first commit

dataset2.csv

@@ -0,0 +1,31 @@
+problem,solution
+"🍎 + 🍎 + 🍎 = 12 → 🍎 =","4"
+"🍌 + 🍌 = 10 → 🍌 =","5"
+"🍒 + 🍒 + 🍒 + 🍒 = 20 → 🍒 =","5"
+"🍊 + 🍊 + 🍇 = 15, 🍊 = 6, 🍇 = ? → 🍇 =",3"
+"🍉 + 🍉 = 18 → 🍉 =","9"
+"🍍 + 🍍 + 🍍 = 24 → 🍍 =","8"
+"🥑 + 🥑 + 🥑 + 🥑 = 16 → 🥑 =","4"
+"🍓 + 🍓 = 14 → 🍓 =","7"
+"🍋 + 🍋 + 🍋 = 21 → 🍋 =","7"
+"🥕 + 🥕 = 8 → 🥕 =","4"
+"🌽 + 🌽 + 🌽 = 30 → 🌽 =","10"
+"🍪 + 🍪 + 🍪 = 15 → 🍪 =","5"
+"🥜 + 🥜 + 🥜 + 🥜 = 40 → 🥜 =","10"
+"🍔 + 🍔 = 20 → 🍔 =","10"
+"🍕 + 🍕 + 🍕 = 27 → 🍕 =","9"
+"🍇 + 🍇 = 8 → 🍇 =","4"
+"🌰 + 🌰 + 🌰 = 18 → 🌰 =","6"
+"🍞 + 🍞 + 🍞 + 🍞 = 40 → 🍞 =","10"
+"🥒 + 🥒 + 🥒 = 21 → 🥒 =","7"
+"🥦 + 🥦 + 🥦 + 🥦 = 28 → 🥦 =","7"
+"🍎 + 🍏 = 12, 🍏 = 5 → 🍎 =","7"
+"🍍 + 🍉 = 20, 🍉 = 8 → 🍍 =","12"
+"🥥 + 🥥 = 30 → 🥥 =","15"
+"🍉 + 🍓 = 16, 🍉 = 10 → 🍓 =","6"
+"🍩 + 🍩 + 🍩 + 🍩 = 32 → 🍩 =","8"
+"🍜 + 🍜 + 🍜 = 18 → 🍜 =","6"
+"🍫 + 🍫 = 14 → 🍫 =","7"
+"🍰 + 🍰 + 🍰 = 24 → 🍰 =","8"
+"🍿 + 🍿 + 🍿 + 🍿 = 20 → 🍿 =","5"
+"🍔 + 🌭 = 18, 🌭 = 8 → 🍔 =","10"

finetuned_deepseek_math/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-math-7b-base
+library_name: peft
+---
+
+# 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. -->
+
+
+
+- **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]
+### Framework versions
+
+- PEFT 0.14.0

finetuned_deepseek_math/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-math-7b-base",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 40,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 20,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

finetuned_deepseek_math/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44055acddcc26f3f79252f1bd6e7d672e61a003276eaef75b381f22e0af48bda
+size 39337728

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+torch
+transformers>=4.45.1
+accelerate
+peft
+datasets

streamlit_app.py

@@ -0,0 +1,73 @@
+import streamlit as st
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig, BitsAndBytesConfig
+from peft import LoraConfig, get_peft_model, prepare_model_for_kbit_training
+
+# Constants
+MODEL_NAME = "deepseek-math"
+SAVE_PATH = "finetuned_deepseek_math"
+
+@st.cache_resource(show_spinner=False)
+def load_model():
+    # # 4-bit quantization configurationi
+    # bnb_config = BitsAndBytesConfig(
+    #     load_in_4bit=True,
+    #     bnb_4bit_quant_type="nf4",
+    #     bnb_4bit_use_double_quant=True,
+    #     bnb_4bit_compute_dtype=torch.bfloat16
+    # )
+
+    # Load tokenizer and model in 4-bit mode
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+    tokenizer.pad_token = tokenizer.eos_token
+
+    model = AutoModelForCausalLM.from_pretrained(
+        MODEL_NAME,
+        torch_dtype=torch.bfloat16,
+        device_map="auto"
+        # quantization_config=bnb_config
+    )
+    model.generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
+    model.generation_config.pad_token_id = model.generation_config.eos_token_id
+
+    # Prepare model for k-bit training and wrap with LoRA via PEFT
+    model = prepare_model_for_kbit_training(model)
+    lora_config = LoraConfig(
+        r=20,
+        lora_alpha=40,
+        target_modules=["q_proj", "v_proj"],
+        lora_dropout=0.05,
+        bias="none",
+        task_type="CAUSAL_LM"
+    )
+    model = get_peft_model(model, lora_config)
+
+    # Load the fine-tuned adapter weights
+    model.load_pretrained(SAVE_PATH)
+    model.eval()
+    return tokenizer, model
+
+def generate_output(prompt, tokenizer, model):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    with torch.inference_mode():
+        outputs = model.generate(
+            input_ids=inputs.input_ids,
+            attention_mask=inputs.attention_mask,
+            max_new_tokens=20,
+            generation_config=model.generation_config
+        )
+    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return result
+
+st.title("Deepseek Math Fine-Tuned Model Inference")
+st.write("Enter your prompt below:")
+
+user_input = st.text_input("Prompt", "🚗 + 🚗 + 🚗 + 🚗 = 20 → 🚗 =")
+
+if st.button("Generate Output"):
+    with st.spinner("Generating answer..."):
+        tokenizer, model = load_model()
+        output = generate_output(user_input, tokenizer, model)
+    st.success("Output generated!")
+    st.write("**Input:**", user_input)
+    st.write("**Output:**", output)