Update README.md

README.md

@@ -16,30 +16,127 @@ license: other
 
 This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
 
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
 # Usage
 
 ```python
 
-from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-model_path = "PATH_TO_THIS_REPO"
+torch.random.manual_seed(0)
 
-tokenizer = AutoTokenizer.from_pretrained(model_path)
 model = AutoModelForCausalLM.from_pretrained(
-    model_path,
-    device_map="auto",
-    torch_dtype='auto'
-).eval()
+    "styalai/competition-math-phinetune-v1", q
+    device_map="cuda", 
+    torch_dtype="auto", 
+    trust_remote_code=True, 
+)
+tokenizer = AutoTokenizer.from_pretrained("styalai/competition-math-phinetune-v1")
 
-# Prompt content: "hi"
 messages = [
-    {"role": "user", "content": "hi"}
+    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
 ]
 
-input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
-output_ids = model.generate(input_ids.to('cuda'))
-response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+)
+
+generation_args = {
+    "max_new_tokens": 500,
+    "return_full_text": False,
+    "temperature": 0.0,
+    "do_sample": False,
+}
+
+output = pipe(messages, **generation_args)
+print(output[0]['generated_text'])
+```
+
+# Info
+
+Fine-tune from styalai/phi-ne-tuning-1-4 who it fine tune from phi-3
+
+parameters of autotrain :
+```python
+project_name = 'competition-math-phinetune-v1-1' # @param {type:"string"}
+model_name = "styalai/competition-math-phinetune-v1" #'microsoft/Phi-3-mini-4k-instruct' # @param {type:"string"}
+
+#@markdown ---
+#@markdown #### Push to Hub?
+#@markdown Use these only if you want to push your trained model to a private repo in your Hugging Face Account
+#@markdown If you dont use these, the model will be saved in Google Colab and you are required to download it manually.
+#@markdown Please enter your Hugging Face write token. The trained model will be saved to your Hugging Face account.
+#@markdown You can find your token here: https://huggingface.co/settings/tokens
+push_to_hub = True # @param ["False", "True"] {type:"raw"}
+hf_token = "hf_****" #@param {type:"string"}
+
+
+#@markdown ---
+#@markdown #### Hyperparameters
+learning_rate = 3e-4 # @param {type:"number"}
+num_epochs = 1 #@param {type:"number"}
+batch_size = 1 # @param {type:"slider", min:1, max:32, step:1}
+block_size = 1024 # @param {type:"number"}
+trainer = "sft" # @param ["default", "sft"] {type:"raw"}
+warmup_ratio = 0.1 # @param {type:"number"}
+weight_decay = 0.01 # @param {type:"number"}
+gradient_accumulation = 4 # @param {type:"number"}
+mixed_precision = "fp16" # @param ["fp16", "bf16", "none"] {type:"raw"}
+peft = True # @param ["False", "True"] {type:"raw"}
+quantization = "int4" # @param ["int4", "int8", "none"] {type:"raw"}
+lora_r = 16 #@param {type:"number"}
+lora_alpha = 32 #@param {type:"number"}
+lora_dropout = 0.05 #@param {type:"number"}
+
+code for the creation of the dataset :
+from datasets import load_dataset
+dataset = load_dataset("camel-ai/math")#, streaming=True)
+
+import pandas as pd
+data = {"text":[]}
+
+msg1 = dataset["train"]["message_1"]
+msg2 = dataset["train"]["message_2"]
+
+for i in range(3500, 7000):
+    user = "<|user|>"+ msg1[i] +"<|end|>\n"
+    phi = "<|assistant|>"+ msg2[i] +"<|end|>"
+    prompt = user+phi
+    data["text"].append(prompt)
+    
+data = pd.DataFrame.from_dict(data)
+print(data)
+#os.mkdir("/kaggle/working/data")
+data.to_csv('data/dataset.csv', index=False, escapechar='\\')
+
+!autotrain llm \
+--train \
+--username "styalai" \
+--merge-adapter \
+--model ${MODEL_NAME} \
+--project-name ${PROJECT_NAME} \
+--data-path data/ \
+--text-column text \
+--lr ${LEARNING_RATE} \
+--batch-size ${BATCH_SIZE} \
+--epochs ${NUM_EPOCHS} \
+--block-size ${BLOCK_SIZE} \
+--warmup-ratio ${WARMUP_RATIO} \
+--lora-r ${LORA_R} \
+--lora-alpha ${LORA_ALPHA} \
+--lora-dropout ${LORA_DROPOUT} \
+--weight-decay ${WEIGHT_DECAY} \
+--gradient-accumulation ${GRADIENT_ACCUMULATION} \
+--quantization ${QUANTIZATION} \
+--mixed-precision ${MIXED_PRECISION} \
+$( [[ "$PEFT" == "True" ]] && echo "--peft" ) \
+$( [[ "$PUSH_TO_HUB" == "True" ]] && echo "--push-to-hub --token ${HF_TOKEN}" )q
+```
 
-# Model response: "Hello! How can I assist you today?"
-print(response)
-```
+durée de l’entrainement : 1:07:41