Upload folder using huggingface_hub

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bigcode/starcoderbase-3b",
+  "activation_function": "gelu_pytorch_tanh",
+  "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": 2816,
+  "n_head": 22,
+  "n_inner": 11264,
+  "n_layer": 36,
+  "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": "float32",
+  "transformers_version": "4.39.1",
+  "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": "4.39.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7a5d141bb0089ad330824310fe9fa86f7e523d1b7228a2cbaf2a74ec87d3af
+size 4874967008

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c640fed7d32450750ad2b97575df5c04748fa341e4a886128424f78fda8a9939
+size 4929983264

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca52a1f308229b40a18fbf3a8c25c61c07e2e9d3ed4a9f28c127d9fdfd8cbf7
+size 2368340008

model.safetensors.index.json

@@ -0,0 +1,443 @@
+{
+  "metadata": {
+    "total_size": 12173244416
+  },
+  "weight_map": {
+    "transformer.h.0.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.20.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.24.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.25.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.26.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.27.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.28.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.3.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.30.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.32.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.32.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.32.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.32.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.32.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.32.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.32.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.32.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.32.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.32.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.32.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.32.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.33.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.33.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.33.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.33.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.33.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.33.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.33.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.33.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.33.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.33.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.33.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.33.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.34.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.34.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.34.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.34.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.34.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.34.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.34.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.34.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.34.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.34.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.34.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.34.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.35.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.35.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.35.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.35.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.35.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.35.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.35.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.35.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.35.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.35.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.35.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.35.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.c_attn.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.c_attn.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.attn.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
+    "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
+    "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00003.safetensors",
+    "transformer.wte.weight": "model-00001-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,186 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:192787e14650e9dcc746872c8d4a95db39ed2c8922634f85b71f7731eea75da5
+size 5176