Upload model

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./models/rm_sft_tldr_pythia_1_4b",
+  "architectures": [
+    "ScalarModel"
+  ],
+  "base_config": {
+    "_name_or_path": "./models/sft_tldr_pythia_1_4b",
+    "architectures": [
+      "GPTNeoXForCausalLM"
+    ],
+    "eos_token_id": 0,
+    "hidden_size": 2048,
+    "intermediate_size": 8192,
+    "model_type": "gpt_neox",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 50304
+  },
+  "base_model": "./models/sft_tldr_pythia_1_4b",
+  "bias": 6.552486854455443,
+  "hidden_size": 2048,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58ef2b673e965393f80d8ef57af3839e1696de9de1a27e40a6550218e4f8890
+size 4978029579

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b866e7f65ecc2a2762e9d32e69a0672059169c9446a01d4d1e9409fdb6f659a
+size 268581422

pytorch_model.bin.index.json

@@ -0,0 +1,300 @@
+{
+  "metadata": {
+    "total_size": 5246509060
+  },
+  "weight_map": {
+    "lm_backbone.embed_in.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.0.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.23.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_backbone.layers.3.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "lm_backbone.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "scalar_head.bias": "pytorch_model-00002-of-00002.bin",
+    "scalar_head.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}