Upload 7 files

README.md

@@ -0,0 +1,36 @@
+---
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- testing
+- random-initialization
+- gpt2
+---
+# Tiny random GPT-2 for testing
+
+This model is randomly initialized and **has not been trained**. It is for
+testing upload, download, tokenization, and model loading only. Its output is
+not meaningful and it is not suitable for real language tasks or benchmarking.
+No pretrained model weights or training datasets were used.
+
+Architecture: 1 GPT-2 layer, 1 attention head, 16 hidden dimensions,
+32 vocabulary tokens, and a maximum context length of 64 tokens.
+Parameter count: 3792.
+
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+repo = "ruhook/test-ruhook"
+tokenizer = AutoTokenizer.from_pretrained(repo)
+model = AutoModelForCausalLM.from_pretrained(repo)
+inputs = tokenizer("hello world", return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=5, do_sample=False)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+Validated locally with Python 3, torch 2.2.2 and transformers 4.46.3.
+The toy word-level tokenizer maps words outside its small vocabulary to UNK.

config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 2,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 3,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 64,
+  "n_embd": 16,
+  "n_head": 1,
+  "n_inner": 32,
+  "n_layer": 1,
+  "n_positions": 64,
+  "pad_token_id": 0,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 32
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96ccdf45486148fb74372624cac7cc827f005453c2da736f0d688464a9f0117
+size 16616

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "[BOS]",
+  "eos_token": "[EOS]",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,87 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "[BOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[EOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "[PAD]": 0,
+      "[UNK]": 1,
+      "[BOS]": 2,
+      "[EOS]": 3,
+      "hello": 4,
+      "world": 5,
+      "this": 6,
+      "is": 7,
+      "a": 8,
+      "tiny": 9,
+      "test": 10,
+      "model": 11,
+      "the": 12,
+      "cat": 13,
+      "sat": 14,
+      "on": 15,
+      "mat": 16,
+      ".": 17,
+      "I": 18,
+      "you": 19,
+      "we": 20,
+      "like": 21,
+      "code": 22,
+      "and": 23,
+      "data": 24,
+      "good": 25,
+      "morning": 26,
+      "one": 27,
+      "two": 28,
+      "three": 29,
+      "yes": 30,
+      "no": 31
+    },
+    "unk_token": "[UNK]"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "model_max_length": 64,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}