Update readme

README.md

@@ -1,58 +1,106 @@
+
 ---
-base_model: meta-llama/Llama-3.2-3B-Instruct
-library_name: transformers
-model_name: results
+license: apache-2.0
+language:
+- en
 tags:
-- generated_from_trainer
-- sft
-- trl
-licence: license
+- llm
+- fine-tune
+- qlora
+- llama
+- bitcoin
+- finance
+- cryptocurrency
+pipeline_tag: text-generation
+base_model: meta-llama/Llama-3.2-3B-Instruct
+datasets:
+- tahamajs/bitcoin-llm-finetuning-dataset
 ---
 
-# Model Card for results
+-----
+
+### **Overview**
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+This model, `tahamajs/llama-3.2-3b-instruct-bitcoin-analyst_best`, is a specialized version of the **Llama-3.2-3B-Instruct** large language model. It has been fine-tuned for the domain of **Bitcoin and cryptocurrency analysis**. The fine-tuning process, which used **QLoRA** on the `tahamajs/bitcoin-llm-finetuning-dataset` dataset, was designed to train the model to act as a virtual Bitcoin analyst.
 
-## Quick start
+-----
+
+### **Usage**
+
+This model uses a PEFT (Parameter-Efficient Fine-Tuning) adapter. To use it, you must first load the base model and then attach the fine-tuned adapter. The adapter itself is very small, making the overall model efficient to load and use.
 
 ```python
-from transformers import pipeline
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+
+# Define the model IDs
+base_model_id = "meta-llama/Llama-3.2-3B-Instruct"
+peft_model_id = "tahamajs/llama-3.2-3b-instruct-bitcoin-analyst_best"
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="mikleeeeemmm/results", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained(base_model_id)
+
+# Load the base model with 4-bit quantization
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16,
+)
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_id,
+    quantization_config=bnb_config,
+    device_map="auto"
+)
+
+# Load the fine-tuned PEFT adapter on top of the base model
+model = PeftModel.from_pretrained(base_model, peft_model_id)
+
+# Example inference
+prompt = "What are the key technical differences between Bitcoin and Ethereum?"
+messages = [
+    {"role": "user", "content": prompt}
+]
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+outputs = model.generate(input_ids=input_ids, max_new_tokens=256)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
-## Training procedure
+-----
+
+### **Training Details** ⚙️
+
+This model was fine-tuned using Supervised Fine-Tuning (SFT) with the `trl.SFTTrainer`. A key aspect of the training was the use of a **custom data collator**, which ensures that the model's loss is calculated only on the assistant's response, not on the user's prompt or the special tokens used to format the conversation. This technique helps the model learn to generate better responses without overfitting to the input.
 
- 
+#### **Hyperparameters**
 
+The following hyperparameters were used for fine-tuning:
 
-This model was trained with SFT.
+| Hyperparameter               | Value           |
+| :--------------------------- | :-------------- |
+| `num_train_epochs`           | 1               |
+| `per_device_train_batch_size`| 1               |
+| `gradient_accumulation_steps`| 4               |
+| `learning_rate`              | 2e-4            |
+| `optim`                      | `paged_adamw_32bit` |
+| `r` (LoRA rank)              | 32              |
+| `lora_alpha`                 | 32              |
 
-### Framework versions
+-----
 
-- TRL: 0.21.0
-- Transformers: 4.55.0
-- Pytorch: 2.6.0+cu124
-- Datasets: 4.0.0
-- Tokenizers: 0.21.4
+### **Limitations and Biases** ⚠️
 
-## Citations
+  * **Domain Specificity:** The model's expertise is concentrated on Bitcoin and cryptocurrency. Its performance on general knowledge tasks may be limited.
+  * **Data Cutoff:** The model's knowledge is static and based on the training data. It will not be aware of recent events or market changes.
+  * **Potential Biases:** Responses may reflect biases present in the training data.
 
+-----
 
+### **License** 📜
 
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```
+This model is licensed under the **Apache 2.0 license**, inherited from its base model.