Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -96,7 +96,6 @@ def display_work_experience():
|
|
96 |
- This new habit aims to educate and inspire, bridging the gap between technical expertise and practical application in the modern data landscape.
|
97 |
- Find my work on [Medium](https://medium.com/@nihar-palem) and [Substack](https://niharpalem.substack.com/publish/posts).
|
98 |
""")
|
99 |
-
|
100 |
def display_skills():
|
101 |
st.title('Skills')
|
102 |
|
@@ -107,7 +106,9 @@ def display_skills():
|
|
107 |
"Data Engineering",
|
108 |
"Data Architecture",
|
109 |
"Visualization",
|
110 |
-
"Specialized Systems"
|
|
|
|
|
111 |
]
|
112 |
|
113 |
# Create tabs
|
@@ -126,12 +127,20 @@ def display_skills():
|
|
126 |
- Relational: MySQL, PostgreSQL
|
127 |
- NoSQL: MongoDB
|
128 |
- Data Warehouses: Snowflake, Redshift
|
|
|
129 |
|
130 |
- **Development Tools**:
|
131 |
- Version Control: Git, GitHub
|
132 |
- Containerization: Docker
|
|
|
133 |
- IDE: VS Code, PyCharm
|
134 |
- Microsoft Office Suite
|
|
|
|
|
|
|
|
|
|
|
|
|
135 |
""")
|
136 |
|
137 |
# AI & Machine Learning
|
@@ -139,28 +148,36 @@ def display_skills():
|
|
139 |
st.subheader("AI & Machine Learning")
|
140 |
st.markdown("""
|
141 |
- **Machine Learning Frameworks**:
|
142 |
-
- PyTorch
|
143 |
- TensorFlow
|
144 |
- Scikit-Learn
|
145 |
- XGBoost, Random Forest, AdaBoost
|
146 |
|
147 |
- **Deep Learning**:
|
148 |
-
- Vision Transformers
|
149 |
- ResNet Architectures
|
150 |
- Neural Networks
|
151 |
- BiLSTM
|
152 |
|
153 |
-
- **
|
154 |
-
-
|
155 |
-
-
|
156 |
-
-
|
157 |
-
-
|
158 |
-
-
|
|
|
159 |
|
160 |
- **Computer Vision**:
|
161 |
- MediaPipe
|
162 |
- OpenCV
|
163 |
- Image Processing Pipelines
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
164 |
""")
|
165 |
|
166 |
# Data Engineering & Cloud
|
@@ -168,7 +185,7 @@ def display_skills():
|
|
168 |
st.subheader("Data Engineering & Cloud")
|
169 |
st.markdown("""
|
170 |
- **Cloud Platforms**:
|
171 |
-
- AWS (Certified)
|
172 |
- Google Cloud Platform (GCP)
|
173 |
- Cloud Architecture Design
|
174 |
|
@@ -183,11 +200,14 @@ def display_skills():
|
|
183 |
- Workflow Orchestration
|
184 |
- Concurrent Processing
|
185 |
- Real-time Data Streaming
|
|
|
186 |
|
187 |
- **Infrastructure**:
|
188 |
-
- CI/CD Pipelines
|
189 |
- Infrastructure as Code
|
190 |
-
-Kubernetes Basics
|
|
|
|
|
191 |
""")
|
192 |
|
193 |
# Data Architecture & Analytics
|
@@ -205,17 +225,21 @@ def display_skills():
|
|
205 |
- Batch Processing
|
206 |
- Time Series Analysis
|
207 |
- Statistical Analysis
|
|
|
|
|
208 |
|
209 |
- **Data Processing**:
|
210 |
- Pandas, NumPy
|
211 |
- Data Wrangling
|
212 |
- Feature Engineering
|
213 |
- Data Quality Assurance
|
|
|
214 |
|
215 |
- **Performance Optimization**:
|
216 |
- Query Optimization
|
217 |
- Indexing Strategies
|
218 |
- Caching Mechanisms
|
|
|
219 |
""")
|
220 |
|
221 |
# Visualization & Deployment
|
@@ -238,6 +262,7 @@ def display_skills():
|
|
238 |
- Streamlit
|
239 |
- Flask
|
240 |
- Web Development
|
|
|
241 |
|
242 |
- **Collaboration Tools**:
|
243 |
- JIRA
|
@@ -273,6 +298,80 @@ def display_skills():
|
|
273 |
- Computer Vision Systems
|
274 |
- Time Series Forecasting
|
275 |
- Anomaly Detection
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
276 |
""")
|
277 |
|
278 |
def display_articles():
|
|
|
96 |
- This new habit aims to educate and inspire, bridging the gap between technical expertise and practical application in the modern data landscape.
|
97 |
- Find my work on [Medium](https://medium.com/@nihar-palem) and [Substack](https://niharpalem.substack.com/publish/posts).
|
98 |
""")
|
|
|
99 |
def display_skills():
|
100 |
st.title('Skills')
|
101 |
|
|
|
106 |
"Data Engineering",
|
107 |
"Data Architecture",
|
108 |
"Visualization",
|
109 |
+
"Specialized Systems",
|
110 |
+
"Multimodal AI",
|
111 |
+
"LLM & Advanced AI"
|
112 |
]
|
113 |
|
114 |
# Create tabs
|
|
|
127 |
- Relational: MySQL, PostgreSQL
|
128 |
- NoSQL: MongoDB
|
129 |
- Data Warehouses: Snowflake, Redshift
|
130 |
+
- Vector Databases: FAISS, Pinecone
|
131 |
|
132 |
- **Development Tools**:
|
133 |
- Version Control: Git, GitHub
|
134 |
- Containerization: Docker
|
135 |
+
- Orchestration: Kubernetes (Basic)
|
136 |
- IDE: VS Code, PyCharm
|
137 |
- Microsoft Office Suite
|
138 |
+
|
139 |
+
- **Frameworks & Libraries**:
|
140 |
+
- LangChain
|
141 |
+
- Hugging Face (Transformers, Diffusers)
|
142 |
+
- Scikit-Learn, Pandas, NumPy
|
143 |
+
- Apache Spark
|
144 |
""")
|
145 |
|
146 |
# AI & Machine Learning
|
|
|
148 |
st.subheader("AI & Machine Learning")
|
149 |
st.markdown("""
|
150 |
- **Machine Learning Frameworks**:
|
151 |
+
- PyTorch (Advanced, PyTorch Distributed, DDP)
|
152 |
- TensorFlow
|
153 |
- Scikit-Learn
|
154 |
- XGBoost, Random Forest, AdaBoost
|
155 |
|
156 |
- **Deep Learning**:
|
157 |
+
- Vision Transformers (ViT)
|
158 |
- ResNet Architectures
|
159 |
- Neural Networks
|
160 |
- BiLSTM
|
161 |
|
162 |
+
- **Distributed Training**:
|
163 |
+
- Multi-GPU Clusters (16+ GPUs)
|
164 |
+
- PyTorch DDP (Distributed Data Parallel)
|
165 |
+
- DeepSpeed
|
166 |
+
- Megatron
|
167 |
+
- CUDA Acceleration
|
168 |
+
- FlashAttention
|
169 |
|
170 |
- **Computer Vision**:
|
171 |
- MediaPipe
|
172 |
- OpenCV
|
173 |
- Image Processing Pipelines
|
174 |
+
- Satellite Imagery Analysis
|
175 |
+
|
176 |
+
- **Model Optimization**:
|
177 |
+
- Model Compression (Quantization, Distillation)
|
178 |
+
- Performance Optimization
|
179 |
+
- CUDA Programming
|
180 |
+
- Parallel Processing
|
181 |
""")
|
182 |
|
183 |
# Data Engineering & Cloud
|
|
|
185 |
st.subheader("Data Engineering & Cloud")
|
186 |
st.markdown("""
|
187 |
- **Cloud Platforms**:
|
188 |
+
- AWS (Certified - Lambda, S3, Glue, EC2, Redshift)
|
189 |
- Google Cloud Platform (GCP)
|
190 |
- Cloud Architecture Design
|
191 |
|
|
|
200 |
- Workflow Orchestration
|
201 |
- Concurrent Processing
|
202 |
- Real-time Data Streaming
|
203 |
+
- ThreadPoolExecutor Optimization
|
204 |
|
205 |
- **Infrastructure**:
|
206 |
+
- CI/CD Pipelines (GitHub Actions)
|
207 |
- Infrastructure as Code
|
208 |
+
- Kubernetes Basics
|
209 |
+
- Production Monitoring
|
210 |
+
- Distributed Training Clusters
|
211 |
""")
|
212 |
|
213 |
# Data Architecture & Analytics
|
|
|
225 |
- Batch Processing
|
226 |
- Time Series Analysis
|
227 |
- Statistical Analysis
|
228 |
+
- A/B Testing
|
229 |
+
- Hypothesis Testing
|
230 |
|
231 |
- **Data Processing**:
|
232 |
- Pandas, NumPy
|
233 |
- Data Wrangling
|
234 |
- Feature Engineering
|
235 |
- Data Quality Assurance
|
236 |
+
- Data Quality Management
|
237 |
|
238 |
- **Performance Optimization**:
|
239 |
- Query Optimization
|
240 |
- Indexing Strategies
|
241 |
- Caching Mechanisms
|
242 |
+
- SQL Performance Tuning
|
243 |
""")
|
244 |
|
245 |
# Visualization & Deployment
|
|
|
262 |
- Streamlit
|
263 |
- Flask
|
264 |
- Web Development
|
265 |
+
- Hugging Face Spaces
|
266 |
|
267 |
- **Collaboration Tools**:
|
268 |
- JIRA
|
|
|
298 |
- Computer Vision Systems
|
299 |
- Time Series Forecasting
|
300 |
- Anomaly Detection
|
301 |
+
- Real-time Web Scraping
|
302 |
+
- Automated Data Quality Checks
|
303 |
+
""")
|
304 |
+
|
305 |
+
# Multimodal AI
|
306 |
+
with tabs[6]:
|
307 |
+
st.subheader("Multimodal AI")
|
308 |
+
st.markdown("""
|
309 |
+
- **Vision-Language Models**:
|
310 |
+
- Qwen-VL
|
311 |
+
- Gemini Multimodal
|
312 |
+
- Vision-Language Understanding
|
313 |
+
- Cross-modal Fine-tuning
|
314 |
+
- Multimodal Evaluation
|
315 |
+
|
316 |
+
- **Visual AI**:
|
317 |
+
- Visual Question Answering (VQA)
|
318 |
+
- Vision Transformers (ViT)
|
319 |
+
- Stable Diffusion XL
|
320 |
+
- Generative AI (Vision)
|
321 |
+
- Image-Text Alignment
|
322 |
+
|
323 |
+
- **Multi-Agent Systems**:
|
324 |
+
- Multi-Agent Multimodal Workflows
|
325 |
+
- Strategic Agent Architecture
|
326 |
+
- Visual Agent Integration
|
327 |
+
- QA Agent Implementation
|
328 |
+
|
329 |
+
- **Evaluation & Testing**:
|
330 |
+
- Multimodal Benchmarking
|
331 |
+
- Cross-modal Bias Detection
|
332 |
+
- Performance Optimization
|
333 |
+
- Adversarial Testing
|
334 |
+
- Statistical Validation Methods
|
335 |
+
""")
|
336 |
+
|
337 |
+
# LLM & Advanced AI
|
338 |
+
with tabs[7]:
|
339 |
+
st.subheader("LLM & Advanced AI")
|
340 |
+
st.markdown("""
|
341 |
+
- **Large Language Models**:
|
342 |
+
- Fine-tuning (PEFT, LoRA, QLoRA)
|
343 |
+
- 2-Stage Training
|
344 |
+
- VLLM/LMMs
|
345 |
+
- Qwen, LLaMA (Llama-3.1-8B), GPT Integration
|
346 |
+
|
347 |
+
- **Advanced Techniques**:
|
348 |
+
- Prompt Engineering (Advanced, Context Injection)
|
349 |
+
- RAG (Retrieval-Augmented Generation)
|
350 |
+
- LLM Evaluation Benchmarking
|
351 |
+
- LLM-as-judge
|
352 |
+
- Auto Hinter Systems
|
353 |
+
|
354 |
+
- **Production AI Systems**:
|
355 |
+
- Multi-Agent Systems
|
356 |
+
- API Integration
|
357 |
+
- Performance Optimization
|
358 |
+
- Tenstorrent Hardware Utilization
|
359 |
+
- MLOps
|
360 |
+
|
361 |
+
- **Specialized Applications**:
|
362 |
+
- Semantic Job Matching
|
363 |
+
- Resume Generation
|
364 |
+
- Marketing Campaign Automation
|
365 |
+
- Infrastructure Change Detection
|
366 |
+
- Exercise Pose Correction
|
367 |
+
|
368 |
+
- **AI Testing & Validation**:
|
369 |
+
- Unit/Integration Testing for AI
|
370 |
+
- Offline Evaluation Frameworks
|
371 |
+
- Model Validation
|
372 |
+
- ROC Curve Analysis
|
373 |
+
- RMSE Validation
|
374 |
+
- Bias Mitigation
|
375 |
""")
|
376 |
|
377 |
def display_articles():
|