Update README.md

README.md

@@ -1,3 +1,101 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+base_model: unsloth/llama-3-8b-bnb-4bit
+---
+
+# VeriUS LLM 8b v0.2
+
+VeriUS LLM is a generative model that is fine-tuned on Llama-3-8B (Unsloth).
+
+
+## Model Details
+Base Model: unsloth/llama-3-8b-bnb-4bit
+
+Training Dataset: A combined dataset of alpaca, dolly and bactrainx which is translated to turkish.
+
+Training Method: Fine-tuned with Unsloth, which uses QLoRA. Used ORPO
+
+#TrainingArguments
+PER_DEVICE_BATCH_SIZE: 2
+GRADIENT_ACCUMULATION_STEPS: 4
+WARMUP_RATIO: 0.03
+NUM_EPOCHS: 2
+LR: 0.000008
+OPTIM: "adamw_8bit"
+WEIGHT_DECAY: 0.01
+LR_SCHEDULER_TYPE: "linear"
+BETA: 0.1
+
+#PEFT Arguments
+RANK: 128
+TARGET_MODULES:
+  - "q_proj"
+  - "k_proj"
+  - "v_proj"
+  - "o_proj"
+  - "gate_proj"
+  - "up_proj"
+  - "down_proj"
+
+LORA_ALPHA: 256
+LORA_DROPOUT: 0
+BIAS: "none"
+GRADIENT_CHECKPOINT: 'unsloth'
+USE_RSLORA: false
+
+## Usage
+This model is trained used Unsloth and uses it for fast inference. For Unsloth installation please refer to: https://github.com/unslothai/unsloth
+
+This model can also be loaded with AutoModelForCausalLM
+
+How to load with unsloth:
+```commandline
+from unsloth import FastLanguageModel
+
+max_seq_len = 2048
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="VeriUs/VeriUS-LLM-8b-v0.2",
+    max_seq_length=max_seq_len,
+    dtype=None,
+    load_in_4bit=True
+)
+FastLanguageModel.for_inference(model)  # Enable native 2x faster inference
+
+prompt_tempate = """Aşağıda, görevini açıklayan bir talimat ve daha fazla bağlam sağlayan bir girdi verilmiştir. İsteği uygun bir şekilde tamamlayan bir yanıt yaz.
+
+### Talimat:
+{}
+
+### Girdi:
+{}
+
+### Yanıt:
+"""
+
+
+def generate_output(instruction, user_input):
+    input_ids = tokenizer(
+        [
+            prompt_tempate.format(instruction, user_input)
+        ], return_tensors="pt").to("cuda")
+
+    outputs = model.generate(**input_ids, max_length=max_seq_len, do_sample=True)
+
+    # removes prompt, comment this out if you want to see it.
+    outputs = [output[len(input_ids[i].ids):] for i, output in enumerate(outputs)]
+
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+
+response = generate_output("Türkiye'nin en kalabalık şehri hangisidir?", "")
+print(response)
+```
+
+## Bias, Risks, and Limitations
+
+Limitations and Known Biases
+Primary Function and Application: VeriUS LLM, an autoregressive language model, is primarily designed to predict the next token in a text string. While often used for various applications, it is important to note that it has not undergone extensive real-world application testing. Its effectiveness and reliability across diverse scenarios remain largely unverified.
+
+Language Comprehension and Generation: The base model is primarily trained in standard English. Even though it fine-tuned with and Turkish dataset, its performance in understanding and generating slang, informal language, or other languages may be limited, leading to potential errors or misinterpretations.
+
+Generation of False Information: Users should be aware that VeriUS LLM may produce inaccurate or misleading information. Outputs should be considered as starting points or suggestions rather than definitive answers.