Mosleh Mahamud - VideoAndMovie

Subscribe for regular AI content

Calculating Memory Requirements Of LLMs

7:32

Calculating Memory Requirements Of LLMs

What is GRPO Fine Tuning and Why Is It Important?

12:40

What is GRPO Fine Tuning and Why Is It Important?

Fine tuning Qwen 3

8:46

Fine tuning Qwen 3

Get the most out of Fine Tuning

10:46

Get the most out of Fine Tuning

Run New Llama 4 For Less Than $1

3:28

Run New Llama 4 For Less Than $1

Quick Look Into Firebase studio

6:28

Quick Look Into Firebase studio

Quick Look: Llama 4

3:37

Quick Look: Llama 4

Function Calling With Gemma 3

5:19

Function Calling With Gemma 3

Fine Tuning Gemma 3

8:55

Fine Tuning Gemma 3

QwQ 32B is Beating Deepseek-R1

3:25

QwQ 32B is Beating Deepseek-R1

Training Deepseek R1 Distill With GRPO

8:59

Training Deepseek R1 Distill With GRPO

Multilingual Embeddings From Nomic Embed Text v2 MOE

2:57

Multilingual Embeddings From Nomic Embed Text v2 MOE

Getting Structured Output From Gemini 2.0 Flash With Pydantic

5:59

Getting Structured Output From Gemini 2.0 Flash With Pydantic

Is Gemini 2 0 Flash The Deepseek Killer?

3:45

Is Gemini 2 0 Flash The Deepseek Killer?

Get Embeddings From Deepseek R1 With vLLM

2:18

Get Embeddings From Deepseek R1 With vLLM

First Look At O3 mini

3:00

First Look At O3 mini

Fine Tuning Deepseek R1

7:28

Fine Tuning Deepseek R1

SmolVLM: Less Parameters Gives More

3:28

SmolVLM: Less Parameters Gives More

Deepseek R1: The Chinese Copied OPEN AI And It's Better

7:04

Deepseek R1: The Chinese Copied OPEN AI And It's Better

Nvidia Cosmos: Building LLMs With Synthetic Data

2:34

Nvidia Cosmos: Building LLMs With Synthetic Data

Fine Tune Phi 4 For Free!

8:56

Fine Tune Phi 4 For Free!

Use TangoFlux To Generate Music: Music Generation LLM

3:38

Use TangoFlux To Generate Music: Music Generation LLM

Deepseek V3: Open Source Model That Beats OPEN AI

3:19

Deepseek V3: Open Source Model That Beats OPEN AI

Phi 4 Beats Models 5 Times It's Size.

2:43

Phi 4 Beats Models 5 Times It's Size.

What is Distributed Inferencing For LLMs?

5:54

What is Distributed Inferencing For LLMs?

Quickly Inferencing with Llama 3.3 70B

3:14

Quickly Inferencing with Llama 3.3 70B

Llama Stack SDK: Streamlined Way to Develop With Llama Models

5:15

Llama Stack SDK: Streamlined Way to Develop With Llama Models

Observability: Using Feedback To Retrain LLMs

2:12

Observability: Using Feedback To Retrain LLMs

What is SGLang And How Can I Serve Llama 3.1 With It?

9:50

What is SGLang And How Can I Serve Llama 3.1 With It?

Removing Background with REMBG 2.0

5:02

Removing Background with REMBG 2.0