Upload folder using huggingface_hub

tokenizer/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da969d56fc3a8fcb72ae57f1484be0a65fc365b6374d98c2460c16a53dceda0a
+size 4400216504

tokenizer/save.py

@@ -0,0 +1,20 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+from safetensors.torch import save_file
+
+# Load your model and tokenizer
+model_name = "Stefan171/TinyLlama-QuantumQuill-chat-12-05-24"
+model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Define the path to save the safetensors model in the current directory
+safetensors_path = "./model.safetensors"
+
+# Convert model parameters to a dictionary
+state_dict = model.state_dict()
+
+# Save the model parameters in safetensors format
+save_file(state_dict, safetensors_path)
+
+# Save the tokenizer in the current directory
+tokenizer.save_pretrained("./")

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": null,
+  "eos_token": "</s>",
+  "mask_token": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 16000,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sep_token": null,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

tokenizer/upload.py

@@ -0,0 +1,26 @@
+from huggingface_hub import HfApi
+
+api = HfApi()
+model_id = "Stefan171/TinyLlama-QuantumQuill-chat-12-05-24"
+
+# Path to the safetensors model file
+safetensors_path = "./model.safetensors"
+
+# Upload the safetensors model
+api.upload_file(
+    path_or_fileobj=safetensors_path,
+    path_in_repo="model.safetensors",
+    repo_id=model_id,
+    repo_type="model"
+)
+
+# Path to the tokenizer folder (current directory)
+tokenizer_path = "./"
+
+# Upload the tokenizer files
+api.upload_folder(
+    folder_path=tokenizer_path,
+    path_in_repo="tokenizer",
+    repo_id=model_id,
+    repo_type="model"
+)