Upload 11 files

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.27.4"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576cba0e7a7f5fdd4d43ed1a7e9dc1702ac4a6ecfa6f748f505e299a187b7f22
+size 197454115

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12809e94625edce2a91b147a5ddfbf7bc9811b4f4ad009494f456670753ddc97
+size 136516203

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2351eea05c8f20963705bf9d343b2b98e13e269bab900c9445144e9ae0d1649f
+size 154390442

pytorch_model.bin.index.json

@@ -0,0 +1,96 @@
+{
+  "metadata": {
+    "total_size": 482826264.0
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.0.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.wpe.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}