Upload 17 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

latest

@@ -0,0 +1 @@
+global_step171

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d39ceabc4f6b42b3600247bb5e3ea35b765f0f70e6d51beb19fdf3fcf77551
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1faa4350c83df94636f6793ac265111a4f7dda4ebab8f6c43b569e9a00137701
+size 1214366696

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 6171877376
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba7f728467bf9dbb04dbb20b49184fb30af042cce85760bc1ca3a49a78b9761
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1231 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9978118161925602,
+  "eval_steps": 500,
+  "global_step": 171,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005835156819839533,
+      "grad_norm": 3.0967645370477803,
+      "learning_rate": 0.0,
+      "loss": 1.0698,
+      "step": 1
+    },
+    {
+      "epoch": 0.011670313639679067,
+      "grad_norm": 3.240964653147952,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 1.0714,
+      "step": 2
+    },
+    {
+      "epoch": 0.0175054704595186,
+      "grad_norm": 3.286415256381705,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.1575,
+      "step": 3
+    },
+    {
+      "epoch": 0.023340627279358133,
+      "grad_norm": 4.198907257722359,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.359,
+      "step": 4
+    },
+    {
+      "epoch": 0.029175784099197667,
+      "grad_norm": 3.4693235279579637,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.9649,
+      "step": 5
+    },
+    {
+      "epoch": 0.0350109409190372,
+      "grad_norm": 3.0568945268705883,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 1.0989,
+      "step": 6
+    },
+    {
+      "epoch": 0.040846097738876735,
+      "grad_norm": 2.2641958909637157,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.9482,
+      "step": 7
+    },
+    {
+      "epoch": 0.046681254558716266,
+      "grad_norm": 2.5090273909864367,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 1.1167,
+      "step": 8
+    },
+    {
+      "epoch": 0.0525164113785558,
+      "grad_norm": 1.976815998901389,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.0178,
+      "step": 9
+    },
+    {
+      "epoch": 0.058351568198395334,
+      "grad_norm": 2.1819711414316108,
+      "learning_rate": 5e-06,
+      "loss": 1.2776,
+      "step": 10
+    },
+    {
+      "epoch": 0.06418672501823487,
+      "grad_norm": 1.8201699012478207,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.1955,
+      "step": 11
+    },
+    {
+      "epoch": 0.0700218818380744,
+      "grad_norm": 1.5462205611641233,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": 0.9814,
+      "step": 12
+    },
+    {
+      "epoch": 0.07585703865791393,
+      "grad_norm": 1.8781521337402638,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0493,
+      "step": 13
+    },
+    {
+      "epoch": 0.08169219547775347,
+      "grad_norm": 1.7561324099023312,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": 0.9224,
+      "step": 14
+    },
+    {
+      "epoch": 0.087527352297593,
+      "grad_norm": 1.4418880184516636,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.8082,
+      "step": 15
+    },
+    {
+      "epoch": 0.09336250911743253,
+      "grad_norm": 1.8346753334483505,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.0255,
+      "step": 16
+    },
+    {
+      "epoch": 0.09919766593727207,
+      "grad_norm": 1.5851713574171153,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.9778,
+      "step": 17
+    },
+    {
+      "epoch": 0.1050328227571116,
+      "grad_norm": 1.670718527610444,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.9377,
+      "step": 18
+    },
+    {
+      "epoch": 0.11086797957695113,
+      "grad_norm": 1.6015249574772341,
+      "learning_rate": 1e-05,
+      "loss": 0.9287,
+      "step": 19
+    },
+    {
+      "epoch": 0.11670313639679067,
+      "grad_norm": 1.6989482004469072,
+      "learning_rate": 9.998945997517957e-06,
+      "loss": 1.152,
+      "step": 20
+    },
+    {
+      "epoch": 0.12253829321663019,
+      "grad_norm": 1.3452249233397808,
+      "learning_rate": 9.99578443444032e-06,
+      "loss": 0.8807,
+      "step": 21
+    },
+    {
+      "epoch": 0.12837345003646974,
+      "grad_norm": 2.1487234818996686,
+      "learning_rate": 9.990516643685222e-06,
+      "loss": 0.7627,
+      "step": 22
+    },
+    {
+      "epoch": 0.13420860685630925,
+      "grad_norm": 1.923473946779632,
+      "learning_rate": 9.983144846158472e-06,
+      "loss": 1.2667,
+      "step": 23
+    },
+    {
+      "epoch": 0.1400437636761488,
+      "grad_norm": 1.1277306360256565,
+      "learning_rate": 9.973672149817232e-06,
+      "loss": 0.7689,
+      "step": 24
+    },
+    {
+      "epoch": 0.14587892049598833,
+      "grad_norm": 1.1475575701592111,
+      "learning_rate": 9.96210254835968e-06,
+      "loss": 0.7796,
+      "step": 25
+    },
+    {
+      "epoch": 0.15171407731582787,
+      "grad_norm": 1.423352108857882,
+      "learning_rate": 9.948440919541277e-06,
+      "loss": 1.0162,
+      "step": 26
+    },
+    {
+      "epoch": 0.1575492341356674,
+      "grad_norm": 1.3087161085162522,
+      "learning_rate": 9.932693023118299e-06,
+      "loss": 0.9945,
+      "step": 27
+    },
+    {
+      "epoch": 0.16338439095550694,
+      "grad_norm": 1.3363607553089747,
+      "learning_rate": 9.91486549841951e-06,
+      "loss": 0.8672,
+      "step": 28
+    },
+    {
+      "epoch": 0.16921954777534645,
+      "grad_norm": 1.1887359433001867,
+      "learning_rate": 9.894965861547023e-06,
+      "loss": 0.9,
+      "step": 29
+    },
+    {
+      "epoch": 0.175054704595186,
+      "grad_norm": 1.3150047218140335,
+      "learning_rate": 9.873002502207502e-06,
+      "loss": 0.786,
+      "step": 30
+    },
+    {
+      "epoch": 0.18088986141502553,
+      "grad_norm": 1.3895338060465705,
+      "learning_rate": 9.848984680175049e-06,
+      "loss": 0.935,
+      "step": 31
+    },
+    {
+      "epoch": 0.18672501823486506,
+      "grad_norm": 1.3275940096513228,
+      "learning_rate": 9.822922521387277e-06,
+      "loss": 0.804,
+      "step": 32
+    },
+    {
+      "epoch": 0.1925601750547046,
+      "grad_norm": 1.0560366942912123,
+      "learning_rate": 9.794827013676206e-06,
+      "loss": 0.7541,
+      "step": 33
+    },
+    {
+      "epoch": 0.19839533187454414,
+      "grad_norm": 0.9888394869609451,
+      "learning_rate": 9.764710002135784e-06,
+      "loss": 0.6956,
+      "step": 34
+    },
+    {
+      "epoch": 0.20423048869438365,
+      "grad_norm": 1.5276601674154802,
+      "learning_rate": 9.732584184127973e-06,
+      "loss": 1.1283,
+      "step": 35
+    },
+    {
+      "epoch": 0.2100656455142232,
+      "grad_norm": 1.0255635415282915,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.7307,
+      "step": 36
+    },
+    {
+      "epoch": 0.21590080233406272,
+      "grad_norm": 1.3172712637289348,
+      "learning_rate": 9.66236114702178e-06,
+      "loss": 0.912,
+      "step": 37
+    },
+    {
+      "epoch": 0.22173595915390226,
+      "grad_norm": 1.2265556745233968,
+      "learning_rate": 9.62429353402556e-06,
+      "loss": 0.8612,
+      "step": 38
+    },
+    {
+      "epoch": 0.2275711159737418,
+      "grad_norm": 1.382293666822052,
+      "learning_rate": 9.584276314284316e-06,
+      "loss": 0.9029,
+      "step": 39
+    },
+    {
+      "epoch": 0.23340627279358134,
+      "grad_norm": 1.4564772263747658,
+      "learning_rate": 9.542326359097619e-06,
+      "loss": 0.9388,
+      "step": 40
+    },
+    {
+      "epoch": 0.23924142961342085,
+      "grad_norm": 1.0351934922881194,
+      "learning_rate": 9.498461354608228e-06,
+      "loss": 0.7048,
+      "step": 41
+    },
+    {
+      "epoch": 0.24507658643326038,
+      "grad_norm": 1.1855152897517165,
+      "learning_rate": 9.452699794345583e-06,
+      "loss": 0.8375,
+      "step": 42
+    },
+    {
+      "epoch": 0.25091174325309995,
+      "grad_norm": 0.9858455620030542,
+      "learning_rate": 9.405060971428924e-06,
+      "loss": 0.6869,
+      "step": 43
+    },
+    {
+      "epoch": 0.2567469000729395,
+      "grad_norm": 0.9902232882820138,
+      "learning_rate": 9.355564970433288e-06,
+      "loss": 0.7302,
+      "step": 44
+    },
+    {
+      "epoch": 0.26258205689277897,
+      "grad_norm": 1.0675035604533485,
+      "learning_rate": 9.30423265892184e-06,
+      "loss": 0.8118,
+      "step": 45
+    },
+    {
+      "epoch": 0.2684172137126185,
+      "grad_norm": 1.3867123886210095,
+      "learning_rate": 9.251085678648072e-06,
+      "loss": 1.0246,
+      "step": 46
+    },
+    {
+      "epoch": 0.27425237053245805,
+      "grad_norm": 1.5259388197713282,
+      "learning_rate": 9.196146436431635e-06,
+      "loss": 1.1016,
+      "step": 47
+    },
+    {
+      "epoch": 0.2800875273522976,
+      "grad_norm": 1.2982224709981671,
+      "learning_rate": 9.13943809471159e-06,
+      "loss": 0.9131,
+      "step": 48
+    },
+    {
+      "epoch": 0.2859226841721371,
+      "grad_norm": 1.0192488730773452,
+      "learning_rate": 9.08098456178111e-06,
+      "loss": 0.6878,
+      "step": 49
+    },
+    {
+      "epoch": 0.29175784099197666,
+      "grad_norm": 1.3595848189757955,
+      "learning_rate": 9.020810481707709e-06,
+      "loss": 0.9331,
+      "step": 50
+    },
+    {
+      "epoch": 0.2975929978118162,
+      "grad_norm": 0.8812342597637117,
+      "learning_rate": 8.958941223943292e-06,
+      "loss": 0.6287,
+      "step": 51
+    },
+    {
+      "epoch": 0.30342815463165573,
+      "grad_norm": 1.2990640418383663,
+      "learning_rate": 8.895402872628352e-06,
+      "loss": 0.9154,
+      "step": 52
+    },
+    {
+      "epoch": 0.30926331145149527,
+      "grad_norm": 1.2083829619551534,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.8133,
+      "step": 53
+    },
+    {
+      "epoch": 0.3150984682713348,
+      "grad_norm": 1.1431625625586879,
+      "learning_rate": 8.763426733072624e-06,
+      "loss": 0.7709,
+      "step": 54
+    },
+    {
+      "epoch": 0.32093362509117435,
+      "grad_norm": 1.0434131741083061,
+      "learning_rate": 8.695044586103297e-06,
+      "loss": 0.8007,
+      "step": 55
+    },
+    {
+      "epoch": 0.3267687819110139,
+      "grad_norm": 1.0904984432710232,
+      "learning_rate": 8.625104604667965e-06,
+      "loss": 0.8123,
+      "step": 56
+    },
+    {
+      "epoch": 0.33260393873085337,
+      "grad_norm": 0.920394581392736,
+      "learning_rate": 8.553636275532236e-06,
+      "loss": 0.6425,
+      "step": 57
+    },
+    {
+      "epoch": 0.3384390955506929,
+      "grad_norm": 1.1503386459221627,
+      "learning_rate": 8.480669729814635e-06,
+      "loss": 0.7206,
+      "step": 58
+    },
+    {
+      "epoch": 0.34427425237053244,
+      "grad_norm": 1.090627383298351,
+      "learning_rate": 8.40623573028327e-06,
+      "loss": 0.7557,
+      "step": 59
+    },
+    {
+      "epoch": 0.350109409190372,
+      "grad_norm": 1.2240349403722315,
+      "learning_rate": 8.330365658386252e-06,
+      "loss": 0.896,
+      "step": 60
+    },
+    {
+      "epoch": 0.3559445660102115,
+      "grad_norm": 1.0765178282667567,
+      "learning_rate": 8.25309150102121e-06,
+      "loss": 0.7681,
+      "step": 61
+    },
+    {
+      "epoch": 0.36177972283005105,
+      "grad_norm": 0.9793957317021386,
+      "learning_rate": 8.174445837049614e-06,
+      "loss": 0.7504,
+      "step": 62
+    },
+    {
+      "epoch": 0.3676148796498906,
+      "grad_norm": 1.2232761418608094,
+      "learning_rate": 8.094461823561473e-06,
+      "loss": 0.8488,
+      "step": 63
+    },
+    {
+      "epoch": 0.37345003646973013,
+      "grad_norm": 1.2088998059050347,
+      "learning_rate": 8.013173181896283e-06,
+      "loss": 0.8523,
+      "step": 64
+    },
+    {
+      "epoch": 0.37928519328956967,
+      "grad_norm": 1.2900325123864722,
+      "learning_rate": 7.930614183426074e-06,
+      "loss": 0.8181,
+      "step": 65
+    },
+    {
+      "epoch": 0.3851203501094092,
+      "grad_norm": 0.9454791838776316,
+      "learning_rate": 7.846819635106569e-06,
+      "loss": 0.7437,
+      "step": 66
+    },
+    {
+      "epoch": 0.39095550692924874,
+      "grad_norm": 0.9144587470068872,
+      "learning_rate": 7.76182486480253e-06,
+      "loss": 0.628,
+      "step": 67
+    },
+    {
+      "epoch": 0.3967906637490883,
+      "grad_norm": 1.15724937547755,
+      "learning_rate": 7.675665706393502e-06,
+      "loss": 0.871,
+      "step": 68
+    },
+    {
+      "epoch": 0.4026258205689278,
+      "grad_norm": 1.5015191452686714,
+      "learning_rate": 7.588378484666214e-06,
+      "loss": 1.0221,
+      "step": 69
+    },
+    {
+      "epoch": 0.4084609773887673,
+      "grad_norm": 1.39998905729372,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.9229,
+      "step": 70
+    },
+    {
+      "epoch": 0.41429613420860684,
+      "grad_norm": 0.948492711117696,
+      "learning_rate": 7.4105675128517456e-06,
+      "loss": 0.6874,
+      "step": 71
+    },
+    {
+      "epoch": 0.4201312910284464,
+      "grad_norm": 1.258374093991861,
+      "learning_rate": 7.320118728046818e-06,
+      "loss": 0.9105,
+      "step": 72
+    },
+    {
+      "epoch": 0.4259664478482859,
+      "grad_norm": 0.9884107530136707,
+      "learning_rate": 7.2286917788826926e-06,
+      "loss": 0.6701,
+      "step": 73
+    },
+    {
+      "epoch": 0.43180160466812545,
+      "grad_norm": 1.4165000586156353,
+      "learning_rate": 7.136325211051905e-06,
+      "loss": 1.0041,
+      "step": 74
+    },
+    {
+      "epoch": 0.437636761487965,
+      "grad_norm": 1.1602616170268807,
+      "learning_rate": 7.043057966391158e-06,
+      "loss": 0.8137,
+      "step": 75
+    },
+    {
+      "epoch": 0.4434719183078045,
+      "grad_norm": 0.8628006157003906,
+      "learning_rate": 6.948929366463397e-06,
+      "loss": 0.6294,
+      "step": 76
+    },
+    {
+      "epoch": 0.44930707512764406,
+      "grad_norm": 1.0039942958404424,
+      "learning_rate": 6.8539790959798045e-06,
+      "loss": 0.7109,
+      "step": 77
+    },
+    {
+      "epoch": 0.4551422319474836,
+      "grad_norm": 1.3931149797330953,
+      "learning_rate": 6.758247186068684e-06,
+      "loss": 0.9198,
+      "step": 78
+    },
+    {
+      "epoch": 0.46097738876732314,
+      "grad_norm": 1.0513701294639524,
+      "learning_rate": 6.6617739973982985e-06,
+      "loss": 0.7459,
+      "step": 79
+    },
+    {
+      "epoch": 0.4668125455871627,
+      "grad_norm": 1.028695671279348,
+      "learning_rate": 6.5646002031607726e-06,
+      "loss": 0.746,
+      "step": 80
+    },
+    {
+      "epoch": 0.4726477024070022,
+      "grad_norm": 0.9959898755507389,
+      "learning_rate": 6.466766771924231e-06,
+      "loss": 0.8316,
+      "step": 81
+    },
+    {
+      "epoch": 0.4784828592268417,
+      "grad_norm": 1.0084464738139896,
+      "learning_rate": 6.368314950360416e-06,
+      "loss": 0.6801,
+      "step": 82
+    },
+    {
+      "epoch": 0.48431801604668123,
+      "grad_norm": 1.2115089332593143,
+      "learning_rate": 6.269286245855039e-06,
+      "loss": 0.9926,
+      "step": 83
+    },
+    {
+      "epoch": 0.49015317286652077,
+      "grad_norm": 1.0623534367007055,
+      "learning_rate": 6.169722409008244e-06,
+      "loss": 0.7846,
+      "step": 84
+    },
+    {
+      "epoch": 0.4959883296863603,
+      "grad_norm": 0.9618691552575331,
+      "learning_rate": 6.0696654160324875e-06,
+      "loss": 0.7579,
+      "step": 85
+    },
+    {
+      "epoch": 0.5018234865061999,
+      "grad_norm": 1.4236190190616003,
+      "learning_rate": 5.9691574510553505e-06,
+      "loss": 0.9145,
+      "step": 86
+    },
+    {
+      "epoch": 0.5076586433260394,
+      "grad_norm": 0.9781934808099418,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.7268,
+      "step": 87
+    },
+    {
+      "epoch": 0.513493800145879,
+      "grad_norm": 1.4459804636005047,
+      "learning_rate": 5.766958274393428e-06,
+      "loss": 0.9873,
+      "step": 88
+    },
+    {
+      "epoch": 0.5193289569657185,
+      "grad_norm": 1.402656043092622,
+      "learning_rate": 5.66535231008227e-06,
+      "loss": 0.9982,
+      "step": 89
+    },
+    {
+      "epoch": 0.5251641137855579,
+      "grad_norm": 1.0200801826456665,
+      "learning_rate": 5.5634658325766066e-06,
+      "loss": 0.678,
+      "step": 90
+    },
+    {
+      "epoch": 0.5309992706053975,
+      "grad_norm": 0.9733189988828815,
+      "learning_rate": 5.46134179731651e-06,
+      "loss": 0.7651,
+      "step": 91
+    },
+    {
+      "epoch": 0.536834427425237,
+      "grad_norm": 1.4664206961259343,
+      "learning_rate": 5.359023259896638e-06,
+      "loss": 1.1306,
+      "step": 92
+    },
+    {
+      "epoch": 0.5426695842450766,
+      "grad_norm": 0.8504168428338762,
+      "learning_rate": 5.2565533579139484e-06,
+      "loss": 0.63,
+      "step": 93
+    },
+    {
+      "epoch": 0.5485047410649161,
+      "grad_norm": 0.9453356240059136,
+      "learning_rate": 5.153975292780852e-06,
+      "loss": 0.7414,
+      "step": 94
+    },
+    {
+      "epoch": 0.5543398978847557,
+      "grad_norm": 1.2873508014079351,
+      "learning_rate": 5.05133231151145e-06,
+      "loss": 0.9491,
+      "step": 95
+    },
+    {
+      "epoch": 0.5601750547045952,
+      "grad_norm": 1.120596468774601,
+      "learning_rate": 4.948667688488552e-06,
+      "loss": 0.8434,
+      "step": 96
+    },
+    {
+      "epoch": 0.5660102115244348,
+      "grad_norm": 0.933260578220278,
+      "learning_rate": 4.846024707219149e-06,
+      "loss": 0.6954,
+      "step": 97
+    },
+    {
+      "epoch": 0.5718453683442742,
+      "grad_norm": 1.1505604485932606,
+      "learning_rate": 4.7434466420860515e-06,
+      "loss": 0.8766,
+      "step": 98
+    },
+    {
+      "epoch": 0.5776805251641138,
+      "grad_norm": 1.3190064743230776,
+      "learning_rate": 4.640976740103363e-06,
+      "loss": 0.9601,
+      "step": 99
+    },
+    {
+      "epoch": 0.5835156819839533,
+      "grad_norm": 1.1031574587195832,
+      "learning_rate": 4.53865820268349e-06,
+      "loss": 0.8262,
+      "step": 100
+    },
+    {
+      "epoch": 0.5893508388037928,
+      "grad_norm": 1.2140720848727085,
+      "learning_rate": 4.436534167423395e-06,
+      "loss": 0.8474,
+      "step": 101
+    },
+    {
+      "epoch": 0.5951859956236324,
+      "grad_norm": 1.0868094387995848,
+      "learning_rate": 4.334647689917734e-06,
+      "loss": 0.7998,
+      "step": 102
+    },
+    {
+      "epoch": 0.6010211524434719,
+      "grad_norm": 1.0979874833235823,
+      "learning_rate": 4.233041725606573e-06,
+      "loss": 0.7538,
+      "step": 103
+    },
+    {
+      "epoch": 0.6068563092633115,
+      "grad_norm": 0.8239976607859979,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.6354,
+      "step": 104
+    },
+    {
+      "epoch": 0.612691466083151,
+      "grad_norm": 1.2986211049877099,
+      "learning_rate": 4.03084254894465e-06,
+      "loss": 0.8842,
+      "step": 105
+    },
+    {
+      "epoch": 0.6185266229029905,
+      "grad_norm": 1.4668023858002492,
+      "learning_rate": 3.930334583967514e-06,
+      "loss": 1.1808,
+      "step": 106
+    },
+    {
+      "epoch": 0.62436177972283,
+      "grad_norm": 0.9088094469191689,
+      "learning_rate": 3.8302775909917585e-06,
+      "loss": 0.7396,
+      "step": 107
+    },
+    {
+      "epoch": 0.6301969365426696,
+      "grad_norm": 1.1598630921383477,
+      "learning_rate": 3.730713754144961e-06,
+      "loss": 0.8171,
+      "step": 108
+    },
+    {
+      "epoch": 0.6360320933625091,
+      "grad_norm": 0.9110392040510746,
+      "learning_rate": 3.6316850496395863e-06,
+      "loss": 0.7386,
+      "step": 109
+    },
+    {
+      "epoch": 0.6418672501823487,
+      "grad_norm": 1.4073871245462084,
+      "learning_rate": 3.5332332280757706e-06,
+      "loss": 0.8708,
+      "step": 110
+    },
+    {
+      "epoch": 0.6477024070021882,
+      "grad_norm": 1.0974400375996476,
+      "learning_rate": 3.4353997968392295e-06,
+      "loss": 0.7883,
+      "step": 111
+    },
+    {
+      "epoch": 0.6535375638220278,
+      "grad_norm": 0.9061825638441261,
+      "learning_rate": 3.3382260026017027e-06,
+      "loss": 0.6915,
+      "step": 112
+    },
+    {
+      "epoch": 0.6593727206418672,
+      "grad_norm": 1.0771803335915262,
+      "learning_rate": 3.241752813931316e-06,
+      "loss": 0.8647,
+      "step": 113
+    },
+    {
+      "epoch": 0.6652078774617067,
+      "grad_norm": 0.9568570846689433,
+      "learning_rate": 3.1460209040201967e-06,
+      "loss": 0.743,
+      "step": 114
+    },
+    {
+      "epoch": 0.6710430342815463,
+      "grad_norm": 0.8038754456744998,
+      "learning_rate": 3.0510706335366034e-06,
+      "loss": 0.6186,
+      "step": 115
+    },
+    {
+      "epoch": 0.6768781911013858,
+      "grad_norm": 1.0490487646998612,
+      "learning_rate": 2.956942033608843e-06,
+      "loss": 0.7842,
+      "step": 116
+    },
+    {
+      "epoch": 0.6827133479212254,
+      "grad_norm": 1.1528124191592586,
+      "learning_rate": 2.863674788948097e-06,
+      "loss": 0.8293,
+      "step": 117
+    },
+    {
+      "epoch": 0.6885485047410649,
+      "grad_norm": 1.1151481901518225,
+      "learning_rate": 2.771308221117309e-06,
+      "loss": 0.8212,
+      "step": 118
+    },
+    {
+      "epoch": 0.6943836615609045,
+      "grad_norm": 0.9417128722043704,
+      "learning_rate": 2.6798812719531843e-06,
+      "loss": 0.6844,
+      "step": 119
+    },
+    {
+      "epoch": 0.700218818380744,
+      "grad_norm": 1.032191371370444,
+      "learning_rate": 2.5894324871482557e-06,
+      "loss": 0.8145,
+      "step": 120
+    },
+    {
+      "epoch": 0.7060539752005836,
+      "grad_norm": 0.8894619973494138,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.7,
+      "step": 121
+    },
+    {
+      "epoch": 0.711889132020423,
+      "grad_norm": 1.0056726773650362,
+      "learning_rate": 2.411621515333788e-06,
+      "loss": 0.7701,
+      "step": 122
+    },
+    {
+      "epoch": 0.7177242888402626,
+      "grad_norm": 1.0869409622185178,
+      "learning_rate": 2.324334293606499e-06,
+      "loss": 0.8878,
+      "step": 123
+    },
+    {
+      "epoch": 0.7235594456601021,
+      "grad_norm": 0.9975686046452821,
+      "learning_rate": 2.238175135197471e-06,
+      "loss": 0.7396,
+      "step": 124
+    },
+    {
+      "epoch": 0.7293946024799417,
+      "grad_norm": 0.9651532423367729,
+      "learning_rate": 2.1531803648934333e-06,
+      "loss": 0.7326,
+      "step": 125
+    },
+    {
+      "epoch": 0.7352297592997812,
+      "grad_norm": 1.2022500141898183,
+      "learning_rate": 2.069385816573928e-06,
+      "loss": 0.8903,
+      "step": 126
+    },
+    {
+      "epoch": 0.7410649161196207,
+      "grad_norm": 1.1194585298700934,
+      "learning_rate": 1.9868268181037186e-06,
+      "loss": 0.7492,
+      "step": 127
+    },
+    {
+      "epoch": 0.7469000729394603,
+      "grad_norm": 0.9563972874909548,
+      "learning_rate": 1.9055381764385272e-06,
+      "loss": 0.7019,
+      "step": 128
+    },
+    {
+      "epoch": 0.7527352297592997,
+      "grad_norm": 1.1116002934004348,
+      "learning_rate": 1.8255541629503865e-06,
+      "loss": 0.8464,
+      "step": 129
+    },
+    {
+      "epoch": 0.7585703865791393,
+      "grad_norm": 0.9834353364914193,
+      "learning_rate": 1.746908498978791e-06,
+      "loss": 0.7098,
+      "step": 130
+    },
+    {
+      "epoch": 0.7644055433989788,
+      "grad_norm": 0.9133138576459355,
+      "learning_rate": 1.6696343416137495e-06,
+      "loss": 0.7116,
+      "step": 131
+    },
+    {
+      "epoch": 0.7702407002188184,
+      "grad_norm": 1.1533333715544398,
+      "learning_rate": 1.5937642697167288e-06,
+      "loss": 0.8582,
+      "step": 132
+    },
+    {
+      "epoch": 0.7760758570386579,
+      "grad_norm": 1.1643056283458053,
+      "learning_rate": 1.5193302701853674e-06,
+      "loss": 0.8634,
+      "step": 133
+    },
+    {
+      "epoch": 0.7819110138584975,
+      "grad_norm": 1.2470889663194495,
+      "learning_rate": 1.4463637244677648e-06,
+      "loss": 1.0618,
+      "step": 134
+    },
+    {
+      "epoch": 0.787746170678337,
+      "grad_norm": 1.137971799681056,
+      "learning_rate": 1.374895395332037e-06,
+      "loss": 0.7659,
+      "step": 135
+    },
+    {
+      "epoch": 0.7935813274981766,
+      "grad_norm": 0.8296991248159793,
+      "learning_rate": 1.3049554138967052e-06,
+      "loss": 0.6202,
+      "step": 136
+    },
+    {
+      "epoch": 0.799416484318016,
+      "grad_norm": 1.267967690991332,
+      "learning_rate": 1.2365732669273778e-06,
+      "loss": 0.7476,
+      "step": 137
+    },
+    {
+      "epoch": 0.8052516411378556,
+      "grad_norm": 1.0879072186919871,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.7832,
+      "step": 138
+    },
+    {
+      "epoch": 0.8110867979576951,
+      "grad_norm": 0.9784037046492985,
+      "learning_rate": 1.1045971273716476e-06,
+      "loss": 0.75,
+      "step": 139
+    },
+    {
+      "epoch": 0.8169219547775346,
+      "grad_norm": 0.969625700866293,
+      "learning_rate": 1.0410587760567104e-06,
+      "loss": 0.8109,
+      "step": 140
+    },
+    {
+      "epoch": 0.8227571115973742,
+      "grad_norm": 1.0370004026477495,
+      "learning_rate": 9.791895182922911e-07,
+      "loss": 0.7486,
+      "step": 141
+    },
+    {
+      "epoch": 0.8285922684172137,
+      "grad_norm": 1.313976521343513,
+      "learning_rate": 9.190154382188921e-07,
+      "loss": 0.9392,
+      "step": 142
+    },
+    {
+      "epoch": 0.8344274252370533,
+      "grad_norm": 1.3968351116673179,
+      "learning_rate": 8.605619052884106e-07,
+      "loss": 1.0106,
+      "step": 143
+    },
+    {
+      "epoch": 0.8402625820568927,
+      "grad_norm": 0.9927938469465771,
+      "learning_rate": 8.03853563568367e-07,
+      "loss": 0.7784,
+      "step": 144
+    },
+    {
+      "epoch": 0.8460977388767323,
+      "grad_norm": 0.9788007150864164,
+      "learning_rate": 7.489143213519301e-07,
+      "loss": 0.8396,
+      "step": 145
+    },
+    {
+      "epoch": 0.8519328956965718,
+      "grad_norm": 1.0639499300007744,
+      "learning_rate": 6.957673410781617e-07,
+      "loss": 0.7964,
+      "step": 146
+    },
+    {
+      "epoch": 0.8577680525164114,
+      "grad_norm": 1.2358144380534066,
+      "learning_rate": 6.444350295667112e-07,
+      "loss": 0.8458,
+      "step": 147
+    },
+    {
+      "epoch": 0.8636032093362509,
+      "grad_norm": 1.1284354446219842,
+      "learning_rate": 5.949390285710777e-07,
+      "loss": 0.8905,
+      "step": 148
+    },
+    {
+      "epoch": 0.8694383661560905,
+      "grad_norm": 0.9040214380343765,
+      "learning_rate": 5.473002056544191e-07,
+      "loss": 0.7118,
+      "step": 149
+    },
+    {
+      "epoch": 0.87527352297593,
+      "grad_norm": 0.9693967414133844,
+      "learning_rate": 5.015386453917742e-07,
+      "loss": 0.7273,
+      "step": 150
+    },
+    {
+      "epoch": 0.8811086797957695,
+      "grad_norm": 1.08806034257909,
+      "learning_rate": 4.576736409023813e-07,
+      "loss": 0.762,
+      "step": 151
+    },
+    {
+      "epoch": 0.886943836615609,
+      "grad_norm": 1.0602639261817013,
+      "learning_rate": 4.15723685715686e-07,
+      "loss": 0.8823,
+      "step": 152
+    },
+    {
+      "epoch": 0.8927789934354485,
+      "grad_norm": 1.015659074679919,
+      "learning_rate": 3.7570646597444196e-07,
+      "loss": 0.8069,
+      "step": 153
+    },
+    {
+      "epoch": 0.8986141502552881,
+      "grad_norm": 1.1556479384409875,
+      "learning_rate": 3.3763885297822153e-07,
+      "loss": 0.9008,
+      "step": 154
+    },
+    {
+      "epoch": 0.9044493070751276,
+      "grad_norm": 1.1155559090709997,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.7752,
+      "step": 155
+    },
+    {
+      "epoch": 0.9102844638949672,
+      "grad_norm": 1.1402114085019883,
+      "learning_rate": 2.6741581587202747e-07,
+      "loss": 0.849,
+      "step": 156
+    },
+    {
+      "epoch": 0.9161196207148067,
+      "grad_norm": 1.0419920776286093,
+      "learning_rate": 2.3528999786421758e-07,
+      "loss": 0.8142,
+      "step": 157
+    },
+    {
+      "epoch": 0.9219547775346463,
+      "grad_norm": 1.1306470417466037,
+      "learning_rate": 2.0517298632379445e-07,
+      "loss": 0.8408,
+      "step": 158
+    },
+    {
+      "epoch": 0.9277899343544858,
+      "grad_norm": 1.125391381754142,
+      "learning_rate": 1.770774786127244e-07,
+      "loss": 0.7793,
+      "step": 159
+    },
+    {
+      "epoch": 0.9336250911743253,
+      "grad_norm": 0.8803202289480606,
+      "learning_rate": 1.510153198249531e-07,
+      "loss": 0.7106,
+      "step": 160
+    },
+    {
+      "epoch": 0.9394602479941648,
+      "grad_norm": 0.9210847874254954,
+      "learning_rate": 1.2699749779249926e-07,
+      "loss": 0.6821,
+      "step": 161
+    },
+    {
+      "epoch": 0.9452954048140044,
+      "grad_norm": 1.0075752224421093,
+      "learning_rate": 1.0503413845297739e-07,
+      "loss": 0.8513,
+      "step": 162
+    },
+    {
+      "epoch": 0.9511305616338439,
+      "grad_norm": 0.8750161290165441,
+      "learning_rate": 8.513450158049109e-08,
+      "loss": 0.7585,
+      "step": 163
+    },
+    {
+      "epoch": 0.9569657184536834,
+      "grad_norm": 1.1096291136415941,
+      "learning_rate": 6.730697688170251e-08,
+      "loss": 0.8467,
+      "step": 164
+    },
+    {
+      "epoch": 0.962800875273523,
+      "grad_norm": 0.9247194424342008,
+      "learning_rate": 5.155908045872349e-08,
+      "loss": 0.7033,
+      "step": 165
+    },
+    {
+      "epoch": 0.9686360320933625,
+      "grad_norm": 0.9831793236532468,
+      "learning_rate": 3.7897451640321326e-08,
+      "loss": 0.7581,
+      "step": 166
+    },
+    {
+      "epoch": 0.9744711889132021,
+      "grad_norm": 0.9263535840213669,
+      "learning_rate": 2.6327850182769065e-08,
+      "loss": 0.697,
+      "step": 167
+    },
+    {
+      "epoch": 0.9803063457330415,
+      "grad_norm": 0.9615311264525579,
+      "learning_rate": 1.6855153841527915e-08,
+      "loss": 0.6953,
+      "step": 168
+    },
+    {
+      "epoch": 0.9861415025528811,
+      "grad_norm": 0.9734970339085126,
+      "learning_rate": 9.48335631477948e-09,
+      "loss": 0.8321,
+      "step": 169
+    },
+    {
+      "epoch": 0.9919766593727206,
+      "grad_norm": 0.8205128623545712,
+      "learning_rate": 4.2155655596809455e-09,
+      "loss": 0.6526,
+      "step": 170
+    },
+    {
+      "epoch": 0.9978118161925602,
+      "grad_norm": 0.8811350978732005,
+      "learning_rate": 1.054002482043237e-09,
+      "loss": 0.7098,
+      "step": 171
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 171,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 4050,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 18593527627776.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835324ea0005cea474e544c6b34d867762fe906ca51b40c06f8bd128d9fcc400
+size 7544

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)