Initial commit

README.md

@@ -0,0 +1,79 @@
+---
+tags:
+- text-generation
+license: cc-by-nc-sa-4.0
+language:
+- ko
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+pipeline_tag: text-generation
+---
+
+# **DataVortexTL-1.1B-v0.1**
+<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">
+
+## **License**
+
+[cc-by-nc-sa-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)
+
+## **Model Details**
+
+### **Base Model**
+[TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)  
+
+### **Trained On**
+H100 80GB 1ea
+
+### **Instruction format**
+
+<!-- It follows **(No Input) Alpaca** format. -->
+
+## **Model Benchmark**
+
+### **Ko-LLM-Leaderboard**
+
+On Benchmarking...
+
+# **Implementation Code**
+
+Since, chat_template already contains insturction format above.
+You can use the code below.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+device = "cuda"
+
+model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexTL-1.1B-v0.1", device_map=device)
+tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexTL-1.1B-v0.1")
+
+messages = [
+    { "role": "user", "content": "대한민국의 수도는 어디야?" }
+]
+
+encoded = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt",
+    return_token_type_ids=False
+).to(device)
+
+decoded = model.generate(
+    input_ids=encoded,
+    temperature=0.2,
+    top_p=0.9,
+    repetition_penalty=1.2,
+    do_sample=True,
+    max_length=4096,
+    eos_token_id=tokenizer.eos_token_id,
+    pad_token_id=tokenizer.eos_token_id
+)
+decoded = decoded[0][encoded.shape[1]:decoded[0].shape[-1]]
+decoded_text = tokenizer.decode(decoded, skip_special_tokens=True)
+print(decoded_text)
+```
+
+<div align="center">
+    <a href="https://edentns.com/">
+        <img src="./Logo.png" alt="Logo" style="height: 3em;">
+    </a>
+</div>

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Edentns/DataVortexTL-1.1B-v0.1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e85fb779e33786c72ae49ce2d557849ca75e3f510ddbe0a6d62b3e993554d2
+size 2200119864

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "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,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}