Upload folder using huggingface_hub

README.md

@@ -1,3 +1,55 @@
 ---
 license: apache-2.0
+tags:
+- TinyLlama
+- QLoRA
+- Politics
+- EU
+- News
+- sft
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 ---
+
+# TinyPoliticaLlama-1.1B
+
+TinyPoliticaLlama-1.1B is a SFT fine-tune of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) and a sister model of [h4rz3rk4s3/TinyParlaMintLlama-1.1B](https://huggingface.co/h4rz3rk4s3/TinyParlaMintLlama-1.1B) and [h4rz3rk4s3/TinyNewsLlama-1.1B](https://huggingface.co/h4rz3rk4s3/TinyNewsLlama-1.1B).
+This model was fine-tuned for ~24h on one A100 40GB on ~225M tokens on the training corpora of both her sister models.
+
+The goal of this project is to study the potential for improving the domain-specific (in this case political) knowledge of small (<3B) LLMs by concentrating the training datasets TF-IDF in respect to the underlying Topics found in the origianl Dataset.
+
+The used training data contains speeches from the **Austrian**, **Danish**, **French**, **British**, **Hungarian**, **Dutch**, **Norwegian**, **Polish**, **Swedish** and **Turkish** Parliament, as well as political news articles from **The New York Times**, **USA Today** and **The Washington Times**.
+
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from accelerate import Accelerator
+import transformers
+import torch
+model = "h4rz3rk4s3/TinyPoliticaLlama-1.1B"
+messages = [
+    {
+        "role": "system",
+        "content": "You are an experienced journalist in the political domain and an expert of European politics.",
+    },
+    {"role": "user", "content": "Write a short article explaining how the French yellow vest protests started, how they developed over time and how the French Government reacted to the protests."},
+]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model, trust_remote_code=True, device_map={"": Accelerator().process_index}
+)
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    tokenizer=tokenizer,
+    model=model,
+    torch_dtype=torch.float16,
+    device_map={"": Accelerator().process_index},
+)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/Masterarbeit/Tiny-Llama",
+  "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,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0",
+  "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": "4.38.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0a410e00bb3e3417b21d8550061c5e5fef16975b82ae55bda24df5cefdc4a3
+size 2200119864

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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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
+}