Upload folder using huggingface_hub

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 48,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": false,
+  "num_attention_heads": 32,
+  "num_experts": 2,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 64
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ece860af28baec4a593c19c5d22e2d4358786d926068c4e26cbee70e7abe145
+size 1219112

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,168 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": null,
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 1
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "<s>": {
+        "id": "<s>",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "<s>"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<unk>": 0,
+      "<s>": 1,
+      "</s>": 2,
+      "_tok_3": 3,
+      "_tok_4": 4,
+      "_tok_5": 5,
+      "_tok_6": 6,
+      "_tok_7": 7,
+      "_tok_8": 8,
+      "_tok_9": 9,
+      "_tok_10": 10,
+      "_tok_11": 11,
+      "_tok_12": 12,
+      "_tok_13": 13,
+      "_tok_14": 14,
+      "_tok_15": 15,
+      "_tok_16": 16,
+      "_tok_17": 17,
+      "_tok_18": 18,
+      "_tok_19": 19,
+      "_tok_20": 20,
+      "_tok_21": 21,
+      "_tok_22": 22,
+      "_tok_23": 23,
+      "_tok_24": 24,
+      "_tok_25": 25,
+      "_tok_26": 26,
+      "_tok_27": 27,
+      "_tok_28": 28,
+      "_tok_29": 29,
+      "_tok_30": 30,
+      "_tok_31": 31,
+      "_tok_32": 32,
+      "_tok_33": 33,
+      "_tok_34": 34,
+      "_tok_35": 35,
+      "_tok_36": 36,
+      "_tok_37": 37,
+      "_tok_38": 38,
+      "_tok_39": 39,
+      "_tok_40": 40,
+      "_tok_41": 41,
+      "_tok_42": 42,
+      "_tok_43": 43,
+      "_tok_44": 44,
+      "_tok_45": 45,
+      "_tok_46": 46,
+      "_tok_47": 47,
+      "_tok_48": 48,
+      "_tok_49": 49,
+      "_tok_50": 50,
+      "_tok_51": 51,
+      "_tok_52": 52,
+      "_tok_53": 53,
+      "_tok_54": 54,
+      "_tok_55": 55,
+      "_tok_56": 56,
+      "_tok_57": 57,
+      "_tok_58": 58,
+      "_tok_59": 59,
+      "_tok_60": 60,
+      "_tok_61": 61,
+      "_tok_62": 62,
+      "_tok_63": 63
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}