Upload folder using huggingface_hub

README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1 @@
+{"auto_mapping": null, "base_model_name_or_path": "atsuki-yamaguchi/bloom-7b1-clp-ja", "bias": "none", "fan_in_fan_out": false, "inference_mode": true, "init_lora_weights": true, "layers_pattern": null, "layers_to_transform": null, "lora_alpha": 32, "lora_dropout": 0.05, "modules_to_save": ["lm_head", "word_embeddings"], "peft_type": "LORA", "r": 8, "revision": null, "target_modules": ["query_key_value", "dense", "dense_h_to_4h", "dense_4h_to_h"], "task_type": "CAUSAL_LM"}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86960b17f22feba1a62e874b2f0713272aadee73c8c59ad51497b885c249a72
+size 1111524920

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-7b1",
+  "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": "float64",
+  "transformers_version": "4.39.0.dev0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:209fe509446ffcce8a36ce9f056d1e74cf2312d6b8b93666a6016fd956b2a401
+size 4807760936

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d129fe531c1cf536393f62b08f0a6f7ced656a3e275d5adfad796e17bd804a
+size 4833124616

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3119cead87c42bc1c9929e61756aa0203c6417dd5b3a12cf37aa2b41182030cc
+size 4833124696

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9c42f65ecc0bde5afe6902d3d673a7550c7b5caf09be4be4393cae437cf0160
+size 4833124696

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02ab42d6c8f666bd71ff1795806632fbcc0819c494af457bc451e17ec8e2a7a
+size 4833124696

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e75478c5ffd8de11b259dbaab1415808ac19f5b86b5645726208237ab4afbb4
+size 1074005816

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 25214222336
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.self_attention.dense.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.self_attention.dense.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.self_attention.dense.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.self_attention.query_key_value.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.self_attention.dense.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.self_attention.dense.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.self_attention.query_key_value.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.self_attention.dense.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.self_attention.query_key_value.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.29.input_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.self_attention.dense.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.self_attention.dense.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.self_attention.query_key_value.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.self_attention.dense.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.self_attention.dense.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.self_attention.dense.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.self_attention.query_key_value.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00002-of-00006.safetensors",
+    "transformer.ln_f.bias": "model-00006-of-00006.safetensors",
+    "transformer.ln_f.weight": "model-00006-of-00006.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00006.safetensors",
+    "transformer.word_embeddings_layernorm.bias": "model-00001-of-00006.safetensors",
+    "transformer.word_embeddings_layernorm.weight": "model-00001-of-00006.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca4df98b41e49381bfd60e429f4736264754f7664db2aea1feab7514bdd3d4a
+size 557114362

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f25c7a6aa4f56a4d283994878acdc2057c1cc32d632535279aaa055c1b8131
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2346009fd980a1b4473ca9be445f17789e6124cf95260d92529ae589a336956
+size 1064

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": "[MASK]",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d78ab344146700112cd41628ac7ce54b79c0868fe0c7c201750d8237b54dbb4
+size 786216

tokenizer_config.json

@@ -0,0 +1,76 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13765279c942ba4b8268ee0bf699cc97dc25f2212f642a4e65b8b555d352f79
+size 4664