ckpt step 13500

checkpoint-13500/config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.05,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 3,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 4096,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 20000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 50000
+}

checkpoint-13500/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0",
+  "use_cache": false
+}

checkpoint-13500/meta.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36296b1d138345a5a3ee3cfb0150989ec6da7300a0033cb4ea1277f9290ec611
+size 1243

checkpoint-13500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b148439381d0ce00de69e676b574287fb5b063d53293569cbb07761309b9a92a
+size 284924368

checkpoint-13500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9988b9b9f2f066421c5d11a89f246885374adb6c743b5af0be98dda3bc9c9a67
+size 569934091

checkpoint-13500/tokenizer_config.json

@@ -0,0 +1,100 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "eos_token": "<|eos|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|speech|>",
+    "<|frame_start|>",
+    "<|frame_end|>",
+    "<|reserved_1|>",
+    "<|reserved_2|>",
+    "<|reserved_3|>",
+    "<|reserved_4|>",
+    "<|reserved_5|>",
+    "<|reserved_6|>",
+    "<|reserved_7|>",
+    "<|reserved_8|>",
+    "<|reserved_9|>",
+    "<|reserved_10|>",
+    "<|reserved_11|>",
+    "<|reserved_12|>",
+    "<|reserved_13|>",
+    "<|reserved_14|>",
+    "<|reserved_15|>",
+    "<|reserved_16|>",
+    "<|reserved_17|>",
+    "<|reserved_18|>",
+    "<|reserved_19|>",
+    "<|reserved_20|>",
+    "<|reserved_21|>",
+    "<|reserved_22|>",
+    "<|reserved_23|>",
+    "<|reserved_24|>",
+    "<|reserved_25|>",
+    "<|reserved_26|>",
+    "<|reserved_27|>",
+    "<|reserved_28|>",
+    "<|reserved_29|>",
+    "<|reserved_30|>",
+    "<|reserved_31|>",
+    "<|reserved_32|>",
+    "<|reserved_33|>",
+    "<|reserved_34|>",
+    "<|reserved_35|>",
+    "<|reserved_36|>",
+    "<|reserved_37|>",
+    "<|reserved_38|>",
+    "<|reserved_39|>",
+    "<|reserved_40|>",
+    "<|reserved_41|>",
+    "<|reserved_42|>",
+    "<|reserved_43|>",
+    "<|reserved_44|>",
+    "<|reserved_45|>",
+    "<|reserved_46|>",
+    "<|reserved_47|>",
+    "<|reserved_48|>",
+    "<|reserved_49|>",
+    "<|reserved_50|>",
+    "<|reserved_51|>",
+    "<|reserved_52|>",
+    "<|reserved_53|>",
+    "<|reserved_54|>",
+    "<|reserved_55|>",
+    "<|reserved_56|>",
+    "<|reserved_57|>",
+    "<|reserved_58|>",
+    "<|reserved_59|>",
+    "<|reserved_60|>",
+    "<|reserved_61|>",
+    "<|reserved_62|>",
+    "<|reserved_63|>",
+    "<|reserved_64|>",
+    "<|reserved_65|>",
+    "<|reserved_66|>",
+    "<|reserved_67|>",
+    "<|reserved_68|>",
+    "<|reserved_69|>",
+    "<|reserved_70|>",
+    "<|reserved_71|>",
+    "<|reserved_72|>",
+    "<|reserved_73|>",
+    "<|reserved_74|>",
+    "<|reserved_75|>",
+    "<|reserved_76|>",
+    "<|reserved_77|>",
+    "<|reserved_78|>",
+    "<|reserved_79|>",
+    "<|reserved_80|>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}