Update README.md

README.md

@@ -1,3 +1,141 @@
 ---
+tags:
+- generated_from_trainer
+model-index:
+- name: Qra-7b-dolly-instruction-0.1
+  results: []
+datasets:
+- s3nh/alpaca-dolly-instruction-only-polish
+language:
+- pl
+inference: true
 license: apache-2.0
+pipeline_tag: text-generation
 ---
+
+# Qra-7b-dolly-instruction-0.1
+
+This model if a fine-tuned version of [OPI-PG/Qra-7b](https://huggingface.co/OPI-PG/Qra-7b) on the [s3nh/alpaca-dolly-instruction-only-polish](https://huggingface.co/datasets/s3nh/alpaca-dolly-instruction-only-polish) dataset.
+
+## Model Description
+
+Trained from [OPI-PG/Qra-7b](https://huggingface.co/OPI-PG/Qra-7b)
+
+## Intended uses & limitations
+
+This model has been fine-tuned for question-answering task. It is possible to use it as a chat, but it doesn't work well because the dataset did not contain conversations.
+
+```py
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+model_id = "nie3e/Qra-7b-dolly-instruction-0.1"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+pipe = pipeline(
+    "text-generation", model=model, tokenizer=tokenizer, device=device
+)
+
+def get_answer(system_prompt: str, user_prompt: str) -> str:
+    input_msg = [
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": user_prompt}
+    ]
+    prompt = pipe.tokenizer.apply_chat_template(
+        input_msg, tokenize=False,
+        add_generation_prompt=True
+    )
+    outputs = pipe(
+        prompt, max_new_tokens=512, do_sample=False, temperature=0.1, top_k=50,
+        top_p=0.1, eos_token_id=pipe.tokenizer.eos_token_id,
+        pad_token_id=pipe.tokenizer.pad_token_id
+    )
+    return outputs[0]['generated_text'][len(prompt):].strip()
+
+print(
+        get_answer(
+        system_prompt="Jesteś przyjaznym chatbotem",
+        user_prompt="Napisz czym jest dokument architectural decision record."
+    )
+)
+```
+
+## Training and evaluation data
+
+Dataset: [s3nh/alpaca-dolly-instruction-only-polish](https://huggingface.co/datasets/s3nh/alpaca-dolly-instruction-only-polish)
+
+Each row has been converted into conversation using this function:
+```py
+system_message = """Jesteś przyjaznym chatbotem"""
+
+def create_conversation(sample) -> dict:
+    strip_characters = "\"'"
+    return {
+        "messages": [
+            {"role": "system", "content": system_message},
+            {"role": "user",
+             "content": f"{sample['instruction'].strip(strip_characters)} "
+                        f"{sample['input'].strip(strip_characters)}"},
+            {"role": "assistant",
+             "content": f"{sample['output'].strip(strip_characters)}"}
+        ]
+    }
+```
+
+Train/test split: 90%/10%
+
+## Training procedure
+
+GPU: 2x RTX 4060Ti 16GB
+Training time: ~13 hours
+
+Using `device_map="auto"`
+
+### Training hyperparameters
+
+Lora config:
+```py
+peft_config = LoraConfig(
+    lora_alpha=128,
+    lora_dropout=0.05,
+    r=256,
+    bias="none",
+    target_modules="all-linear",
+    task_type="CAUSAL_LM"
+)
+```
+
+Training arguments:
+```py
+args = TrainingArguments(
+    output_dir="Qra-7b-dolly-instruction-0.1",
+    num_train_epochs=3,
+    per_device_train_batch_size=1,
+    gradient_accumulation_steps=6,
+    gradient_checkpointing=True,
+    optim="adamw_torch_fused",
+    logging_steps=10,
+    save_strategy="epoch",
+    learning_rate=2e-4,
+    bf16=True,
+    tf32=True,
+    max_grad_norm=0.3,
+    warmup_ratio=0.03,
+    lr_scheduler_type="constant",
+    push_to_hub=False,
+    report_to=["tensorboard"],
+)
+```
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2