Add GPUburnout-2B-75K base model (1.921B params, 75K growth steps, loss 2.406)

chat_template.jinja

@@ -0,0 +1,4 @@
+{% for message in messages %}<|im_start|>{{ message['role'] }}
+{{ message['content'] }}<|im_end|>
+{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2304,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 36,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 9,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": true,
+  "vocab_size": 32005
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "do_sample": true,
+  "eos_token_id": 32001,
+  "max_new_tokens": 256,
+  "pad_token_id": 1,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 50,
+  "top_p": 0.9,
+  "transformers_version": "5.3.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e92980e8efe5e380adb12d0ea456cd4617ce7e96443534fa2318a05e356f121
+size 3842387296

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}