step 5000

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}

config.json

@@ -0,0 +1,106 @@
+{
+  "N": 20,
+  "base_config_dict": {
+    "_name_or_path": "microsoft/phi-4",
+    "architectures": [
+      "Phi3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 100257,
+    "chunk_size_feed_forward": 0,
+    "dtype": "bfloat16",
+    "embd_pdrop": 0.0,
+    "eos_token_id": 100265,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "ignore_keys_at_rope_validation": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 17920,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 16384,
+    "model_type": "phi3",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 10,
+    "original_max_position_embeddings": 16384,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 100349,
+    "partial_rotary_factor": 1.0,
+    "problem_type": null,
+    "resid_pdrop": 0.0,
+    "return_dict": true,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "partial_rotary_factor": 1.0,
+      "rope_theta": 250000,
+      "rope_type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "transformers_version": "5.3.0",
+    "use_cache": true,
+    "vocab_size": 100352
+  },
+  "base_model_name_or_path": "microsoft/phi-4",
+  "decoder_layer_indices": [
+    39
+  ],
+  "encoder_layer_indices": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5
+  ],
+  "hidden_size": 5120,
+  "model_type": "lds",
+  "q_threshold": 0.9,
+  "reasoning_layer_indices": [
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38
+  ],
+  "transformers_version": "5.3.0",
+  "vocab_size": 100352
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdcd1cdc1c6fb2ec6cc441929a853affc597a38e137110896f02ea6ce754d4cb
+size 29332254348

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "model_max_length": 16384,
+  "pad_token": "<|dummy_85|>",
+  "tokenizer_class": "TokenizersBackend"
+}