Upload BloomForCausalLM

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/bloomz-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,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

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": "4.36.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54dbf40954ab509b0b7def8b086dd364e1ed29774205e36b8aebc5ea40f5cd6
+size 4975258008

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d01817368c8d363a3ce93129fa4982d561db31986f3ae152eafe23d62da9048
+size 4866712640

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68eef13caa855e901d2c9174bee74df7692675fe969dd42c34db1f7507e0d7f
+size 4296104456

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+  "metadata": {
+    "total_size": 14138032128
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.20.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.20.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.20.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.21.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.dense.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.dense.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.7.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.7.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.8.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.8.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.8.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.self_attention.dense.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.9.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
+    "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00003.safetensors",
+    "transformer.word_embeddings_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.word_embeddings_layernorm.weight": "model-00001-of-00003.safetensors"
+  }
+}