upload

.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 +1,30 @@
+{
+  "_name_or_path": "/lustre/fsn1/projects/rech/gkb/uua32zb/grand_challenge/checkpoints/Arab/Qwen__Qwen2.5-3B-annealing_only-Arab-fineweb2-0.0001LR-8192CL-2GAS-2BS-3EPOCHS-0.9BETA1-0.95BETA2-cosineLRSCHEDULER/",
+  "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": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "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": "4.46.1"
+}

latest

@@ -0,0 +1 @@
+global_step9032

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e09b721c4602f3d8a1697cb70bbe271c7628e1968559d96f3d48f865c5780e6
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf59363899958f93488294ba521acf38cf707ff0a4b8cce55e23e0c1c84b217
+size 1836696752

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 6794207232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "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"
+  }
+}

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 +1,208 @@
+{
+  "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",
+  "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 +1,1293 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500.0,
+  "global_step": 9032,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005535872453498672,
+      "grad_norm": 0.3433230221271515,
+      "learning_rate": 9.999243862184318e-05,
+      "loss": 0.5047,
+      "step": 50
+    },
+    {
+      "epoch": 0.011071744906997343,
+      "grad_norm": 0.3460846543312073,
+      "learning_rate": 9.99697567743503e-05,
+      "loss": 0.4958,
+      "step": 100
+    },
+    {
+      "epoch": 0.016607617360496013,
+      "grad_norm": 0.3351586163043976,
+      "learning_rate": 9.993196131776239e-05,
+      "loss": 0.5042,
+      "step": 150
+    },
+    {
+      "epoch": 0.022143489813994686,
+      "grad_norm": 0.3249658942222595,
+      "learning_rate": 9.987906368350908e-05,
+      "loss": 0.5105,
+      "step": 200
+    },
+    {
+      "epoch": 0.027679362267493356,
+      "grad_norm": 0.3283194303512573,
+      "learning_rate": 9.981107987075097e-05,
+      "loss": 0.5084,
+      "step": 250
+    },
+    {
+      "epoch": 0.033215234720992026,
+      "grad_norm": 0.3149356544017792,
+      "learning_rate": 9.972803044154077e-05,
+      "loss": 0.5144,
+      "step": 300
+    },
+    {
+      "epoch": 0.0387511071744907,
+      "grad_norm": 0.2961554527282715,
+      "learning_rate": 9.962994051460408e-05,
+      "loss": 0.5148,
+      "step": 350
+    },
+    {
+      "epoch": 0.04428697962798937,
+      "grad_norm": 0.2816214859485626,
+      "learning_rate": 9.951683975774213e-05,
+      "loss": 0.5166,
+      "step": 400
+    },
+    {
+      "epoch": 0.04982285208148804,
+      "grad_norm": 0.2994770109653473,
+      "learning_rate": 9.938876237885859e-05,
+      "loss": 0.5135,
+      "step": 450
+    },
+    {
+      "epoch": 0.05535872453498671,
+      "grad_norm": 0.30968600511550903,
+      "learning_rate": 9.92457471156133e-05,
+      "loss": 0.5168,
+      "step": 500
+    },
+    {
+      "epoch": 0.060894596988485386,
+      "grad_norm": 0.28216496109962463,
+      "learning_rate": 9.908783722370576e-05,
+      "loss": 0.5154,
+      "step": 550
+    },
+    {
+      "epoch": 0.06643046944198405,
+      "grad_norm": 0.2902168035507202,
+      "learning_rate": 9.891508046379226e-05,
+      "loss": 0.5181,
+      "step": 600
+    },
+    {
+      "epoch": 0.07196634189548273,
+      "grad_norm": 0.27671435475349426,
+      "learning_rate": 9.872752908704042e-05,
+      "loss": 0.5172,
+      "step": 650
+    },
+    {
+      "epoch": 0.0775022143489814,
+      "grad_norm": 0.3017374277114868,
+      "learning_rate": 9.852523981932558e-05,
+      "loss": 0.5155,
+      "step": 700
+    },
+    {
+      "epoch": 0.08303808680248007,
+      "grad_norm": 0.39052456617355347,
+      "learning_rate": 9.830827384407377e-05,
+      "loss": 0.5183,
+      "step": 750
+    },
+    {
+      "epoch": 0.08857395925597875,
+      "grad_norm": 0.27979791164398193,
+      "learning_rate": 9.807669678375643e-05,
+      "loss": 0.519,
+      "step": 800
+    },
+    {
+      "epoch": 0.09410983170947741,
+      "grad_norm": 0.29228779673576355,
+      "learning_rate": 9.783057868004257e-05,
+      "loss": 0.5165,
+      "step": 850
+    },
+    {
+      "epoch": 0.09964570416297608,
+      "grad_norm": 0.2779007852077484,
+      "learning_rate": 9.756999397261433e-05,
+      "loss": 0.5161,
+      "step": 900
+    },
+    {
+      "epoch": 0.10518157661647476,
+      "grad_norm": 0.28288534283638,
+      "learning_rate": 9.729502147665228e-05,
+      "loss": 0.5192,
+      "step": 950
+    },
+    {
+      "epoch": 0.11071744906997343,
+      "grad_norm": 0.26600030064582825,
+      "learning_rate": 9.700574435899745e-05,
+      "loss": 0.5169,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1162533215234721,
+      "grad_norm": 0.2742815911769867,
+      "learning_rate": 9.670225011299695e-05,
+      "loss": 0.5183,
+      "step": 1050
+    },
+    {
+      "epoch": 0.12178919397697077,
+      "grad_norm": 0.2582996189594269,
+      "learning_rate": 9.63846305320413e-05,
+      "loss": 0.5197,
+      "step": 1100
+    },
+    {
+      "epoch": 0.12732506643046945,
+      "grad_norm": 0.30109143257141113,
+      "learning_rate": 9.605298168180095e-05,
+      "loss": 0.5169,
+      "step": 1150
+    },
+    {
+      "epoch": 0.1328609388839681,
+      "grad_norm": 0.2727769613265991,
+      "learning_rate": 9.570740387117078e-05,
+      "loss": 0.5174,
+      "step": 1200
+    },
+    {
+      "epoch": 0.13839681133746679,
+      "grad_norm": 0.2607158422470093,
+      "learning_rate": 9.534800162193117e-05,
+      "loss": 0.5161,
+      "step": 1250
+    },
+    {
+      "epoch": 0.14393268379096547,
+      "grad_norm": 0.25849565863609314,
+      "learning_rate": 9.497488363713477e-05,
+      "loss": 0.5152,
+      "step": 1300
+    },
+    {
+      "epoch": 0.14946855624446412,
+      "grad_norm": 0.24172639846801758,
+      "learning_rate": 9.458816276822877e-05,
+      "loss": 0.5139,
+      "step": 1350
+    },
+    {
+      "epoch": 0.1550044286979628,
+      "grad_norm": 0.25869038701057434,
+      "learning_rate": 9.418795598092243e-05,
+      "loss": 0.5132,
+      "step": 1400
+    },
+    {
+      "epoch": 0.16054030115146148,
+      "grad_norm": 0.24481342732906342,
+      "learning_rate": 9.377438431981013e-05,
+      "loss": 0.5124,
+      "step": 1450
+    },
+    {
+      "epoch": 0.16607617360496013,
+      "grad_norm": 0.2613767087459564,
+      "learning_rate": 9.334757287176088e-05,
+      "loss": 0.5137,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1716120460584588,
+      "grad_norm": 0.27489006519317627,
+      "learning_rate": 9.290765072808507e-05,
+      "loss": 0.5133,
+      "step": 1550
+    },
+    {
+      "epoch": 0.1771479185119575,
+      "grad_norm": 0.24412401020526886,
+      "learning_rate": 9.24547509454902e-05,
+      "loss": 0.5129,
+      "step": 1600
+    },
+    {
+      "epoch": 0.18268379096545614,
+      "grad_norm": 0.2562081515789032,
+      "learning_rate": 9.198901050583726e-05,
+      "loss": 0.5125,
+      "step": 1650
+    },
+    {
+      "epoch": 0.18821966341895482,
+      "grad_norm": 0.2570527493953705,
+      "learning_rate": 9.151057027470968e-05,
+      "loss": 0.5125,
+      "step": 1700
+    },
+    {
+      "epoch": 0.1937555358724535,
+      "grad_norm": 0.2716536223888397,
+      "learning_rate": 9.1019574958808e-05,
+      "loss": 0.5116,
+      "step": 1750
+    },
+    {
+      "epoch": 0.19929140832595216,
+      "grad_norm": 0.23633652925491333,
+      "learning_rate": 9.05161730621825e-05,
+      "loss": 0.5092,
+      "step": 1800
+    },
+    {
+      "epoch": 0.20482728077945084,
+      "grad_norm": 0.2512938380241394,
+      "learning_rate": 9.000051684131736e-05,
+      "loss": 0.5106,
+      "step": 1850
+    },
+    {
+      "epoch": 0.21036315323294952,
+      "grad_norm": 0.23882919549942017,
+      "learning_rate": 8.947276225908001e-05,
+      "loss": 0.5139,
+      "step": 1900
+    },
+    {
+      "epoch": 0.21589902568644817,
+      "grad_norm": 0.23613141477108002,
+      "learning_rate": 8.893306893754924e-05,
+      "loss": 0.5074,
+      "step": 1950
+    },
+    {
+      "epoch": 0.22143489813994685,
+      "grad_norm": 0.40293580293655396,
+      "learning_rate": 8.83816001097368e-05,
+      "loss": 0.5113,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22697077059344553,
+      "grad_norm": 0.28628790378570557,
+      "learning_rate": 8.781852257021658e-05,
+      "loss": 0.5084,
+      "step": 2050
+    },
+    {
+      "epoch": 0.2325066430469442,
+      "grad_norm": 0.22755330801010132,
+      "learning_rate": 8.724400662467693e-05,
+      "loss": 0.5097,
+      "step": 2100
+    },
+    {
+      "epoch": 0.23804251550044286,
+      "grad_norm": 0.24709023535251617,
+      "learning_rate": 8.665822603841072e-05,
+      "loss": 0.506,
+      "step": 2150
+    },
+    {
+      "epoch": 0.24357838795394154,
+      "grad_norm": 0.28524163365364075,
+      "learning_rate": 8.606135798375909e-05,
+      "loss": 0.5055,
+      "step": 2200
+    },
+    {
+      "epoch": 0.24911426040744022,
+      "grad_norm": 0.23480156064033508,
+      "learning_rate": 8.545358298652494e-05,
+      "loss": 0.5075,
+      "step": 2250
+    },
+    {
+      "epoch": 0.2546501328609389,
+      "grad_norm": 0.437676340341568,
+      "learning_rate": 8.483508487137175e-05,
+      "loss": 0.5026,
+      "step": 2300
+    },
+    {
+      "epoch": 0.26018600531443753,
+      "grad_norm": 0.22623884677886963,
+      "learning_rate": 8.420605070622508e-05,
+      "loss": 0.5031,
+      "step": 2350
+    },
+    {
+      "epoch": 0.2657218777679362,
+      "grad_norm": 0.535098135471344,
+      "learning_rate": 8.356667074569274e-05,
+      "loss": 0.5034,
+      "step": 2400
+    },
+    {
+      "epoch": 0.2712577502214349,
+      "grad_norm": 0.2235407531261444,
+      "learning_rate": 8.291713837352147e-05,
+      "loss": 0.5022,
+      "step": 2450
+    },
+    {
+      "epoch": 0.27679362267493357,
+      "grad_norm": 0.2247524857521057,
+      "learning_rate": 8.225765004410688e-05,
+      "loss": 0.501,
+      "step": 2500
+    },
+    {
+      "epoch": 0.28232949512843225,
+      "grad_norm": 0.2457551658153534,
+      "learning_rate": 8.158840522307491e-05,
+      "loss": 0.5029,
+      "step": 2550
+    },
+    {
+      "epoch": 0.28786536758193093,
+      "grad_norm": 0.23865674436092377,
+      "learning_rate": 8.090960632695245e-05,
+      "loss": 0.5018,
+      "step": 2600
+    },
+    {
+      "epoch": 0.2934012400354296,
+      "grad_norm": 0.2285149097442627,
+      "learning_rate": 8.022145866194534e-05,
+      "loss": 0.4996,
+      "step": 2650
+    },
+    {
+      "epoch": 0.29893711248892824,
+      "grad_norm": 0.24315951764583588,
+      "learning_rate": 7.952417036184248e-05,
+      "loss": 0.499,
+      "step": 2700
+    },
+    {
+      "epoch": 0.3044729849424269,
+      "grad_norm": 0.23202696442604065,
+      "learning_rate": 7.88179523250647e-05,
+      "loss": 0.4978,
+      "step": 2750
+    },
+    {
+      "epoch": 0.3100088573959256,
+      "grad_norm": 1.3122915029525757,
+      "learning_rate": 7.810301815087752e-05,
+      "loss": 0.5002,
+      "step": 2800
+    },
+    {
+      "epoch": 0.3155447298494243,
+      "grad_norm": 0.2154541313648224,
+      "learning_rate": 7.737958407478687e-05,
+      "loss": 0.4954,
+      "step": 2850
+    },
+    {
+      "epoch": 0.32108060230292296,
+      "grad_norm": 0.21684616804122925,
+      "learning_rate": 7.664786890313758e-05,
+      "loss": 0.4938,
+      "step": 2900
+    },
+    {
+      "epoch": 0.32661647475642164,
+      "grad_norm": 0.224802166223526,
+      "learning_rate": 7.590809394693428e-05,
+      "loss": 0.4972,
+      "step": 2950
+    },
+    {
+      "epoch": 0.33215234720992026,
+      "grad_norm": 0.2258644551038742,
+      "learning_rate": 7.516048295490479e-05,
+      "loss": 0.4934,
+      "step": 3000
+    },
+    {
+      "epoch": 0.33768821966341894,
+      "grad_norm": 0.23096325993537903,
+      "learning_rate": 7.440526204582605e-05,
+      "loss": 0.4961,
+      "step": 3050
+    },
+    {
+      "epoch": 0.3432240921169176,
+      "grad_norm": 0.21675239503383636,
+      "learning_rate": 7.364265964013354e-05,
+      "loss": 0.4924,
+      "step": 3100
+    },
+    {
+      "epoch": 0.3487599645704163,
+      "grad_norm": 0.21985754370689392,
+      "learning_rate": 7.287290639083415e-05,
+      "loss": 0.4922,
+      "step": 3150
+    },
+    {
+      "epoch": 0.354295837023915,
+      "grad_norm": 0.23622620105743408,
+      "learning_rate": 7.209623511374408e-05,
+      "loss": 0.4925,
+      "step": 3200
+    },
+    {
+      "epoch": 0.35983170947741366,
+      "grad_norm": 0.21478299796581268,
+      "learning_rate": 7.131288071707251e-05,
+      "loss": 0.4886,
+      "step": 3250
+    },
+    {
+      "epoch": 0.3653675819309123,
+      "grad_norm": 0.22236472368240356,
+      "learning_rate": 7.052308013037245e-05,
+      "loss": 0.491,
+      "step": 3300
+    },
+    {
+      "epoch": 0.37090345438441097,
+      "grad_norm": 0.2187700718641281,
+      "learning_rate": 6.972707223288002e-05,
+      "loss": 0.4876,
+      "step": 3350
+    },
+    {
+      "epoch": 0.37643932683790965,
+      "grad_norm": 0.21888881921768188,
+      "learning_rate": 6.892509778126442e-05,
+      "loss": 0.4877,
+      "step": 3400
+    },
+    {
+      "epoch": 0.38197519929140833,
+      "grad_norm": 0.21689431369304657,
+      "learning_rate": 6.811739933680964e-05,
+      "loss": 0.4869,
+      "step": 3450
+    },
+    {
+      "epoch": 0.387511071744907,
+      "grad_norm": 0.2281043827533722,
+      "learning_rate": 6.730422119205072e-05,
+      "loss": 0.4877,
+      "step": 3500
+    },
+    {
+      "epoch": 0.3930469441984057,
+      "grad_norm": 0.22390636801719666,
+      "learning_rate": 6.648580929688611e-05,
+      "loss": 0.4853,
+      "step": 3550
+    },
+    {
+      "epoch": 0.3985828166519043,
+      "grad_norm": 0.21681427955627441,
+      "learning_rate": 6.566241118418888e-05,
+      "loss": 0.4848,
+      "step": 3600
+    },
+    {
+      "epoch": 0.404118689105403,
+      "grad_norm": 0.21562883257865906,
+      "learning_rate": 6.483427589493921e-05,
+      "loss": 0.4812,
+      "step": 3650
+    },
+    {
+      "epoch": 0.4096545615589017,
+      "grad_norm": 0.21386685967445374,
+      "learning_rate": 6.400165390290056e-05,
+      "loss": 0.4819,
+      "step": 3700
+    },
+    {
+      "epoch": 0.41519043401240036,
+      "grad_norm": 0.2484877109527588,
+      "learning_rate": 6.316479703886268e-05,
+      "loss": 0.485,
+      "step": 3750
+    },
+    {
+      "epoch": 0.42072630646589904,
+      "grad_norm": 0.22386734187602997,
+      "learning_rate": 6.232395841447406e-05,
+      "loss": 0.4812,
+      "step": 3800
+    },
+    {
+      "epoch": 0.4262621789193977,
+      "grad_norm": 0.22139135003089905,
+      "learning_rate": 6.1479392345687e-05,
+      "loss": 0.4773,
+      "step": 3850
+    },
+    {
+      "epoch": 0.43179805137289634,
+      "grad_norm": 0.2121252417564392,
+      "learning_rate": 6.063135427583849e-05,
+      "loss": 0.4795,
+      "step": 3900
+    },
+    {
+      "epoch": 0.437333923826395,
+      "grad_norm": 0.2234639823436737,
+      "learning_rate": 5.978010069839004e-05,
+      "loss": 0.479,
+      "step": 3950
+    },
+    {
+      "epoch": 0.4428697962798937,
+      "grad_norm": 0.21746611595153809,
+      "learning_rate": 5.892588907934987e-05,
+      "loss": 0.4798,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4484056687333924,
+      "grad_norm": 0.22007162868976593,
+      "learning_rate": 5.806897777940113e-05,
+      "loss": 0.4764,
+      "step": 4050
+    },
+    {
+      "epoch": 0.45394154118689106,
+      "grad_norm": 0.20671077072620392,
+      "learning_rate": 5.720962597575922e-05,
+      "loss": 0.4795,
+      "step": 4100
+    },
+    {
+      "epoch": 0.45947741364038974,
+      "grad_norm": 0.22428496181964874,
+      "learning_rate": 5.634809358378242e-05,
+      "loss": 0.4761,
+      "step": 4150
+    },
+    {
+      "epoch": 0.4650132860938884,
+      "grad_norm": 0.2182442545890808,
+      "learning_rate": 5.5484641178359165e-05,
+      "loss": 0.4769,
+      "step": 4200
+    },
+    {
+      "epoch": 0.47054915854738705,
+      "grad_norm": 0.22536329925060272,
+      "learning_rate": 5.461952991509574e-05,
+      "loss": 0.4747,
+      "step": 4250
+    },
+    {
+      "epoch": 0.47608503100088573,
+      "grad_norm": 0.213382750749588,
+      "learning_rate": 5.3753021451328525e-05,
+      "loss": 0.4761,
+      "step": 4300
+    },
+    {
+      "epoch": 0.4816209034543844,
+      "grad_norm": 0.2281421571969986,
+      "learning_rate": 5.2885377866984345e-05,
+      "loss": 0.4731,
+      "step": 4350
+    },
+    {
+      "epoch": 0.4871567759078831,
+      "grad_norm": 0.2082875370979309,
+      "learning_rate": 5.2016861585313034e-05,
+      "loss": 0.4714,
+      "step": 4400
+    },
+    {
+      "epoch": 0.49269264836138177,
+      "grad_norm": 0.22015559673309326,
+      "learning_rate": 5.11477352935163e-05,
+      "loss": 0.4704,
+      "step": 4450
+    },
+    {
+      "epoch": 0.49822852081488045,
+      "grad_norm": 0.21323701739311218,
+      "learning_rate": 5.0278261863296416e-05,
+      "loss": 0.47,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5037643932683791,
+      "grad_norm": 0.20574581623077393,
+      "learning_rate": 4.940870427134954e-05,
+      "loss": 0.4671,
+      "step": 4550
+    },
+    {
+      "epoch": 0.5093002657218778,
+      "grad_norm": 0.21198670566082,
+      "learning_rate": 4.8539325519826925e-05,
+      "loss": 0.4679,
+      "step": 4600
+    },
+    {
+      "epoch": 0.5148361381753764,
+      "grad_norm": 0.2015901505947113,
+      "learning_rate": 4.767038855678866e-05,
+      "loss": 0.4704,
+      "step": 4650
+    },
+    {
+      "epoch": 0.5203720106288751,
+      "grad_norm": 0.2089219093322754,
+      "learning_rate": 4.680215619667364e-05,
+      "loss": 0.467,
+      "step": 4700
+    },
+    {
+      "epoch": 0.5259078830823738,
+      "grad_norm": 0.2178608626127243,
+      "learning_rate": 4.593489104080993e-05,
+      "loss": 0.4649,
+      "step": 4750
+    },
+    {
+      "epoch": 0.5314437555358724,
+      "grad_norm": 0.20710888504981995,
+      "learning_rate": 4.5068855397989796e-05,
+      "loss": 0.4674,
+      "step": 4800
+    },
+    {
+      "epoch": 0.5369796279893712,
+      "grad_norm": 0.21702979505062103,
+      "learning_rate": 4.4204311205132924e-05,
+      "loss": 0.4658,
+      "step": 4850
+    },
+    {
+      "epoch": 0.5425155004428698,
+      "grad_norm": 0.20264098048210144,
+      "learning_rate": 4.334151994806235e-05,
+      "loss": 0.4644,
+      "step": 4900
+    },
+    {
+      "epoch": 0.5480513728963685,
+      "grad_norm": 0.20313504338264465,
+      "learning_rate": 4.2480742582416666e-05,
+      "loss": 0.4622,
+      "step": 4950
+    },
+    {
+      "epoch": 0.5535872453498671,
+      "grad_norm": 0.21679863333702087,
+      "learning_rate": 4.162223945472271e-05,
+      "loss": 0.4612,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5591231178033658,
+      "grad_norm": 0.21348516643047333,
+      "learning_rate": 4.0766270223652356e-05,
+      "loss": 0.461,
+      "step": 5050
+    },
+    {
+      "epoch": 0.5646589902568645,
+      "grad_norm": 0.21236220002174377,
+      "learning_rate": 3.991309378148746e-05,
+      "loss": 0.4627,
+      "step": 5100
+    },
+    {
+      "epoch": 0.5701948627103631,
+      "grad_norm": 0.21011418104171753,
+      "learning_rate": 3.906296817581662e-05,
+      "loss": 0.4622,
+      "step": 5150
+    },
+    {
+      "epoch": 0.5757307351638619,
+      "grad_norm": 0.1996048539876938,
+      "learning_rate": 3.821615053148717e-05,
+      "loss": 0.4607,
+      "step": 5200
+    },
+    {
+      "epoch": 0.5812666076173605,
+      "grad_norm": 0.2122189849615097,
+      "learning_rate": 3.737289697283673e-05,
+      "loss": 0.4585,
+      "step": 5250
+    },
+    {
+      "epoch": 0.5868024800708592,
+      "grad_norm": 0.20436163246631622,
+      "learning_rate": 3.653346254622683e-05,
+      "loss": 0.4582,
+      "step": 5300
+    },
+    {
+      "epoch": 0.5923383525243578,
+      "grad_norm": 0.19280461966991425,
+      "learning_rate": 3.569810114290297e-05,
+      "loss": 0.4587,
+      "step": 5350
+    },
+    {
+      "epoch": 0.5978742249778565,
+      "grad_norm": 0.1989956647157669,
+      "learning_rate": 3.486706542220388e-05,
+      "loss": 0.4582,
+      "step": 5400
+    },
+    {
+      "epoch": 0.6034100974313552,
+      "grad_norm": 0.20169289410114288,
+      "learning_rate": 3.404060673514339e-05,
+      "loss": 0.4584,
+      "step": 5450
+    },
+    {
+      "epoch": 0.6089459698848538,
+      "grad_norm": 0.2046155035495758,
+      "learning_rate": 3.3218975048388065e-05,
+      "loss": 0.4549,
+      "step": 5500
+    },
+    {
+      "epoch": 0.6144818423383526,
+      "grad_norm": 0.2124761939048767,
+      "learning_rate": 3.240241886865346e-05,
+      "loss": 0.4541,
+      "step": 5550
+    },
+    {
+      "epoch": 0.6200177147918512,
+      "grad_norm": 0.19483420252799988,
+      "learning_rate": 3.159118516754205e-05,
+      "loss": 0.4533,
+      "step": 5600
+    },
+    {
+      "epoch": 0.6255535872453498,
+      "grad_norm": 0.2233278751373291,
+      "learning_rate": 3.0785519306845326e-05,
+      "loss": 0.4542,
+      "step": 5650
+    },
+    {
+      "epoch": 0.6310894596988486,
+      "grad_norm": 0.23966117203235626,
+      "learning_rate": 2.9985664964332904e-05,
+      "loss": 0.4534,
+      "step": 5700
+    },
+    {
+      "epoch": 0.6366253321523472,
+      "grad_norm": 0.21558792889118195,
+      "learning_rate": 2.919186406005099e-05,
+      "loss": 0.4512,
+      "step": 5750
+    },
+    {
+      "epoch": 0.6421612046058459,
+      "grad_norm": 0.20280343294143677,
+      "learning_rate": 2.8404356683152257e-05,
+      "loss": 0.4536,
+      "step": 5800
+    },
+    {
+      "epoch": 0.6476970770593445,
+      "grad_norm": 0.2108713537454605,
+      "learning_rate": 2.7623381019279905e-05,
+      "loss": 0.4495,
+      "step": 5850
+    },
+    {
+      "epoch": 0.6532329495128433,
+      "grad_norm": 0.21031597256660461,
+      "learning_rate": 2.6849173278526906e-05,
+      "loss": 0.4491,
+      "step": 5900
+    },
+    {
+      "epoch": 0.6587688219663419,
+      "grad_norm": 0.21196845173835754,
+      "learning_rate": 2.608196762399329e-05,
+      "loss": 0.4469,
+      "step": 5950
+    },
+    {
+      "epoch": 0.6643046944198405,
+      "grad_norm": 0.21073392033576965,
+      "learning_rate": 2.5321996100962165e-05,
+      "loss": 0.4499,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6698405668733393,
+      "grad_norm": 0.1942080855369568,
+      "learning_rate": 2.456948856671647e-05,
+      "loss": 0.4476,
+      "step": 6050
+    },
+    {
+      "epoch": 0.6753764393268379,
+      "grad_norm": 0.20621733367443085,
+      "learning_rate": 2.3824672621017512e-05,
+      "loss": 0.4492,
+      "step": 6100
+    },
+    {
+      "epoch": 0.6809123117803366,
+      "grad_norm": 0.2076757699251175,
+      "learning_rate": 2.30877735372662e-05,
+      "loss": 0.4457,
+      "step": 6150
+    },
+    {
+      "epoch": 0.6864481842338352,
+      "grad_norm": 0.20099569857120514,
+      "learning_rate": 2.2359014194367982e-05,
+      "loss": 0.4451,
+      "step": 6200
+    },
+    {
+      "epoch": 0.6919840566873339,
+      "grad_norm": 0.20270654559135437,
+      "learning_rate": 2.163861500932191e-05,
+      "loss": 0.4479,
+      "step": 6250
+    },
+    {
+      "epoch": 0.6975199291408326,
+      "grad_norm": 0.28589048981666565,
+      "learning_rate": 2.0926793870554458e-05,
+      "loss": 0.4463,
+      "step": 6300
+    },
+    {
+      "epoch": 0.7030558015943312,
+      "grad_norm": 0.208979532122612,
+      "learning_rate": 2.0223766072018043e-05,
+      "loss": 0.4469,
+      "step": 6350
+    },
+    {
+      "epoch": 0.70859167404783,
+      "grad_norm": 0.2149340659379959,
+      "learning_rate": 1.952974424807425e-05,
+      "loss": 0.4452,
+      "step": 6400
+    },
+    {
+      "epoch": 0.7141275465013286,
+      "grad_norm": 0.19958503544330597,
+      "learning_rate": 1.8844938309181493e-05,
+      "loss": 0.4419,
+      "step": 6450
+    },
+    {
+      "epoch": 0.7196634189548273,
+      "grad_norm": 0.20782802999019623,
+      "learning_rate": 1.8169555378406457e-05,
+      "loss": 0.4443,
+      "step": 6500
+    },
+    {
+      "epoch": 0.725199291408326,
+      "grad_norm": 0.2087666094303131,
+      "learning_rate": 1.7503799728778787e-05,
+      "loss": 0.4436,
+      "step": 6550
+    },
+    {
+      "epoch": 0.7307351638618246,
+      "grad_norm": 0.19283324480056763,
+      "learning_rate": 1.6847872721507525e-05,
+      "loss": 0.4425,
+      "step": 6600
+    },
+    {
+      "epoch": 0.7362710363153233,
+      "grad_norm": 0.207339808344841,
+      "learning_rate": 1.6201972745078493e-05,
+      "loss": 0.4387,
+      "step": 6650
+    },
+    {
+      "epoch": 0.7418069087688219,
+      "grad_norm": 0.20270253717899323,
+      "learning_rate": 1.5566295155250643e-05,
+      "loss": 0.4395,
+      "step": 6700
+    },
+    {
+      "epoch": 0.7473427812223207,
+      "grad_norm": 0.19986706972122192,
+      "learning_rate": 1.4941032215969641e-05,
+      "loss": 0.4396,
+      "step": 6750
+    },
+    {
+      "epoch": 0.7528786536758193,
+      "grad_norm": 0.20881563425064087,
+      "learning_rate": 1.4326373041216772e-05,
+      "loss": 0.4398,
+      "step": 6800
+    },
+    {
+      "epoch": 0.758414526129318,
+      "grad_norm": 0.21014416217803955,
+      "learning_rate": 1.3722503537810322e-05,
+      "loss": 0.4361,
+      "step": 6850
+    },
+    {
+      "epoch": 0.7639503985828167,
+      "grad_norm": 0.1940258890390396,
+      "learning_rate": 1.312960634917721e-05,
+      "loss": 0.4399,
+      "step": 6900
+    },
+    {
+      "epoch": 0.7694862710363153,
+      "grad_norm": 0.19840975105762482,
+      "learning_rate": 1.2547860800111506e-05,
+      "loss": 0.4378,
+      "step": 6950
+    },
+    {
+      "epoch": 0.775022143489814,
+      "grad_norm": 0.19728879630565643,
+      "learning_rate": 1.1977442842536684e-05,
+      "loss": 0.4345,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7805580159433126,
+      "grad_norm": 0.2010977864265442,
+      "learning_rate": 1.1418525002288155e-05,
+      "loss": 0.4378,
+      "step": 7050
+    },
+    {
+      "epoch": 0.7860938883968114,
+      "grad_norm": 0.20416665077209473,
+      "learning_rate": 1.0871276326931846e-05,
+      "loss": 0.4365,
+      "step": 7100
+    },
+    {
+      "epoch": 0.79162976085031,
+      "grad_norm": 0.20482172071933746,
+      "learning_rate": 1.0335862334634972e-05,
+      "loss": 0.4378,
+      "step": 7150
+    },
+    {
+      "epoch": 0.7971656333038086,
+      "grad_norm": 0.20648156106472015,
+      "learning_rate": 9.812444964104195e-06,
+      "loss": 0.4357,
+      "step": 7200
+    },
+    {
+      "epoch": 0.8027015057573074,
+      "grad_norm": 0.20412269234657288,
+      "learning_rate": 9.30118252560639e-06,
+      "loss": 0.4353,
+      "step": 7250
+    },
+    {
+      "epoch": 0.808237378210806,
+      "grad_norm": 0.5004847645759583,
+      "learning_rate": 8.802229653086974e-06,
+      "loss": 0.4344,
+      "step": 7300
+    },
+    {
+      "epoch": 0.8137732506643047,
+      "grad_norm": 0.19423185288906097,
+      "learning_rate": 8.31573725739999e-06,
+      "loss": 0.4366,
+      "step": 7350
+    },
+    {
+      "epoch": 0.8193091231178034,
+      "grad_norm": 0.20235984027385712,
+      "learning_rate": 7.841852480664413e-06,
+      "loss": 0.4336,
+      "step": 7400
+    },
+    {
+      "epoch": 0.8248449955713021,
+      "grad_norm": 0.20814161002635956,
+      "learning_rate": 7.380718651760227e-06,
+      "loss": 0.4346,
+      "step": 7450
+    },
+    {
+      "epoch": 0.8303808680248007,
+      "grad_norm": 0.19815950095653534,
+      "learning_rate": 6.9324752429778986e-06,
+      "loss": 0.4374,
+      "step": 7500
+    },
+    {
+      "epoch": 0.8359167404782993,
+      "grad_norm": 0.20228245854377747,
+      "learning_rate": 6.497257827834219e-06,
+      "loss": 0.4347,
+      "step": 7550
+    },
+    {
+      "epoch": 0.8414526129317981,
+      "grad_norm": 0.20134137570858002,
+      "learning_rate": 6.075198040067431e-06,
+      "loss": 0.4355,
+      "step": 7600
+    },
+    {
+      "epoch": 0.8469884853852967,
+      "grad_norm": 0.19768740236759186,
+      "learning_rate": 5.66642353382395e-06,
+      "loss": 0.4314,
+      "step": 7650
+    },
+    {
+      "epoch": 0.8525243578387954,
+      "grad_norm": 0.2048715204000473,
+      "learning_rate": 5.2710579450486794e-06,
+      "loss": 0.4324,
+      "step": 7700
+    },
+    {
+      "epoch": 0.8580602302922941,
+      "grad_norm": 0.1978369802236557,
+      "learning_rate": 4.889220854090704e-06,
+      "loss": 0.4326,
+      "step": 7750
+    },
+    {
+      "epoch": 0.8635961027457927,
+      "grad_norm": 0.20312413573265076,
+      "learning_rate": 4.521027749535578e-06,
+      "loss": 0.4324,
+      "step": 7800
+    },
+    {
+      "epoch": 0.8691319751992914,
+      "grad_norm": 0.19481532275676727,
+      "learning_rate": 4.166589993275216e-06,
+      "loss": 0.4327,
+      "step": 7850
+    },
+    {
+      "epoch": 0.87466784765279,
+      "grad_norm": 0.201799213886261,
+      "learning_rate": 3.826014786825971e-06,
+      "loss": 0.4317,
+      "step": 7900
+    },
+    {
+      "epoch": 0.8802037201062888,
+      "grad_norm": 0.1976991593837738,
+      "learning_rate": 3.499405138904882e-06,
+      "loss": 0.4312,
+      "step": 7950
+    },
+    {
+      "epoch": 0.8857395925597874,
+      "grad_norm": 0.19549186527729034,
+      "learning_rate": 3.186859834274292e-06,
+      "loss": 0.434,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8912754650132861,
+      "grad_norm": 0.19139450788497925,
+      "learning_rate": 2.8884734038637506e-06,
+      "loss": 0.431,
+      "step": 8050
+    },
+    {
+      "epoch": 0.8968113374667848,
+      "grad_norm": 0.2454349398612976,
+      "learning_rate": 2.6043360961787666e-06,
+      "loss": 0.428,
+      "step": 8100
+    },
+    {
+      "epoch": 0.9023472099202834,
+      "grad_norm": 0.2521144449710846,
+      "learning_rate": 2.3345338500046e-06,
+      "loss": 0.4332,
+      "step": 8150
+    },
+    {
+      "epoch": 0.9078830823737821,
+      "grad_norm": 0.20436929166316986,
+      "learning_rate": 2.079148268413683e-06,
+      "loss": 0.4305,
+      "step": 8200
+    },
+    {
+      "epoch": 0.9134189548272807,
+      "grad_norm": 0.2020627111196518,
+      "learning_rate": 1.8382565940843532e-06,
+      "loss": 0.4311,
+      "step": 8250
+    },
+    {
+      "epoch": 0.9189548272807795,
+      "grad_norm": 0.19668377935886383,
+      "learning_rate": 1.6119316859383838e-06,
+      "loss": 0.4313,
+      "step": 8300
+    },
+    {
+      "epoch": 0.9244906997342781,
+      "grad_norm": 0.18962964415550232,
+      "learning_rate": 1.4002419971044512e-06,
+      "loss": 0.4291,
+      "step": 8350
+    },
+    {
+      "epoch": 0.9300265721877768,
+      "grad_norm": 0.20305824279785156,
+      "learning_rate": 1.2032515542141187e-06,
+      "loss": 0.4297,
+      "step": 8400
+    },
+    {
+      "epoch": 0.9355624446412755,
+      "grad_norm": 0.19335156679153442,
+      "learning_rate": 1.0210199380366659e-06,
+      "loss": 0.4271,
+      "step": 8450
+    },
+    {
+      "epoch": 0.9410983170947741,
+      "grad_norm": 0.1913912147283554,
+      "learning_rate": 8.536022654585751e-07,
+      "loss": 0.4285,
+      "step": 8500
+    },
+    {
+      "epoch": 0.9466341895482728,
+      "grad_norm": 0.20103470981121063,
+      "learning_rate": 7.010491728131452e-07,
+      "loss": 0.4306,
+      "step": 8550
+    },
+    {
+      "epoch": 0.9521700620017715,
+      "grad_norm": 0.1967928558588028,
+      "learning_rate": 5.634068005652804e-07,
+      "loss": 0.4286,
+      "step": 8600
+    },
+    {
+      "epoch": 0.9577059344552702,
+      "grad_norm": 0.19620321691036224,
+      "learning_rate": 4.4071677935605407e-07,
+      "loss": 0.4321,
+      "step": 8650
+    },
+    {
+      "epoch": 0.9632418069087688,
+      "grad_norm": 0.19100981950759888,
+      "learning_rate": 3.3301621741132496e-07,
+      "loss": 0.4302,
+      "step": 8700
+    },
+    {
+      "epoch": 0.9687776793622674,
+      "grad_norm": 0.20217867195606232,
+      "learning_rate": 2.403376893181486e-07,
+      "loss": 0.4288,
+      "step": 8750
+    },
+    {
+      "epoch": 0.9743135518157662,
+      "grad_norm": 0.1999254822731018,
+      "learning_rate": 1.6270922617245832e-07,
+      "loss": 0.4307,
+      "step": 8800
+    },
+    {
+      "epoch": 0.9798494242692648,
+      "grad_norm": 0.19564539194107056,
+      "learning_rate": 1.001543071008637e-07,
+      "loss": 0.4292,
+      "step": 8850
+    },
+    {
+      "epoch": 0.9853852967227635,
+      "grad_norm": 0.18959170579910278,
+      "learning_rate": 5.2691852159314495e-08,
+      "loss": 0.4328,
+      "step": 8900
+    },
+    {
+      "epoch": 0.9909211691762622,
+      "grad_norm": 0.19490332901477814,
+      "learning_rate": 2.0336216610622462e-08,
+      "loss": 0.4298,
+      "step": 8950
+    },
+    {
+      "epoch": 0.9964570416297609,
+      "grad_norm": 0.20640763640403748,
+      "learning_rate": 3.097186582606826e-09,
+      "loss": 0.4306,
+      "step": 9000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 9032,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.462893197723854e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ee87e8e197eaa524b3b9d7f3e919d8b8af8b5a66008e432551b430fa78bcbf
+size 6968

zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/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 json
+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)
+
+        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 files:
+        state_dict = torch.load(f, map_location=device)
+        # 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}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) 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")
+
+
+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 = fp32_flat_groups[0].numel() * 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
+    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}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        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 get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=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
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    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.
+
+    """
+    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")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+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)
+
+    # 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")
+        state_dict_split = split_torch_state_dict_into_shards(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
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # 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)