added sai model

src/trian/train_sai.py

@@ -0,0 +1,147 @@
+import os
+from dotenv import load_dotenv
+from datasets import load_dataset
+from unsloth import FastMistralModel
+from trl import SFTTrainer
+from transformers import TrainingArguments
+from huggingface_hub import login
+import json
+import random
+from datasets import Dataset
+from datasets import concatenate_datasets
+import torch
+
+load_dotenv()
+
+HUGGING_FACE_ACCESS_TOKEN = os.getenv('HUGGING_FACE_ACCESS_TOKEN')
+login()
+
+max_seq_length = 4096  # Can change to whatever number <= 4096
+dtype = None  # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = True  # Use 4bit quantization to reduce memory usage. Can be False.
+
+model, tokenizer = FastMistralModel.from_pretrained(
+    model_name="mistralai/Mistral-7B-Instruct-v0.1",  # You can change this to any Llama model!
+    max_seq_length=max_seq_length,
+    dtype=dtype,
+    load_in_4bit=load_in_4bit,
+    # trust_remote_code=True,
+    token=HUGGING_FACE_ACCESS_TOKEN,
+)
+model = FastMistralModel.get_peft_model(
+    model,
+    r=16,
+    target_modules=["q_proj", "k_proj", "v_proj", "o_proj",
+                    "gate_proj", "up_proj", "down_proj", ],
+    lora_alpha=16,
+    lora_dropout=0,  # Currently only supports dropout = 0
+    bias="none",  # Currently only supports bias = "none"
+    use_gradient_checkpointing=True,
+    random_state=3407,
+    max_seq_length=max_seq_length,
+)
+
+dataset = load_dataset("HuggingFaceH4/ultrachat_200k", token=HUGGING_FACE_ACCESS_TOKEN)
+
+ultrachat_total_rows = len(dataset["train_sft"])
+
+sai_data = []
+with open('data/sai-processed.jsonl') as f:
+    for line in f:
+        sai_obj = json.loads(line)
+        sai_data.append({
+            "prompt": sai_obj["initialPrompt"],
+            "messages": [
+                {"content": sai_obj["initialPrompt"], "role": "user"},
+                {"content": sai_obj["revisionResponse"], "role": "assistant"}
+            ]
+        })
+
+sai_data = Dataset.from_list(sai_data)
+
+sai_data = sai_data.shuffle(seed=42)
+
+train_sft = dataset["train_sft"]
+train_sft = train_sft.shuffle(seed=42)
+test_sft = dataset["test_sft"]
+test_sft = test_sft.shuffle(seed=42)
+
+# i choose 50k sample for training and 2k for test
+train_sft_subset = train_sft.select(range(150000))
+test_sft_subset = test_sft.select(range(3000))
+
+# Get the same proportion of the SAI data as the Ultrachat data
+sai_train_sft = sai_data.select(range(int(len(train_sft_subset)/ultrachat_total_rows * len(sai_data))))
+sai_test_sft = sai_data.select(range(int(len(test_sft_subset)/ultrachat_total_rows * len(sai_data))))
+
+print("Ultrachat Total Rows: ", ultrachat_total_rows)
+print("Ultrachat Train Length: ", len(train_sft_subset))
+print("Ultrachat Test Length: ", len(test_sft_subset))
+print("SAI Data Length: ", len(sai_data))
+print("SAI Train Length: ", len(sai_train_sft))
+print("SAI Test Length: ", len(sai_test_sft))
+
+train_sft_subset_len = len(train_sft_subset) - len(sai_train_sft)
+train_sft_subset = concatenate_datasets([train_sft_subset.select(range(train_sft_subset_len)), sai_train_sft])
+
+test_sft_subset_len = len(test_sft_subset) - len(sai_test_sft)
+test_sft_subset = concatenate_datasets([test_sft_subset.select(range(test_sft_subset_len)), sai_test_sft])
+
+print("Combined Train Length: ", len(train_sft_subset))
+print("Combined Test Length: ", len(test_sft_subset))
+
+def formatting_func(example):
+    formatted_messages = []
+
+    for message in example['messages']:
+        content = message['content']
+        role = message['role']
+        formatted_message = {"role": role, "content": content}
+        formatted_messages.append(formatted_message)
+
+    return {"text": "\n".join([str(msg) for msg in formatted_messages])}
+
+train_sft = train_sft_subset.map(formatting_func)
+test_sft = test_sft_subset.map(formatting_func)
+
+
+HAS_BFLOAT16 = torch.cuda.is_bf16_supported()
+learning_rate = 1e-4
+weight_decay = 0.01
+warmup_steps = 10
+lr_scheduler_type = "linear"
+optimizer = "adamw_8bit"
+random_state = 3407
+
+argument = TrainingArguments(
+    per_device_train_batch_size = 1,
+    gradient_accumulation_steps = 4,
+    warmup_steps = warmup_steps,
+    max_steps = 240,
+    learning_rate = learning_rate,
+    fp16 = not HAS_BFLOAT16,
+    bf16 = HAS_BFLOAT16,
+    logging_steps = 1,
+    output_dir = "outputs",
+    optim = optimizer,
+    weight_decay = weight_decay,
+    lr_scheduler_type = lr_scheduler_type,
+    seed = random_state,
+    report_to = "none",
+)
+
+trainer = SFTTrainer(
+    model = model,
+    train_dataset=train_sft,
+    eval_dataset=test_sft,
+    dataset_text_field = "text",
+    max_seq_length = max_seq_length,
+    args = argument,
+)
+
+trainer.train()
+
+trainer.save_model("./ultrachat_sai")
+
+trainer.push_to_hub("vanbujm/ultrachat_sai")
+tokenizer.push_to_hub("vanbujm/ultrachat_sai")

ultrachat_sai/README.md

@@ -0,0 +1,200 @@
+---
+library_name: transformers
+tags:
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

ultrachat_sai/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}