Upload GPTBigCodeForCausalLM

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bigcode/starcoder",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 6144,
+  "n_head": 48,
+  "n_inner": 24576,
+  "n_layer": 40,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": true,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.32.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d36889bea73951ead5934433b1a3a4d6f93162c5a643db7e81437cb0ae64195
+size 9957947824

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4bb44becb0d6fb141efcc62ade2e67ae554de371ed3eaa795ecb200c13ed756
+size 9857346344

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba923fcb2da15187c12cb80614b1b12ccb8243bfedb06426265e68635d6c6c1
+size 9857346344

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5db7b9405bbf2146e54fa7c8ced369202eba4fc042a923727ec00e519e259d6
+size 1362323832

model.safetensors.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_size": 31034912768
+  },
+  "weight_map": {
+    "transformer.h.0.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.0.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.0.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.1.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.1.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.10.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.10.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.10.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.10.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.11.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.11.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.11.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.11.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.12.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.12.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.12.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.12.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.13.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.13.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.14.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.14.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.15.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.15.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.16.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.16.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.17.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.17.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.18.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.18.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.18.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.18.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.19.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.19.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.19.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.19.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.2.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.2.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.2.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.20.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.20.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.20.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.20.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.21.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.21.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.21.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.21.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.22.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.22.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.22.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.22.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.23.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.23.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.23.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.23.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.24.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.24.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.24.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.24.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.24.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.24.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.24.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.24.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.24.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.24.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.25.attn.c_attn.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.25.attn.c_attn.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.25.attn.c_proj.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.25.attn.c_proj.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.25.ln_2.bias": "model-00002-of-00004.safetensors",
+    "transformer.h.25.ln_2.weight": "model-00002-of-00004.safetensors",
+    "transformer.h.25.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.25.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.25.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.25.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.26.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.26.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.26.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.26.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.26.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.26.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.27.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.27.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.27.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.27.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.27.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.27.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.28.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.28.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.28.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.28.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.28.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.28.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.28.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.29.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.29.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.29.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.29.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.29.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.29.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.29.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.3.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.3.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.3.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.30.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.30.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.30.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.30.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.30.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.30.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.30.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.30.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.30.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.30.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.30.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.30.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.31.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.31.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.31.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.31.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.31.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.31.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.31.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.31.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.31.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.31.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.31.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.32.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.32.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.32.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.32.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.32.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.32.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.32.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.32.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.32.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.32.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.32.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.32.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.33.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.33.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.33.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.33.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.33.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.33.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.33.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.33.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.33.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.33.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.33.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.33.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.34.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.34.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.34.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.34.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.34.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.34.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.34.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.34.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.34.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.34.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.34.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.34.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.35.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.35.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.35.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.35.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.35.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.35.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.35.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.35.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.35.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.35.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.35.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.35.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.36.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.36.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.36.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.36.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.36.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.36.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.36.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.36.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.36.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.36.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.36.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.36.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.37.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.37.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.37.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.37.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.37.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.37.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.37.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.37.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.37.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.37.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.37.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.37.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.38.attn.c_attn.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.38.attn.c_attn.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.38.attn.c_proj.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.38.attn.c_proj.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.38.ln_1.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.38.ln_1.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.38.ln_2.bias": "model-00003-of-00004.safetensors",
+    "transformer.h.38.ln_2.weight": "model-00003-of-00004.safetensors",
+    "transformer.h.38.mlp.c_fc.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.38.mlp.c_fc.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.38.mlp.c_proj.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.38.mlp.c_proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.39.attn.c_attn.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.39.attn.c_attn.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.39.attn.c_proj.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.39.attn.c_proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.39.ln_1.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.39.ln_1.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.39.ln_2.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.39.ln_2.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.39.mlp.c_fc.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.39.mlp.c_fc.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.39.mlp.c_proj.bias": "model-00004-of-00004.safetensors",
+    "transformer.h.39.mlp.c_proj.weight": "model-00004-of-00004.safetensors",
+    "transformer.h.4.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.4.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.4.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.5.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.5.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.5.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.5.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.6.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.6.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.6.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.6.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.7.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.7.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.7.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.7.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.8.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.8.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.8.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.8.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.9.attn.c_attn.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.9.attn.c_attn.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.9.attn.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.9.attn.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
+    "transformer.ln_f.bias": "model-00004-of-00004.safetensors",
+    "transformer.ln_f.weight": "model-00004-of-00004.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00004.safetensors",
+    "transformer.wte.weight": "model-00001-of-00004.safetensors"
+  }
+}