Upload folder using huggingface_hub

.gitattributes

@@ -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
+rank0.engine filter=lfs diff=lfs merge=lfs -text
+tokenization/tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,188 @@
+{
+    "version": "0.18.1",
+    "pretrained_config": {
+        "mlp_bias": false,
+        "attn_bias": false,
+        "rotary_base": 1000000,
+        "rotary_scaling": null,
+        "disable_weight_only_quant_plugin": false,
+        "num_labels": 1,
+        "use_logn_attn": false,
+        "moe": {
+            "num_experts": 0,
+            "shared_expert_intermediate_size": 0,
+            "top_k": 0,
+            "normalization_mode": 0,
+            "sparse_mixer_epsilon": 0.01,
+            "tp_mode": 0,
+            "device_limited_n_group": 0,
+            "device_limited_topk_group": 0,
+            "device_limited_routed_scaling_factor": 1.0
+        },
+        "architecture": "Qwen3ForCausalLM",
+        "dtype": "bfloat16",
+        "vocab_size": 151669,
+        "hidden_size": 1024,
+        "num_hidden_layers": 28,
+        "num_attention_heads": 16,
+        "hidden_act": "silu",
+        "logits_dtype": "float16",
+        "norm_epsilon": 1e-06,
+        "runtime_defaults": null,
+        "position_embedding_type": "rope_gpt_neox",
+        "num_key_value_heads": 8,
+        "intermediate_size": 3072,
+        "max_position_embeddings": 32768,
+        "mapping": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "cp_size": 1,
+            "tp_size": 1,
+            "pp_size": 1,
+            "moe_tp_size": 1,
+            "moe_ep_size": 1,
+            "auto_parallel": false
+        },
+        "quantization": {
+            "quant_algo": "FP8",
+            "kv_cache_quant_algo": null,
+            "group_size": 128,
+            "smoothquant_val": 0.5,
+            "clamp_val": null,
+            "use_meta_recipe": false,
+            "has_zero_point": false,
+            "pre_quant_scale": false,
+            "exclude_modules": [
+                "lm_head"
+            ]
+        },
+        "use_parallel_embedding": true,
+        "embedding_sharding_dim": 0,
+        "head_size": 128,
+        "qk_layernorm": false,
+        "rotary_embedding_dim": 128,
+        "producer": {
+            "name": "modelopt",
+            "version": "0.27.0"
+        },
+        "share_embedding_table": false,
+        "residual_mlp": false,
+        "bias": false,
+        "rotary_pct": 1.0,
+        "rank": 0,
+        "decoder": "qwen",
+        "rmsnorm": true,
+        "lm_head_bias": false,
+        "seq_length": 8192,
+        "qwen_type": "qwen3",
+        "moe_intermediate_size": 0,
+        "moe_shared_expert_intermediate_size": 0,
+        "tie_word_embeddings": true,
+        "model_type": "qwen",
+        "pooling_mode": "lasttoken",
+        "is_causal": true,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        }
+    },
+    "build_config": {
+        "max_input_len": 32768,
+        "max_seq_len": 32768,
+        "opt_batch_size": 8,
+        "max_batch_size": 256,
+        "max_beam_width": 1,
+        "max_num_tokens": 32768,
+        "opt_num_tokens": 256,
+        "max_prompt_embedding_table_size": 0,
+        "kv_cache_type": "DISABLED",
+        "gather_context_logits": false,
+        "gather_generation_logits": false,
+        "strongly_typed": true,
+        "force_num_profiles": null,
+        "profiling_verbosity": "layer_names_only",
+        "enable_debug_output": false,
+        "max_draft_len": 0,
+        "speculative_decoding_mode": 1,
+        "use_refit": false,
+        "input_timing_cache": null,
+        "output_timing_cache": "model.cache",
+        "lora_config": {
+            "lora_dir": [],
+            "lora_ckpt_source": "hf",
+            "max_lora_rank": 64,
+            "lora_target_modules": [],
+            "trtllm_modules_to_hf_modules": {}
+        },
+        "auto_parallel_config": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "cluster_key": null,
+            "cluster_info": null,
+            "sharding_cost_model": "alpha_beta",
+            "comm_cost_model": "alpha_beta",
+            "enable_pipeline_parallelism": false,
+            "enable_shard_unbalanced_shape": false,
+            "enable_shard_dynamic_shape": false,
+            "enable_reduce_scatter": true,
+            "builder_flags": null,
+            "debug_mode": false,
+            "infer_shape": true,
+            "validation_mode": false,
+            "same_buffer_io": {},
+            "same_spec_io": {},
+            "sharded_io_allowlist": [],
+            "fill_weights": false,
+            "parallel_config_cache": null,
+            "profile_cache": null,
+            "dump_path": null,
+            "debug_outputs": []
+        },
+        "weight_sparsity": false,
+        "weight_streaming": false,
+        "plugin_config": {
+            "dtype": "bfloat16",
+            "bert_attention_plugin": "auto",
+            "gpt_attention_plugin": "auto",
+            "gemm_plugin": null,
+            "explicitly_disable_gemm_plugin": false,
+            "gemm_swiglu_plugin": null,
+            "fp8_rowwise_gemm_plugin": null,
+            "qserve_gemm_plugin": null,
+            "identity_plugin": null,
+            "nccl_plugin": null,
+            "lora_plugin": null,
+            "weight_only_groupwise_quant_matmul_plugin": null,
+            "weight_only_quant_matmul_plugin": null,
+            "smooth_quant_plugins": true,
+            "smooth_quant_gemm_plugin": null,
+            "layernorm_quantization_plugin": null,
+            "rmsnorm_quantization_plugin": null,
+            "quantize_per_token_plugin": false,
+            "quantize_tensor_plugin": false,
+            "moe_plugin": "auto",
+            "mamba_conv1d_plugin": "auto",
+            "low_latency_gemm_plugin": null,
+            "low_latency_gemm_swiglu_plugin": null,
+            "context_fmha": true,
+            "bert_context_fmha_fp32_acc": false,
+            "paged_kv_cache": false,
+            "remove_input_padding": true,
+            "reduce_fusion": false,
+            "user_buffer": false,
+            "tokens_per_block": 64,
+            "use_paged_context_fmha": false,
+            "use_fp8_context_fmha": false,
+            "multiple_profiles": false,
+            "paged_state": false,
+            "streamingllm": false,
+            "manage_weights": false,
+            "use_fused_mlp": true,
+            "pp_reduce_scatter": false
+        },
+        "use_strip_plan": false,
+        "max_encoder_input_len": 1024,
+        "monitor_memory": false,
+        "use_mrope": false
+    }
+}

rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73f63e38635edcb326d24f0bde57b995b71531c38e481d2f16e3936dfe3265b
+size 779308428

tokenization/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": true,
+    "include_prompt": true
+}

tokenization/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669
+}

tokenization/config_sentence_transformers.json

@@ -0,0 +1,8 @@
+{
+  "prompts": {
+    "query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

tokenization/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

tokenization/model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 15134590976
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

tokenization/model_auto.py

@@ -0,0 +1,47 @@
+from transformers import AutoModel
+from huggingface_hub import HfApi, snapshot_download
+
+def get_model(model_name: str):
+    """
+    Load a model from the Hugging Face model hub.
+
+    Args:
+        model_name (str): The name of the model to load.
+
+    Returns:
+        transformers.PreTrainedModel: The loaded model.
+    """
+    return AutoModel.from_pretrained(model_name, torch_dtype="bfloat16")
+
+
+def upload_and_convert(
+    model_name: str = "mixedbread-ai/mxbai-rerank-base-v2",
+):
+    """Upload the converted sequence classifier to the hub."""
+    model = get_model(model_name)
+    split_name = model_name.split("/")[-1]
+    
+    
+
+    snapshot_download(f"{model_name}", local_dir=f"./{split_name}")
+    model.save_pretrained(f"./{split_name}")
+
+    api = HfApi()
+    api.create_repo(repo_id=f"michaelfeil/{split_name}-auto", exist_ok=True)
+    api.upload_folder(
+        repo_id=f"michaelfeil/{split_name}-auto",
+        folder_path=f"./{split_name}",
+    )
+
+
+if __name__ == "__main__":
+    upload_and_convert(
+        model_name="Qwen/Qwen3-Embedding-0.6B",
+    )
+    upload_and_convert(
+        model_name="Qwen/Qwen3-Embedding-4B",
+    )
+    upload_and_convert(
+        model_name="Qwen/Qwen3-Embedding-8B",
+    )
+    print("Model uploaded successfully.")

tokenization/modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

tokenization/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
+size 11423705

tokenization/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}