Upload 11 files

config.json

@@ -0,0 +1,45 @@
+{
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "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
+    }
+  },
+  "transformers_version": "4.57.6",
+  "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": "4.57.6"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69af2b70e27a9536cdb484d6f0d7c7c68c0fcec8e58a9c3f807618dc91bca669
+size 154389640

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad397cafc64d18a8087da4352480a02126499ec3825f022434b48fd77229a2dd
+size 97666440

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6dba5feebfd6e860130d4c35037822932f36e030386a826cf8d98d55c426745
+size 75601856

model.safetensors.index.json

@@ -0,0 +1,84 @@
+{
+  "metadata": {
+    "total_parameters": 81912576,
+    "total_size": 327650304
+  },
+  "weight_map": {
+    "transformer.h.0.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.0.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.0.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.0.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.1.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.1.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.1.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.1.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.2.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.2.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.3.attn.c_attn.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.3.attn.c_attn.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.3.attn.c_proj.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.3.attn.c_proj.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.4.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.4.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.5.attn.c_attn.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.5.attn.c_attn.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.5.attn.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.5.attn.c_proj.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00003-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-00002-of-00003.safetensors",
+    "transformer.wte.weight": "model-00001-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}