update

.gitattributes

@@ -33,3 +33,7 @@ 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
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<image>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,84 @@
+{
+  "_name_or_path": "/mnt/damovl/yyq/LongVU/LongVU_Qwen2_7B_cambrian",
+  "architectures": [
+    "CambrianQwenForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "connect_layer": 2,
+  "connector_depth": 3,
+  "connector_only": true,
+  "dino_threshold": 0.83,
+  "drop_threshold": 0.8,
+  "eos_token_id": 151645,
+  "frame_pos": false,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "highres": true,
+  "highres_connect": false,
+  "image_aspect_ratio": "pad",
+  "image_position": 91,
+  "image_token_len": 144,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "is_image_newline": true,
+  "is_st_sampler": false,
+  "lowres_token": 8,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "sva",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_sampler_lr": null,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower_aux_list": [
+    "siglip/CLIP-ViT-SO400M-14-384",
+    "facebook/dinov2-giant-res378"
+  ],
+  "mm_vision_tower_aux_token_len_list": [
+    576,
+    576
+  ],
+  "mm_vision_tower_lr": null,
+  "model_type": "cambrian_qwen",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "num_of_vision_sampler_layers": 10,
+  "num_query_group": 1,
+  "pretraining_tp": 1,
+  "query_num_list": [
+    144
+  ],
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "spmd_debug": null,
+  "spmd_fsdp_sharding": null,
+  "spmd_mesh": null,
+  "start_of_vision_sampler_layers": 0,
+  "stride_of_vision_sampler_layers": 3,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 8192,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "tune_mm_mlp_adapter": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_hidden_size": 1024,
+  "vision_tower_aux_token_len_list": [
+    576,
+    576
+  ],
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.42.4",
+  "use_cache": false
+}

global_step741/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325e2fbb769ad610c77054b581f5cf9646a9a154331f6f49c3a5dd7c6979e60a
+size 11507505868

global_step741/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4404cad0a8269b7ae46ae1be1498e4d0089bd36a4d10e1938b720c645de8ad
+size 11507507340

global_step741/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f8cceec93f4d86c71e83811816d89ca640c26b00f5c1b2d60146a08ca9af828
+size 11507507596

global_step741/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cacda971a2aec5a4c27993dd510fea6720982d839ee548cc441cc9e8a86a401d
+size 11507507660

global_step741/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a66d7766df080e4a3a3f44047746a035a172dd3f21de36fb3f4dffe4f6571c
+size 11507507532

global_step741/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd86ba2024c47f32a9131e8e2cf122a08f39cf85946461761e7ed98666f895e6
+size 11507507276

global_step741/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793f900d3ed81c7613e833f5eb4d29c495acb214d587a58d1961e7d76d79077c
+size 11507508236

global_step741/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f79c2af5cd54201fd335ac408600e49846b2fb27f2aeb5e0f3a9a62bbae097
+size 11507510476

global_step741/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a48b68883462ce39e68a0f996de693ae8945db58d099a123f5384030c4c9772
+size 15343452856

latest

@@ -0,0 +1 @@
+global_step741

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41f56c10c13c0ece80b71b0916dae6bc7ad24453c0877fc6ec0b043e6bb0734
+size 4877670176

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b49010db26c2c6e9685e053d0b3036740d862b29ee7ecc966f4af24fbea9ff
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9779343f9870a70179123b94010b60f554633af62f0181af94f48cb2ad43d449
+size 4442965440

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9adb0e4104faeac3f634caa80379e85220c25abfb81f0f0eb662a61d34d2495c
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,436 @@
+{
+  "metadata": {
+    "total_size": 15343331328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.image_newline": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_0.0.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_0.0.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_0.2.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_0.2.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_0.3.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_0.3.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_1.0.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_1.0.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_1.2.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_1.2.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_1.3.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector_aux_1.3.weight": "model-00003-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_query": "model-00001-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_0.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_0.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_0.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_1.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_1.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.k_proj_1.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.q_proj.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.q_proj.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.q_proj.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_0.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_0.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_0.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_1.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_1.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.cross_attn.v_proj_1.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.pos_embed_0": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.pos_embed_1": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.proj_context.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.proj_in.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.proj_out.linear_1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.0.proj_out.linear_2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_0.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_0.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_0.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_1.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_1.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.k_proj_1.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.q_proj.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.q_proj.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.q_proj.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_0.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_0.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_0.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_1.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_1.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.cross_attn.v_proj_1.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.pos_embed_0": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.pos_embed_1": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.proj_context.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.proj_in.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.proj_out.linear_1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.1.proj_out.linear_2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_0.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_0.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_0.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_1.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_1.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.k_proj_1.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.q_proj.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.q_proj.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.q_proj.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_0.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_0.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_0.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_1.0.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_1.0.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.cross_attn.v_proj_1.1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.norm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.pos_embed_0": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.pos_embed_1": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.proj_context.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.proj_in.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.proj_out.linear_1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_sampler_0.layers.2.proj_out.linear_2.weight": "model-00003-of-00004.safetensors"
+  }
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fadd8eaf8176b5c2f86cb16165e55c152f9fad64e53332ebf9dfbc585ade8600
+size 1064

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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_config.json

@@ -0,0 +1,53 @@
+{
+  "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": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,551 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 5000.0,
+  "global_step": 741,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01349527665317139,
+      "grad_norm": 7.016904524087463,
+      "learning_rate": 8.695652173913043e-07,
+      "loss": 1.1369,
+      "step": 10
+    },
+    {
+      "epoch": 0.02699055330634278,
+      "grad_norm": 4.2020279077827905,
+      "learning_rate": 1.7391304347826085e-06,
+      "loss": 1.0452,
+      "step": 20
+    },
+    {
+      "epoch": 0.04048582995951417,
+      "grad_norm": 3.441796090298099,
+      "learning_rate": 1.999530989041473e-06,
+      "loss": 0.9533,
+      "step": 30
+    },
+    {
+      "epoch": 0.05398110661268556,
+      "grad_norm": 3.5191614427600753,
+      "learning_rate": 1.9972348515341017e-06,
+      "loss": 0.8914,
+      "step": 40
+    },
+    {
+      "epoch": 0.06747638326585695,
+      "grad_norm": 2.9690875149374367,
+      "learning_rate": 1.9930298323185945e-06,
+      "loss": 0.8475,
+      "step": 50
+    },
+    {
+      "epoch": 0.08097165991902834,
+      "grad_norm": 3.0556169559708475,
+      "learning_rate": 1.986923980536286e-06,
+      "loss": 0.8232,
+      "step": 60
+    },
+    {
+      "epoch": 0.09446693657219973,
+      "grad_norm": 2.9704481548374653,
+      "learning_rate": 1.9789289838540896e-06,
+      "loss": 0.822,
+      "step": 70
+    },
+    {
+      "epoch": 0.10796221322537113,
+      "grad_norm": 2.999043629121677,
+      "learning_rate": 1.969060146092264e-06,
+      "loss": 0.791,
+      "step": 80
+    },
+    {
+      "epoch": 0.1214574898785425,
+      "grad_norm": 3.17575389006719,
+      "learning_rate": 1.9573363579302263e-06,
+      "loss": 0.806,
+      "step": 90
+    },
+    {
+      "epoch": 0.1349527665317139,
+      "grad_norm": 2.9165449315999563,
+      "learning_rate": 1.943780060746493e-06,
+      "loss": 0.7961,
+      "step": 100
+    },
+    {
+      "epoch": 0.1484480431848853,
+      "grad_norm": 2.952637325540401,
+      "learning_rate": 1.928417203661959e-06,
+      "loss": 0.7962,
+      "step": 110
+    },
+    {
+      "epoch": 0.16194331983805668,
+      "grad_norm": 3.014781591451641,
+      "learning_rate": 1.911277193868751e-06,
+      "loss": 0.7781,
+      "step": 120
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 2.8796052156819716,
+      "learning_rate": 1.8923928403397207e-06,
+      "loss": 0.776,
+      "step": 130
+    },
+    {
+      "epoch": 0.18893387314439947,
+      "grad_norm": 2.8482523150497117,
+      "learning_rate": 1.8718002910263424e-06,
+      "loss": 0.7615,
+      "step": 140
+    },
+    {
+      "epoch": 0.20242914979757085,
+      "grad_norm": 2.922903791793236,
+      "learning_rate": 1.8495389636652184e-06,
+      "loss": 0.7543,
+      "step": 150
+    },
+    {
+      "epoch": 0.21592442645074225,
+      "grad_norm": 2.9536979340238547,
+      "learning_rate": 1.8256514703256447e-06,
+      "loss": 0.7598,
+      "step": 160
+    },
+    {
+      "epoch": 0.22941970310391363,
+      "grad_norm": 3.1334920821882126,
+      "learning_rate": 1.8001835358426684e-06,
+      "loss": 0.7489,
+      "step": 170
+    },
+    {
+      "epoch": 0.242914979757085,
+      "grad_norm": 3.2092630967068683,
+      "learning_rate": 1.7731839102917642e-06,
+      "loss": 0.7551,
+      "step": 180
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 2.987735102823792,
+      "learning_rate": 1.7447042756726754e-06,
+      "loss": 0.7503,
+      "step": 190
+    },
+    {
+      "epoch": 0.2699055330634278,
+      "grad_norm": 2.979147030983217,
+      "learning_rate": 1.7147991469810365e-06,
+      "loss": 0.7528,
+      "step": 200
+    },
+    {
+      "epoch": 0.2834008097165992,
+      "grad_norm": 3.1413426729820904,
+      "learning_rate": 1.6835257678571512e-06,
+      "loss": 0.7387,
+      "step": 210
+    },
+    {
+      "epoch": 0.2968960863697706,
+      "grad_norm": 3.1214265634728897,
+      "learning_rate": 1.650944001011663e-06,
+      "loss": 0.7281,
+      "step": 220
+    },
+    {
+      "epoch": 0.31039136302294196,
+      "grad_norm": 2.978380133818548,
+      "learning_rate": 1.6171162136378713e-06,
+      "loss": 0.7514,
+      "step": 230
+    },
+    {
+      "epoch": 0.32388663967611336,
+      "grad_norm": 2.85376146602686,
+      "learning_rate": 1.5821071580300269e-06,
+      "loss": 0.7403,
+      "step": 240
+    },
+    {
+      "epoch": 0.33738191632928477,
+      "grad_norm": 3.1598761470719734,
+      "learning_rate": 1.5459838476361322e-06,
+      "loss": 0.7435,
+      "step": 250
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 2.821356522721463,
+      "learning_rate": 1.5088154287824932e-06,
+      "loss": 0.7209,
+      "step": 260
+    },
+    {
+      "epoch": 0.3643724696356275,
+      "grad_norm": 2.98057980294587,
+      "learning_rate": 1.4706730483155736e-06,
+      "loss": 0.7311,
+      "step": 270
+    },
+    {
+      "epoch": 0.37786774628879893,
+      "grad_norm": 3.0364233244848364,
+      "learning_rate": 1.4316297174145016e-06,
+      "loss": 0.7282,
+      "step": 280
+    },
+    {
+      "epoch": 0.3913630229419703,
+      "grad_norm": 2.949886690990857,
+      "learning_rate": 1.391760171834918e-06,
+      "loss": 0.7078,
+      "step": 290
+    },
+    {
+      "epoch": 0.4048582995951417,
+      "grad_norm": 2.9507364249680053,
+      "learning_rate": 1.3511407288516878e-06,
+      "loss": 0.7201,
+      "step": 300
+    },
+    {
+      "epoch": 0.4183535762483131,
+      "grad_norm": 2.827650772154331,
+      "learning_rate": 1.3098491411743014e-06,
+      "loss": 0.7147,
+      "step": 310
+    },
+    {
+      "epoch": 0.4318488529014845,
+      "grad_norm": 2.8781557252440635,
+      "learning_rate": 1.267964448114608e-06,
+      "loss": 0.7295,
+      "step": 320
+    },
+    {
+      "epoch": 0.44534412955465585,
+      "grad_norm": 2.952298995368144,
+      "learning_rate": 1.2255668242917648e-06,
+      "loss": 0.724,
+      "step": 330
+    },
+    {
+      "epoch": 0.45883940620782726,
+      "grad_norm": 3.121925726144687,
+      "learning_rate": 1.1827374261640126e-06,
+      "loss": 0.697,
+      "step": 340
+    },
+    {
+      "epoch": 0.47233468286099867,
+      "grad_norm": 2.852801476396792,
+      "learning_rate": 1.1395582366810346e-06,
+      "loss": 0.718,
+      "step": 350
+    },
+    {
+      "epoch": 0.48582995951417,
+      "grad_norm": 3.0303857364861955,
+      "learning_rate": 1.0961119083542726e-06,
+      "loss": 0.7197,
+      "step": 360
+    },
+    {
+      "epoch": 0.4993252361673414,
+      "grad_norm": 3.166667043296761,
+      "learning_rate": 1.05248160504558e-06,
+      "loss": 0.7091,
+      "step": 370
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 2.906467539598673,
+      "learning_rate": 1.0087508427770638e-06,
+      "loss": 0.6934,
+      "step": 380
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 3.02782546633098,
+      "learning_rate": 9.650033298668279e-07,
+      "loss": 0.7025,
+      "step": 390
+    },
+    {
+      "epoch": 0.5398110661268556,
+      "grad_norm": 2.8912523592077637,
+      "learning_rate": 9.213228066966326e-07,
+      "loss": 0.7033,
+      "step": 400
+    },
+    {
+      "epoch": 0.553306342780027,
+      "grad_norm": 2.82347772754047,
+      "learning_rate": 8.777928854181709e-07,
+      "loss": 0.7,
+      "step": 410
+    },
+    {
+      "epoch": 0.5668016194331984,
+      "grad_norm": 2.9229669660658293,
+      "learning_rate": 8.344968899048091e-07,
+      "loss": 0.7022,
+      "step": 420
+    },
+    {
+      "epoch": 0.5802968960863698,
+      "grad_norm": 3.1576009691196707,
+      "learning_rate": 7.915176962551347e-07,
+      "loss": 0.7037,
+      "step": 430
+    },
+    {
+      "epoch": 0.5937921727395412,
+      "grad_norm": 3.1084612640931173,
+      "learning_rate": 7.489375741536281e-07,
+      "loss": 0.7073,
+      "step": 440
+    },
+    {
+      "epoch": 0.6072874493927125,
+      "grad_norm": 2.9866909336253595,
+      "learning_rate": 7.068380293921141e-07,
+      "loss": 0.6877,
+      "step": 450
+    },
+    {
+      "epoch": 0.6207827260458839,
+      "grad_norm": 2.8444556383038053,
+      "learning_rate": 6.652996478534394e-07,
+      "loss": 0.6996,
+      "step": 460
+    },
+    {
+      "epoch": 0.6342780026990553,
+      "grad_norm": 3.073223609545424,
+      "learning_rate": 6.244019412560143e-07,
+      "loss": 0.6941,
+      "step": 470
+    },
+    {
+      "epoch": 0.6477732793522267,
+      "grad_norm": 2.8831703732503753,
+      "learning_rate": 5.842231949544962e-07,
+      "loss": 0.7049,
+      "step": 480
+    },
+    {
+      "epoch": 0.6612685560053981,
+      "grad_norm": 3.060533732204664,
+      "learning_rate": 5.448403180879439e-07,
+      "loss": 0.679,
+      "step": 490
+    },
+    {
+      "epoch": 0.6747638326585695,
+      "grad_norm": 2.9803982323010585,
+      "learning_rate": 5.063286963622902e-07,
+      "loss": 0.6972,
+      "step": 500
+    },
+    {
+      "epoch": 0.6882591093117408,
+      "grad_norm": 2.8648873659535794,
+      "learning_rate": 4.687620477489337e-07,
+      "loss": 0.6894,
+      "step": 510
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 2.8594131054352054,
+      "learning_rate": 4.3221228137566223e-07,
+      "loss": 0.6984,
+      "step": 520
+    },
+    {
+      "epoch": 0.7152496626180836,
+      "grad_norm": 2.826483265916211,
+      "learning_rate": 3.9674935988002325e-07,
+      "loss": 0.6806,
+      "step": 530
+    },
+    {
+      "epoch": 0.728744939271255,
+      "grad_norm": 3.0466631136136875,
+      "learning_rate": 3.624411654886108e-07,
+      "loss": 0.7028,
+      "step": 540
+    },
+    {
+      "epoch": 0.7422402159244265,
+      "grad_norm": 2.8395840111896806,
+      "learning_rate": 3.293533700786286e-07,
+      "loss": 0.6966,
+      "step": 550
+    },
+    {
+      "epoch": 0.7557354925775979,
+      "grad_norm": 2.9054816392819154,
+      "learning_rate": 2.975493094704435e-07,
+      "loss": 0.6908,
+      "step": 560
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 2.9460246471571345,
+      "learning_rate": 2.670898621917629e-07,
+      "loss": 0.6947,
+      "step": 570
+    },
+    {
+      "epoch": 0.7827260458839406,
+      "grad_norm": 2.941971675288718,
+      "learning_rate": 2.3803333294549644e-07,
+      "loss": 0.6795,
+      "step": 580
+    },
+    {
+      "epoch": 0.796221322537112,
+      "grad_norm": 3.0680540747802527,
+      "learning_rate": 2.104353410043712e-07,
+      "loss": 0.6743,
+      "step": 590
+    },
+    {
+      "epoch": 0.8097165991902834,
+      "grad_norm": 3.1007189679330374,
+      "learning_rate": 1.843487137459261e-07,
+      "loss": 0.6941,
+      "step": 600
+    },
+    {
+      "epoch": 0.8232118758434548,
+      "grad_norm": 2.8712948349597625,
+      "learning_rate": 1.598233855316856e-07,
+      "loss": 0.6827,
+      "step": 610
+    },
+    {
+      "epoch": 0.8367071524966262,
+      "grad_norm": 3.028709196939323,
+      "learning_rate": 1.369063021240665e-07,
+      "loss": 0.7058,
+      "step": 620
+    },
+    {
+      "epoch": 0.8502024291497976,
+      "grad_norm": 2.8663884949478655,
+      "learning_rate": 1.1564133082398942e-07,
+      "loss": 0.6926,
+      "step": 630
+    },
+    {
+      "epoch": 0.863697705802969,
+      "grad_norm": 2.7965685313183983,
+      "learning_rate": 9.606917650120083e-08,
+      "loss": 0.6902,
+      "step": 640
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 2.9702187500416426,
+      "learning_rate": 7.822730367804331e-08,
+      "loss": 0.6809,
+      "step": 650
+    },
+    {
+      "epoch": 0.8906882591093117,
+      "grad_norm": 2.9740711603347534,
+      "learning_rate": 6.214986481581364e-08,
+      "loss": 0.6846,
+      "step": 660
+    },
+    {
+      "epoch": 0.9041835357624831,
+      "grad_norm": 3.108653359820244,
+      "learning_rate": 4.786763494098689e-08,
+      "loss": 0.6845,
+      "step": 670
+    },
+    {
+      "epoch": 0.9176788124156545,
+      "grad_norm": 3.0730509775220005,
+      "learning_rate": 3.540795273643926e-08,
+      "loss": 0.6942,
+      "step": 680
+    },
+    {
+      "epoch": 0.9311740890688259,
+      "grad_norm": 2.8851954067191885,
+      "learning_rate": 2.479466821043419e-08,
+      "loss": 0.6858,
+      "step": 690
+    },
+    {
+      "epoch": 0.9446693657219973,
+      "grad_norm": 2.7753430457192816,
+      "learning_rate": 1.604809704353949e-08,
+      "loss": 0.6911,
+      "step": 700
+    },
+    {
+      "epoch": 0.9581646423751687,
+      "grad_norm": 2.894348481910036,
+      "learning_rate": 9.184981700866346e-09,
+      "loss": 0.6892,
+      "step": 710
+    },
+    {
+      "epoch": 0.97165991902834,
+      "grad_norm": 2.9242281390477505,
+      "learning_rate": 4.218459384065953e-09,
+      "loss": 0.6878,
+      "step": 720
+    },
+    {
+      "epoch": 0.9851551956815114,
+      "grad_norm": 3.0382180715715568,
+      "learning_rate": 1.1580368844316125e-09,
+      "loss": 0.6897,
+      "step": 730
+    },
+    {
+      "epoch": 0.9986504723346828,
+      "grad_norm": 3.0414366034886235,
+      "learning_rate": 9.572385238243441e-12,
+      "loss": 0.6865,
+      "step": 740
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 741,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 350,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.306076234857578e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2972accc9d738f819604a83095fbac9d0518b360b7d97ed2b4ef2f45dc082894
+size 6776

zero_to_fp32.py

@@ -0,0 +1,587 @@
+#!/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 . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+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):
+    """
+    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)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+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 _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()
+            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):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _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 param_shapes.items():
+
+        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):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _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):
+    """
+    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``
+
+    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)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    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_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``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``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+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_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    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("-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_file, tag=args.tag)