Delete folder checkpoint-603 with huggingface_hub

checkpoint-603/config.json

@@ -1,26 +0,0 @@
-{
-  "_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
-  "architectures": [
-    "MistralForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-05,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
-  "use_cache": false,
-  "vocab_size": 32002
-}

checkpoint-603/generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "do_sample": true,
-  "eos_token_id": 2,
-  "transformers_version": "4.38.2"
-}

checkpoint-603/global_step603/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:59370e22148d3a8a1d2cd4624d7946cbd7616b76121082a13fe7734a7d5d02c5
-size 4831623435

checkpoint-603/global_step603/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b53042893025c005ef60ddc8f3397c4183eccf3bb8d43ca6fe90b937586c5be3
-size 4831623435

checkpoint-603/global_step603/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cef9cf818255a83cde92a08ece9ca1eff5aaaf294200103287c9446b18ba83cb
-size 4831623435

checkpoint-603/global_step603/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:76a96afb8918f45759eb193305769f1d407427f79b37364fd4066fb832c4cf2b
-size 4831623435

checkpoint-603/global_step603/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:76f6f1b8a0c4a54dc38c3811a0160fe52885a7f82982e78eea9dbe8ec5be1799
-size 4831623435

checkpoint-603/global_step603/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:af7f387005cd25db76e0929d2bdbe6eec2be1a8b08e284fffba3a2c6b3c71bb5
-size 4831623435

checkpoint-603/global_step603/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c06d83b7316728ec5932771c7f7b3b8108c5ce6affa4f06d2f1909b490e0d58e
-size 4831623435

checkpoint-603/global_step603/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d58b1f6f3a57acccdd9de93ee37604f78994e878101c8d31e0b54ee51667710f
-size 4831623435

checkpoint-603/global_step603/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0e25c081ab69293c7624657196aa101e5f93da28fd53ce9c0ed7c2cde1e7bda5
-size 4831623435

checkpoint-603/global_step603/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a7f068ea32760e0b48dac2d6af9eac8a70cb1e844c7f3df607dba31b5b1a65bb
-size 153829

checkpoint-603/global_step603/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0f012302b249642f3647f99b5acf92cbab815fb99a79368a02ab1aa7147d9cc9
-size 153829

checkpoint-603/global_step603/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4aac9dbbcd4643c54be734b072c8a79493529ef0c76048fb783945075bdd0f4a
-size 153829

checkpoint-603/global_step603/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1df7d9f001aa84b5743fd10d6afb2a15e032818f728d246a9a55f62a90f78eb3
-size 153829

checkpoint-603/global_step603/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:549ad2aae080a1d987992d584bb537308f73c6734215531882ce33c6e440a523
-size 153829

checkpoint-603/global_step603/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:43eb9c0d5739614a0e52559181b5107c8b4a52fe8f2823b3a5fe055a536a2d27
-size 153829

checkpoint-603/global_step603/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eedbfca9cde614f50defef9af4967b35a4f4ccf27e94df4ad2ff4be358848b54
-size 153829

checkpoint-603/global_step603/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ada9a3962cbc0dd20da5343bc7f4aa055b4e752ab514423e555f7cbdbc2b3c2c
-size 153829

checkpoint-603/global_step603/zero_pp_rank_8_mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f40ba5b0013f52277f2af3d3822c99d8fdae8a69c1c3c7c3794949261d198b86
-size 153829

checkpoint-603/latest

@@ -1 +0,0 @@
-global_step603

checkpoint-603/model-00001-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:25433fce8850cf2c8bfb942d2859f8b1ae795d54153015bfda50c860636f2d33
-size 4943178720

checkpoint-603/model-00002-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1b4ab548de5173dd2f658babb32a5dc829cbec02780d3349d8fe38ea754d6e0e
-size 4999819336

checkpoint-603/model-00003-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:647792278f578fc90f83abfaef9375524293e96a59884f35e68895f545856809
-size 4540532728

checkpoint-603/model.safetensors.index.json

@@ -1,298 +0,0 @@
-{
-  "metadata": {
-    "total_size": 14483496960
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00003-of-00003.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors"
-  }
-}

checkpoint-603/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d78df38122b8b51b69a3cce1a8d8cb0f7d8684196dde8fb6d174ef0fd3440d89
-size 16240

checkpoint-603/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:499f46e15237a5856de1a8f0582d02e4319721d83140e01c31e9e1db92da7108
-size 16240

checkpoint-603/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4b32ec8b414a3886bf179af827449dee557e95bfa64a7c20f26c186df2659c9f
-size 16240

checkpoint-603/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:82765e3b8fb57ca7779e75617b51182226eed278593e6441a31510115950353d
-size 16240

checkpoint-603/rng_state_4.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6dd2c24e041054b45b5bf8c50512ea8c4552e5f2e877fe798759dec7a7f3aae1
-size 16240

checkpoint-603/rng_state_5.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:92b3e1210264272a2020cbcb79f6ade48528f5682dadcecb7a94805779548161
-size 16240

checkpoint-603/rng_state_6.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:556ec0b910e14a1a5ab8fb6a1a16d525b89e31c69dd9b6cd8d4a4cccad65b546
-size 16240

checkpoint-603/rng_state_7.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e830dc416886fe1aafeacfa75da6baacdbe9a61c66d2f1fbc11417753a516513
-size 16240

checkpoint-603/rng_state_8.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80d7cb0002af3e22c063c6751b91836d7e06c4267f7ba8e1912c42d6867e4885
-size 16240

checkpoint-603/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1cf517ae91e21a035522e0b4a4fedb4101eafa6a9cc5b1728a258fae8d83e6cb
-size 1064

checkpoint-603/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f7f4a52e7a4e455192e0e321f42138a81946c62773f6570625fe5cb773689e26
-size 7352

checkpoint-603/zero_to_fp32.py

@@ -1,592 +0,0 @@
-#!/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 _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):
-    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)