Adding `safetensors` variant of this model

.gitattributes

@@ -33,7 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-Downloaded_Repo-134M-F16.gguf filter=lfs diff=lfs merge=lfs -text
-KateAI.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
-KateAI.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
-KateAI.SOURCE.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,43 +1,21 @@
----
-language:
-- en
-pipeline_tag: text-generation
-datasets:
-- roneneldan/TinyStories
-- bookcorpus/bookcorpus
----
-
-# **Warning!!**
-
-This model is in the process of being moved from gpt2 architecture -> a custom architecture.
-Note that it may not work at certain times because of the moving.
-Thank you for understanding.
-
-# Kate
-
-This is a custom model for text generation.
-Money wasted: 11€
-
-## Model Details
-
-- `model_type`: KateAIForCasualLM
-
-## Usage
-
-Please use the api of the space.
-```
-pip install gradio_client
-```
-```
-from gradio_client import Client
-
-client = Client("unamedai/Kate")
-result = client.predict(
-    message="Once,",
-    max_tokens=512,
-    temperature=0.8,
-    top_p=0.95,
-    api_name="/predict"
-)
-print(result)
-```
+---
+language:
+- en
+pipeline_tag: text2text-generation
+---
+# My Custom Model
+
+This is a custom model for text generation.
+
+## Model Details
+
+- `model_type`: Sparkoo
+
+## Usage
+
+```python
+from transformers import AutoModel, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("Sparkoo/KateAi")
+model = AutoModel.from_pretrained("Sparkoo/KateAi", from_safetensors=True)
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -1,7 +1,7 @@
 {
   "activation_function": "gelu_new",
   "architectures": [
-    "KateAIForCausalLM"
+    "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
@@ -9,28 +9,23 @@
   "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "model_type": "kate",
-  "n_ctx": 768,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
   "n_embd": 768,
-  "num_heads": 8,
-  "n_inner": null,
-  "num_layers": 8,
-  "hidden_size": 768,
-  "pad_token_id": 50256,
-  "max_seq_length": 512,
-  "intermediate_size": 3072,
-  "dropout": 0.1,
-  "reorder_and_upcast_attn": false,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 1024,
   "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": "4.47.1",
-  "use_cache": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
   "vocab_size": 50257
-}
+}

custom_tokenizer.json

@@ -0,0 +1 @@
+{"word_to_index": {"[PAD]": 0, "[UNK]": 1, "[SOS]": 2, "[EOS]": 3, "a": 4, "sentence.": 5, "are": 6, "language": 7, "this": 8, "is": 9, "test": 10, "another": 11, "example": 12, "transformers": 13, "powerful": 14, "models.": 15, "let's": 16, "train": 17, "simple": 18, "model.": 19, "models": 20, "amazing": 21, "at": 22, "generating": 23, "text.": 24}, "special_tokens": ["[PAD]", "[UNK]", "[SOS]", "[EOS]"]}

generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
-  "pad_token_id": 50256,
-  "transformers_version": "4.47.1"
-}

model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5f33c78bcb29e09bd4f398e95ae06c46770a137acfef824ecf28e017e7866aa5
-size 537377892

model_card.yaml

@@ -0,0 +1,17 @@
+
+---
+model-index:
+- name: sparkoo
+  results: []
+  model-type: sparkoo
+  paperswithcode-id: null
+  cn-model: null
+  hf-hub-id: Sparkoo/sparkooKateAI
+  release-notes: null
+  ethical-source: null
+  language: en
+  libs-version: 4.41.2
+  tags:
+  - sparkoo
+  - seq2seq
+---

special_tokens_map.json

@@ -1,24 +1,13 @@
-{
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<|endoftext|>",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1,23 +1,57 @@
-{
-  "add_bos_token": false,
-  "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|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
-}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}