Update README.md

README.md

@@ -1,67 +1,72 @@
 ---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- mlabonne/OmniBeagle-7B
+- flemmingmiguel/MBX-7B-v3
+- AiMavenAi/AiMaven-Prometheus
+base_model:
+- mlabonne/OmniBeagle-7B
+- flemmingmiguel/MBX-7B-v3
+- AiMavenAi/AiMaven-Prometheus
 license: apache-2.0
 ---
 
-Modelo entrenado con DPO
 
-Merge de dos modelos
 
-codigo de train:
+# NeuTrixOmniBe-DPO
 
-# LoRA configuration
-peft_config = LoraConfig(
-    r=16,
-    lora_alpha=16,
-    lora_dropout=0.05,
-    bias="none",
-    task_type="CAUSAL_LM",
-    target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
-)
+NeuTrixOmniBe-DPO is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+```yaml
+MODEL_NAME = "NeuTrixOmniBe-DPO"
+yaml_config = """
+slices:
+  - sources:
+      - model: CultriX/NeuralTrix-7B-dpo
+        layer_range: [0, 32]
+      - model: paulml/OmniBeagleSquaredMBX-v3-7B-v2
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: CultriX/NeuralTrix-7B-dpo
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+"""```
 
-# Model to fine-tune
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    torch_dtype=torch.float16,
-    load_in_4bit=True
-)
-model.config.use_cache = False
+It was then trained with DPO using: 
+* Intel/orca_dpo_pairs
 
-# Reference model
-ref_model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    torch_dtype=torch.float16,
-    load_in_4bit=True
-)
+## 🧩 Configuration
 
-# Training arguments
-training_args = TrainingArguments(
-    per_device_train_batch_size=4,
-    gradient_accumulation_steps=4,
-    gradient_checkpointing=True,
-    learning_rate=5e-5,
-    lr_scheduler_type="cosine",
-    max_steps=200,
-    save_strategy="no",
-    logging_steps=1,
-    output_dir=new_model,
-    optim="paged_adamw_32bit",
-    warmup_steps=100,
-    bf16=True,
-    report_to="wandb",
-)
 
-# Create DPO trainer
-dpo_trainer = DPOTrainer(
-    model,
-    ref_model,
-    args=training_args,
-    train_dataset=dataset,
-    tokenizer=tokenizer,
-    peft_config=peft_config,
-    beta=0.1,
-    max_prompt_length=1024,
-    max_length=1536,
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Kukedlc/NeuTrixOmniBe-DPO"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
 )
 
-# Fine-tune model with DPO
-dpo_trainer.train()
+outputs = pipeline(prompt, max_new_tokens=128, do_sample=True, temperature=0.5, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```