Upload GPTJForCausalLM

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "/models/checkpoints/pyg-exp-syn-joined/checkpoint-2090",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 64,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50400
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e42f0f202a44933b978d500a9755597bd658d52c03ee31305dd8dea3867cb9
+size 10044463672

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a98925da240ada60476072ff3009912007db0b148520ed7557e74be8ab9b0ca
+size 2174856859

pytorch_model.bin.index.json

@@ -0,0 +1,348 @@
+{
+  "metadata": {
+    "total_size": 12116445688.0
+  },
+  "weight_map": {
+    "lm_head.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.0.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.3.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.masked_bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}