fusion": true,
+  "cross_entropy_fusion_impl": "native",
+  "calculate_per_token_loss": true,
+  "use_flash_attn": false,
+  "attention_backend": "flash",
+  "optimizer": "adam",
+  "optimizer_cpu_offload": false,
+  "optimizer_offload_fraction": 1.0,
+  "use_precision_aware_optimizer": false,
+  "main_grads_dtype": "fp32",
+  "main_params_dtype": "fp32",
+  "exp_avg_dtype": "fp32",
+  "exp_avg_sq_dtype": "fp32",
+  "dataloader_type": "cyclic",
+  "manual_gc": false,
+  "manual_gc_interval": 0,
+  "lr": 1e-05,
+  "lr_decay_style": "cosine",
+  "lr_decay_iters": null,
+  "lr_warmup_iters": 0,
+  "lr_warmup_fraction": 0.05,
+  "min_lr": 1e-06,
+  "weight_decay": 0.1,
+  "clip_grad": 1.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_eps": 1e-08,
+  "sgd_momentum": 0.9,
+  "save": "/workspace/megatron_output/Iceblink-v3-SFT-1/v0-20251101-193922",
+  "save_interval": 25,
+  "save_retain_interval": null,
+  "no_save_optim": true,
+  "no_save_rng": true,
+  "load": "/workspace/glm-4.5-air-mcore",
+  "no_load_optim": false,
+  "no_load_rng": false,
+  "finetune": true,
+  "ckpt_format": "torch_dist",
+  "no_initialization": true,
+  "auto_detect_ckpt_format": true,
+  "exit_on_missing_checkpoint": true,
+  "async_save": false,
+  "use_persistent_ckpt_worker": false,
+  "ckpt_fully_parallel_load": false,
+  "ckpt_assume_constant_structure": false,
+  "distributed_backend": "nccl",
+  "local_rank": 0,
+  "use_distributed_optimizer": true,
+  "tensor_model_parallel_size": 8,
+  "pipeline_model_parallel_size": 1,
+  "decoder_first_pipeline_num_layers": null,
+  "decoder_last_pipeline_num_layers": null,
+  "sequence_parallel": true,
+  "context_parallel_size": 1,
+  "tp_comm_overlap": false,
+  "overlap_grad_reduce": false,
+  "overlap_param_gather": false,
+  "distributed_timeout_minutes": 300000,
+  "num_layers_per_virtual_pipeline_stage": null,
+  "num_virtual_stages_per_pipeline_rank": null,
+  "microbatch_group_size_per_virtual_pipeline_stage": null,
+  "pipeline_model_parallel_layout": null,
+  "num_layers": 46,
+  "hidden_size": 4096,
+  "ffn_hidden_size": 10944,
+  "num_attention_heads": 96,
+  "group_query_attention": true,
+  "num_query_groups": 8,
+  "max_position_embeddings": 131072,
+  "position_embedding_type": "rope",
+  "mrope_section": null,
+  "rotary_base": 1000000,
+  "rotary_percent": 1.0,
+  "rotary_interleaved": false,
+  "normalization": "RMSNorm",
+  "norm_epsilon": 1e-05,
+  "swiglu": true,
+  "untie_embeddings_and_output_weights": true,
+  "disable_bias_linear": true,
+  "add_qkv_bias": true,
+  "attention_dropout": 0.0,
+  "hidden_dropout": 0.0,
+  "kv_channels": 128,
+  "qk_layernorm": false,
+  "transformer_impl": "transformer_engine",
+  "num_experts": 128,
+  "moe_layer_freq": "[0]*1+[1]*45",
+  "moe_ffn_hidden_size": 1408,
+  "moe_shared_expert_intermediate_size": 1408,
+  "moe_router_topk": 8,
+  "moe_router_pre_softmax": false,
+  "moe_router_dtype": "fp32",
+  "moe_router_score_function": "sigmoid",
+  "moe_router_bias_update_rate": 0.001,
+  "moe_router_enable_expert_bias": true,
+  "moe_router_topk_scaling_factor": 1.0,
+  "moe_router_load_balancing_type": "aux_loss",
+  "expert_model_parallel_size": 8,
+  "expert_tensor_parallel_size": 1,
+  "moe_token_dispatcher_type": null,
+  "moe_enable_deepep": false,
+  "moe_grouped_gemm": true,
+  "moe_permute_fusion": true,
+  "moe_aux_loss_coeff": 0.0005,
+  "moe_z_loss_coeff": null,
+  "moe_shared_expert_overlap": true,
+  "moe_layer_recompute": false,
+  "moe_expert_capacity_factor": null,
+  "moe_pad_expert_input_to_capacity": false,
+  "moe_token_drop_policy": null,
+  "multi_latent_attention": false,
+  "q_lora_rank": null,
+  "kv_lora_rank": 32,
+  "qk_head_dim": 128,
+  "qk_pos_emb_head_dim": 64,
+  "fp8_format": null,
+  "fp8_recipe": "delayed",
+  "fp8_amax_history_len": 1024,
+  "fp8_amax_compute_algo": "max",
+  "fp8_param_gather": false,
+  "fp16": false,
+  "bf16": true,
+  "apply_query_key_layer_scaling": false,
+  "attention_softmax_in_fp32": true,
+  "log_params_norm": false,
+  "log_throughput": false,
+  "tensorboard_log_interval": 1,
+  "tensorboard_queue_size": 50,
+  "log_timers_to_tensorboard": true,
+  "no_log_learning_rate_to_tensorboard": false,
+  "log_validation_ppl_to_tensorboard": true,
+  "log_memory_to_tensorboard": true,
+  "logging_level": null,
+  "wandb_project": "Megatron-Air-SFT",
+  "wandb_exp_name": "Iceblink-v3-SFT-1",
+  "wandb_save_dir": null,
+  "eval_iters": -1,
+  "eval_interval": 20,
+  "seq_length": 10280,
+  "num_workers": 8,
+  "megatron_extra_kwargs": {},
+  "add_version": true,
+  "rank": 0,
+  "global_world_size": 8,
+  "local_world_size": 8,
+  "model_suffix": "GLM-4.5-Air",
+  "model_info": "ModelInfo(model_type='glm4_5', model_dir='/root/.cache/modelscope/hub/models/ZhipuAI/GLM-4___5-Air', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=True, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='glm4_5', model_groups=[ModelGroup(models=[Model(ms_model_id='ZhipuAI/GLM-4.5-Air-Base', hf_model_id='zai-org/GLM-4.5-Air-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Air', hf_model_id='zai-org/GLM-4.5-Air', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Air-FP8', hf_model_id='zai-org/GLM-4.5-Air-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Base', hf_model_id='zai-org/GLM-4.5-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5', hf_model_id='zai-org/GLM-4.5', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-FP8', hf_model_id='zai-org/GLM-4.5-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='ZhipuAI/GLM-4.6', hf_model_id='zai-org/GLM-4.6', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='glm4_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x718e1047a7a0>, model_arch=None, architectures=['Glm4MoeForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.54'], tags=[])",
+  "model_dir": "/root/.cache/modelscope/hub/models/ZhipuAI/GLM-4___5-Air",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'qwen2_5', 'qwq', 'qwq_preview', 'qwen2_5_math', 'llama', 'llama3', 'llama3_1', 'llama3_2', 'longwriter_llama3_1', 'codefuse_codellama', 'marco_o1', 'deepseek', 'deepseek_r1_distill', 'yi', 'yi_coder', 'sus', 'skywork_o1', 'openbuddy_llama', 'openbuddy_llama3', 'megrez', 'reflection', 'numina', 'ziya', 'mengzi3', 'qwen3', 'qwen3_thinking', 'qwen3_nothinking', 'qwen2_moe', 'qwen3_moe', 'qwen3_moe_thinking', 'qwen3_coder', 'internlm3', 'mimo', 'mimo_rl', 'moonlight', 'deepseek_moe', 'deepseek_v2', 'deepseek_v2_5', 'deepseek_r1', 'dots1', 'ernie', 'glm4_5', 'deepseek_v3_1', 'ernie_thinking'], convert_mcore2hf=<function convert_mcore2hf at 0x718d83275e40>, convert_hf2mcore=<function convert_hf2mcore at 0x718d83275a80>, model_cls=<class 'swift.megatron.model.gpt_model.GPTModel'>, convert_hf_config=<function convert_gpt_hf_config at 0x718d83245940>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x718d832179c0>, visual_cls=None, extra_args_provider=None)",
+  "extra_args": {
+    "use_ray": false,
+    "ray_exp_name": null,
+    "device_groups": null,
+    "model": "ZhipuAI/GLM-4.5-Air",
+    "model_type": "glm4_5",
+    "model_revision": null,
+    "task_type": "causal_lm",
+    "torch_dtype": "bfloat16",
+    "attn_impl": null,
+    "new_special_tokens": [],
+    "num_labels": null,
+    "problem_type": null,
+    "rope_scaling": null,
+    "device_map": null,
+    "max_memory": {},
+    "max_model_len": null,
+    "local_repo_path": null,
+    "init_strategy": null,
+    "template": "glm4_5",
+    "system": null,
+    "max_length": 10280,
+    "truncation_strategy": "delete",
+    "max_pixels": null,
+    "agent_template": null,
+    "norm_bbox": null,
+    "use_chat_template": true,
+    "padding_free": true,
+    "padding_side": "right",
+    "sequence_parallel_size": 1,
+    "response_prefix": null,
+    "template_backend": "swift",
+    "dataset": [
+      "/workspace/joined_dataset_cleaned_modified.jsonl"
+    ],
+    "val_dataset": [],
+    "split_dataset_ratio": 0.01,
+    "data_seed": 42,
+    "dataset_num_proc": 8,
+    "load_from_cache_file": true,
+    "dataset_shuffle": true,
+    "val_dataset_shuffle": false,
+    "streaming": false,
+    "interleave_prob": null,
+    "stopping_strategy": "first_exhausted",
+    "shuffle_buffer_size": 1000,
+    "download_mode": "reuse_dataset_if_exists",
+    "columns": {},
+    "strict": false,
+    "remove_unused_columns": true,
+    "model_name": null,
+    "model_author": null,
+    "custom_dataset_info": [],
+    "quant_method": null,
+    "quant_bits": null,
+    "hqq_axis": null,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "bnb_4bit_quant_storage": null,
+    "max_new_tokens": null,
+    "temperature": null,
+    "top_k": null,
+    "top_p": null,
+    "repetition_penalty": null,
+    "num_beams": 1,
+    "stream": false,
+    "stop_words": [],
+    "logprobs": false,
+    "top_logprobs": null,
+    "ckpt_dir": "/workspace/glm-4.5-air-mcore",
+    "lora_modules": [],
+    "tuner_backend": "peft",
+    "train_type": "lora",
+    "adapters": [],
+    "external_plugins": [],
+    "model_kwargs": {},
+    "load_args": false,
+    "load_data_args": false,
+    "packing": true,
+    "packing_length": 10280,
+    "lazy_tokenize": false,
+    "cached_dataset": [],
+    "custom_register_path": [],
+    "use_hf": false,
+    "hub_token": null,
+    "ddp_timeout": 18000000,
+    "ddp_backend": null,
+    "ignore_args_error": false,
+    "use_swift_lora": false,
+    "freeze_llm": false,
+    "freeze_vit": true,
+    "freeze_aligner": true,
+    "freeze_parameters": [],
+    "freeze_parameters_regex": null,
+    "freeze_parameters_ratio": 0.0,
+    "trainable_parameters": [],
+    "trainable_parameters_regex": null,
+    "adapter_load": null,
+    "target_modules": [
+      "all-linear"
+    ],
+    "target_regex": null,
+    "modules_to_save": [],
+    "lora_rank": 256,
+    "lora_alpha": 16,
+    "lora_dropout": 0.05,
+    "lora_bias": "none",
+    "lora_dtype": null,
+    "use_rslora": true,
+    "rlhf_type": null,
+    "ref_load": null,
+    "ref_adapter_load": null,
+    "beta": 0.1,
+    "rpo_alpha": null,
+    "reference_free": false,
+    "label_smoothing": 0.0,
+    "f_divergence_type": "reverse_kl",
+    "loss_type": null,
+    "desirable_weight": 1.0,
+    "undesirable_weight": 1.0,
+    "calculate_KL": null,
+    "center_rewards_coefficient": null,
+    "padded_vocab_size": 151552,
+    "initialize_embedding": false,
+    "mlp_padding_free": false,
+    "dataloader_persistent_workers": true,
+    "dataloader_prefetch_factor": 10,
+    "architectures": "Glm4MoeForCausalLM",
+    "llm_architectures": null,
+    "max_epochs": 2,
+    "enable_dft_loss": false,
+    "enable_channel_loss": false,
+    "original_max_position_embeddings": null,
+    "partial_rotary_factor": 0.5,
+    "use_shared_expert_gate": false,
+    "vit_gradient_checkpointing": true,
+    "gradient_checkpointing_kwargs": null,
+    "linear_num_value_heads": null,
+    "linear_num_key_heads": null,
+    "linear_key_head_dim": null,
+    "linear_value_head_dim": null,
+    "linear_conv_kernel_dim": null,
+    "layer_types": null,
+    "mrope_interleaved": false,
+    "add_version": true,
+    "model_info": "ModelInfo(model_type='glm4_5', model_dir='/root/.cache/modelscope/hub/models/ZhipuAI/GLM-4___5-Air', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=True, config=None, task_type='causal_lm', num_labels=None)",
+    "model_meta": "ModelMeta(model_type='glm4_5', model_groups=[ModelGroup(models=[Model(ms_model_id='ZhipuAI/GLM-4.5-Air-Base', hf_model_id='zai-org/GLM-4.5-Air-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Air', hf_model_id='zai-org/GLM-4.5-Air', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Air-FP8', hf_model_id='zai-org/GLM-4.5-Air-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Base', hf_model_id='zai-org/GLM-4.5-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5', hf_model_id='zai-org/GLM-4.5', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-FP8', hf_model_id='zai-org/GLM-4.5-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='ZhipuAI/GLM-4.6', hf_model_id='zai-org/GLM-4.6', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='glm4_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x718e1047a7a0>, model_arch=None, architectures=['Glm4MoeForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.54'], tags=[])",
+    "megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'qwen2_5', 'qwq', 'qwq_preview', 'qwen2_5_math', 'llama', 'llama3', 'llama3_1', 'llama3_2', 'longwriter_llama3_1', 'codefuse_codellama', 'marco_o1', 'deepseek', 'deepseek_r1_distill', 'yi', 'yi_coder', 'sus', 'skywork_o1', 'openbuddy_llama', 'openbuddy_llama3', 'megrez', 'reflection', 'numina', 'ziya', 'mengzi3', 'qwen3', 'qwen3_thinking', 'qwen3_nothinking', 'qwen2_moe', 'qwen3_moe', 'qwen3_moe_thinking', 'qwen3_coder', 'internlm3', 'mimo', 'mimo_rl', 'moonlight', 'deepseek_moe', 'deepseek_v2', 'deepseek_v2_5', 'deepseek_r1', 'dots1', 'ernie', 'glm4_5', 'deepseek_v3_1', 'ernie_thinking'], convert_mcore2hf=<function convert_mcore2hf at 0x718d83275e40>, convert_hf2mcore=<function convert_hf2mcore at 0x718d83275a80>, model_cls=<class 'swift.megatron.model.gpt_model.GPTModel'>, convert_hf_config=<function convert_gpt_hf_config at 0x718d83245940>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x718d832179c0>, visual_cls=None, extra_args_provider=None)"
+  }
+}

chat_template.jinja

@@ -0,0 +1,103 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}
+<arg_key>{arg-key-1}</arg_key>
+<arg_value>{arg-value-1}</arg_value>
+<arg_key>{arg-key-2}</arg_key>
+<arg_value>{arg-value-2}</arg_value>
+...
+</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>
+{{ visible_text(m.content) }}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.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_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<tool_call>' + tc.name }}
+{% set _args = tc.arguments %}
+{% for k, v in _args.items() %}
+<arg_key>{{ k }}</arg_key>
+<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
+{% endfor %}
+</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>
+{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "first_k_dense_replace": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1408,
+  "n_group": 1,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37639ec42fc97943ccf32767591cae3dc91e08acf7345fd34c40d8ec5118c879
+size 4991854888

model-00002-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1939bfea34981074cb751a23833688193a692124ff4791b11f11cd16048e8e
+size 4994465672

model-00003-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306adc29236fec4e3fd8faf76adb83186753bab68e590e4bcecbd0f5e138401b
+size 4994465696

model-00004-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c122f3159e1cdd3d6f9d8ac038b27fcbf1ff7cd27d58cb6ca16664e42e60737a
+size 4994465696

model-00005-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd72817a2584a1befd52e547654c18c15dd541d4611cebe0bb3e1b128a04acc
+size 4994465696

model-00006-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4e5941cfeeba9ca6d576675be5be2d2b3ba0bff5df1fda94ff4a1e629fe9cb
+size 4974587952

model-00007-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae46b20e23147bac48c74099e7d8e7ffcf088f763961cfa1bd0c86d532bc299
+size 4991318928

model-00008-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6480fc83a8e8de6ed9864c7f5ff6082d00c9ed370ad438ad2dee96ec4978a2
+size 4994465664

model-00009-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b69c78a10644794b5acea498179409aa7884ac0df573c3222d9e7d1d2ab1a90f
+size 4994465784

model-00010-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240b5d748bbd524acc23fadc1bd0abfe7a0a7ade9159d0fe4d74e54ca3ebe5a3
+size 4994466104

model-00011-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348bd51624d1c015ba118fd6428d916b9eb37a2a661ad68c9541995c0191a8bc
+size 4994466104

model-00012-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b133d39a2f249c53ae7c0cd92d745874fa012896c9233a5eb03378e32440229
+size 4994466104

model-00013-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1067ec336c66450a781d02d27cd266fb4522bfd7f3caae54d556b5e76415bbec
+size 4994466104

model-00014-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae01e88f3f47c16356157499e051210ea26ae5bfb94554e0ec7375cf6369558
+size 4994466104

model-00015-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb240a8c63c072cdbe9e0d0fe4bb21dd5bd69097e2f5d533bb296f802de4a5c8
+size 4994466104

model-00016-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8f780a4e98896a5cdec39476173faa9146850801d175a74025aedd76a8bba2
+size 4994466104

model-00017-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c33ac6b45306e75dc3dd41014517343a3a6d1fd9aa1ac17dc85776d23650b9e
+size 4994466104

model-00018-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae1effe91c6c53ef0e7b30b4e6bd00bce3dabcb770ae905cefbbef636a7390c8
+size 4994466112

model-00019-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d3aab8293ef8e98eeeed7f4d418dd233b4aa5f4d6c570be3959068dd7f11d5
+size 4994466120

model-00020-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819de2744c126a9472a239dfdd97fceb67e3fd554c6a1ced85bb075015ba2e70
+size 4994466120

model-00021-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1da88df140bf43acc805e403aa48041d173fa339cc1a827fae60b66d6e9e715
+size 4992409992

model-00022-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7ae936a92c97415b76fbf9c343834055311065c946f6adc097a24efb21cd53
+size 4996566656

model-00023-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4af23f53b359da50cadecf2615fbba2db6c7a9e5f17f4b42504d5b48978ff36
+size 4994466088

model-00024-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e600022626722fc1a27d2b1c7e2abe44011210f5740470f2b480b1852f4f75f8
+size 4994466104

model-00025-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e15b5cf247594f7beee01c7b76e76159034c2c16151d65b6d83b729c1219cb8
+size 4994466104

model-00026-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7950789e57ba1c211b76e2eb2f7f9d504c4ebd02422311a3e66c929a5c5d4636
+size 4994466104

model-00027-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9afe43c15516d09c99813fdfc1fd71dc9f5ad83ff458f7ca9bf4c7949f577c
+size 4994466104

model-00028-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c966254ec6db47d72fd0410f712330c4167f03846d0298fb3124d68fc474ef
+size 4994466104

model-00029-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5939de91bff11a2deed12e68eb489198ba10cb6fd6566874bf997a1edfb54701
+size 4994466104

model-00030-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55613837eb1a3d20ca416944023a6b6f1760d97ae053c876cf223d32238fadbd
+size 4994466104

model-00031-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b371a2c51ee9e62b6a2fd29c50d41c5dc29a5d078c32406d86e6db4e8eb16d7
+size 4994466104

model-00032-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457e4928c935d2546a7bc209dc92c696f648b700d836381279f5fe44a78d81f3
+size 4994466104

model-00033-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9532ddc08b2c89c4bccbe0c2001bf1da622004841460d919002622ffaa9d48a
+size 4994466112

model-00035-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f540c11eeee253a19dd68faed3cbd369e3be606597737a638cc39b28a4949a63
+size 4994466120

model-00036-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856683d83c4e7a5ab8f5ce2fe70596d56f40db5b29076e879fcd755355954d05
+size 4903256352

model-00037-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a15089c9135ecd10ec2416a338960e8bdfae017bfe53d7636bedd9c5cdd2c3a
+size 4993444616

model-00038-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3599aa802a524d2cd1feb3dcb5ab44804770c883aac764c61331acc5247c69
+size 4994466080

model-00039-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b05e5a3f5c334fe4f2f9802cd858c8825ad2ca41635e44cd388bc9420f99e15
+size 4994466104

model-00040-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aeb2d838cb73505772f4b13f319b405e56d26fdc0478f8fa75b7fceb18b779a
+size 4994466104

model-00041-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa75cf6c629e660807fc554384f5ee0af2c022b50765e7d1d6fc920f1c6fd49
+size 4994466104

model-00042-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0b67b4c40bd6a3cfde6c9f95ad0ab516cdf722927c82f6f585816a7fadf279
+size 4994466104

model-00043-of-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7aeb6d063560105a06d50e8629632d6cad53e88280112b82e9909243c2863a5
+size 4056996976

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
+size 19970700