Push to HF hub

.gitattributes

@@ -0,0 +1,25 @@
+checkpoint-5000/global_step5000/mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/global_step5000/zero_pp_rank_0_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/global_step5000/zero_pp_rank_1_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/global_step5000/zero_pp_rank_2_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/global_step5000/zero_pp_rank_3_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/global_step5000/zero_pp_rank_4_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/global_step5000/zero_pp_rank_5_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/global_step5000/zero_pp_rank_6_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/global_step5000/zero_pp_rank_7_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/rng_state_1.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/rng_state_2.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/rng_state_3.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/rng_state_4.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/rng_state_5.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/rng_state_6.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/rng_state_7.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/training_args.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,5 @@
+checkpoint-20000/
+checkpoint-25000/
+checkpoint-15000/
+checkpoint-10000/
+checkpoint-5000/

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "bigscience/bloom-7b1",
+  "adapters": {
+    "adapters": {},
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusions": {}
+  },
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 30,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.20.0.dev0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230cf5e74ef0dfcc3a5d8bf0d295db444c6b1d097dc6ff4c23ea9a79aad1a533
+size 14138065939

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15630ffcb92d9e7bb1dce4378db5a9bfbaeefa6a92f8655c4145cdc73b153b9e
+size 14138049747

pytorch_model.bin.index copy.json

@@ -0,0 +1,373 @@
+{
+  "metadata": {
+    "total_size": 16193241088
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

pytorch_model.bin.index.json

@@ -0,0 +1,373 @@
+{
+  "metadata": {
+    "total_size": 16193241088
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
+size 14500443

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "add_prefix_space": false, "name_or_path": "bigscience/bloom-7b1", "special_tokens_map_file": null, "padding_side": "left", "tokenizer_class": "BloomTokenizer"}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 2.62109375,
+  "best_model_checkpoint": "/home/zhengxinyong/outputs/bloom-7b1_de_continual-pretrain_100000samples_-1vocab_original/checkpoint-15000",
+  "epoch": 1.6485328058028355,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0001,
+      "loss": 3.0311,
+      "step": 2500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0001,
+      "loss": 2.7334,
+      "step": 5000
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 2.775390625,
+      "eval_runtime": 12.1862,
+      "eval_samples_per_second": 65.976,
+      "eval_steps_per_second": 8.288,
+      "step": 5000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0001,
+      "loss": 2.6307,
+      "step": 7500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001,
+      "loss": 2.4576,
+      "step": 10000
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 2.68359375,
+      "eval_runtime": 12.1913,
+      "eval_samples_per_second": 65.949,
+      "eval_steps_per_second": 8.285,
+      "step": 10000
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001,
+      "loss": 2.2705,
+      "step": 12500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001,
+      "loss": 2.2921,
+      "step": 15000
+    },
+    {
+      "epoch": 1.65,
+      "eval_loss": 2.62109375,
+      "eval_runtime": 12.1817,
+      "eval_samples_per_second": 66.0,
+      "eval_steps_per_second": 8.291,
+      "step": 15000
+    }
+  ],
+  "max_steps": 25000,
+  "num_train_epochs": 3,
+  "total_flos": 4.4542120389519606e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c419972f4b56ec21c71afa39eb805af3cd86942e2c33ef1c8b084aa1d90d6d
+size 4399