Add 50m-100m checkpoint

50m-100m/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "model_type": "qwen3",
+  "vocab_size": 19,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 16384,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "torch_dtype": "float32"
+}

50m-100m/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0
+}

50m-100m/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8548f37f450cc73be97c15410c5592b3bfe76ff8741afc492b8be15e9b58a1d5
+size 201507992

50m-100m/tokenizer.json

@@ -0,0 +1 @@
+{"version": "1.0", "truncation": null, "padding": null, "added_tokens": [{"id": 0, "content": "<PAD>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 1, "content": "<BOS>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 2, "content": "<EOS>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 3, "content": "<BEGIN_GRID>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 4, "content": "<END_GRID>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 5, "content": "<BEGIN_ROW>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 6, "content": "<END_ROW>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 7, "content": "<INPUT>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 8, "content": "<OUTPUT>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 9, "content": "<COLOR_BLACK>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 10, "content": "<COLOR_BLUE>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 11, "content": "<COLOR_RED>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 12, "content": "<COLOR_GREEN>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 13, "content": "<COLOR_YELLOW>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 14, "content": "<COLOR_GREY>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 15, "content": "<COLOR_FUCHSIA>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 16, "content": "<COLOR_ORANGE>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 17, "content": "<COLOR_TEAL>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 18, "content": "<COLOR_BROWN>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}], "normalizer": null, "pre_tokenizer": {"type": "WhitespaceSplit"}, "post_processor": null, "decoder": {"type": "WordPiece", "prefix": "##", "cleanup": false}, "model": {"type": "WordLevel", "vocab": {"<PAD>": 0, "<BOS>": 1, "<EOS>": 2, "<BEGIN_GRID>": 3, "<END_GRID>": 4, "<BEGIN_ROW>": 5, "<END_ROW>": 6, "<INPUT>": 7, "<OUTPUT>": 8, "<COLOR_BLACK>": 9, "<COLOR_BLUE>": 10, "<COLOR_RED>": 11, "<COLOR_GREEN>": 12, "<COLOR_YELLOW>": 13, "<COLOR_GREY>": 14, "<COLOR_FUCHSIA>": 15, "<COLOR_ORANGE>": 16, "<COLOR_TEAL>": 17, "<COLOR_BROWN>": 18}, "unk_token": "<PAD>"}}

50m-100m/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<BOS>",
+  "eos_token": "<EOS>",
+  "pad_token": "<PAD>",
+  "additional_special_tokens": [
+    "<BEGIN_GRID>",
+    "<END_GRID>",
+    "<BEGIN_ROW>",
+    "<END_ROW>",
+    "<INPUT>",
+    "<OUTPUT>"
+  ],
+  "model_max_length": 16384,
+  "clean_up_tokenization_spaces": false
+}