gauravvij137's submissions

1.		Show HN: Host any GGUF model in one command (github.com/dakshjain-1616)
		3 points by gauravvij137 22 days ago \| past
2.		Show HN: FC-Eval – CLI to Benchmark Local or Cloud LLMs on Function Calling (github.com/gauravvij)
		3 points by gauravvij137 35 days ago \| past
3.		Show HN: Auto LLM Ranker – Describe a task in English and get ranked models (github.com/gauravvij)
		3 points by gauravvij137 44 days ago \| past
4.		Show HN: GitHub Repo Agent – an agent that explores and reasons on GitHub repos (github.com/gauravvij)
		4 points by gauravvij137 50 days ago \| past
5.		Show HN: Kitten TTS Based Low-Latency Streaming Voice Assistant on CPU (github.com/abhishekgandhi-neo)
		3 points by gauravvij137 55 days ago \| past
6.		Show HN: LLM Council – Run multiple LLMs with critique and consensus eval (github.com/abhishekgandhi-neo)
		4 points by gauravvij137 56 days ago \| past
7.		Show HN: CLI tool to analyze your Vector Embeddings! (github.com/dakshjain-1616)
		2 points by gauravvij137 61 days ago \| past \| 1 comment
8.		AI Agent swarm for Stock trading simulation (github.com/dakshjain-1616)
		3 points by gauravvij137 63 days ago \| past \| 1 comment
9.		9x MobileNet V2 size reduction with Quantization aware training (github.com/dakshjain-1616)
		2 points by gauravvij137 64 days ago \| past \| 2 comments
10.		Machine learning agent in VS Code IDE (visualstudio.com)
		3 points by gauravvij137 87 days ago \| past \| 1 comment
11.		Show HN: First autonomous ML and AI engineering Agent (visualstudio.com)
		5 points by gauravvij137 89 days ago \| past
12.		Neo is leading the MLE Bench with 34.2% score (github.com/openai)
		1 point by gauravvij137 8 months ago \| past \| 1 comment
13.		Show HN: Heyneo.so – We built the first autonomous Machine Learning Engineer (heyneo.so)
		6 points by gauravvij137 on Feb 28, 2025 \| past \| 1 comment
14.		Finetune, Eval, Deploy 60 LLMs in a single Colab notebook (colab.research.google.com)
		38 points by gauravvij137 on Sept 16, 2024 \| past \| 6 comments
15.		Colab Notebook for finetuning Gemma 2 2B IT model (colab.research.google.com)
		4 points by gauravvij137 on Aug 3, 2024 \| past \| 2 comments
16.		Llama 405B vs. GPT 4O – Prompt by prompt comparison (monsterapi.ai)
		4 points by gauravvij137 on Aug 1, 2024 \| past \| 1 comment
17.		Synthesize instruction datasets from PDFs for LLM Fine-tuning (medium.com/raagulbharatwaj)
		1 point by gauravvij137 on July 31, 2024 \| past
18.		Is it 405B or 70B Llama on Meta chat? (meta.ai)
		2 points by gauravvij137 on July 27, 2024 \| past \| 1 comment
19.		Show HN: An API to fine-tune Whisper AI Model for high fidelity transcriptions (colab.research.google.com)
		3 points by gauravvij137 on July 1, 2024 \| past
20.		Show HN: Auto Blog Writer with title, description and images (Zephyr and SDXL) (colab.research.google.com)
		4 points by gauravvij137 on Dec 26, 2023 \| past \| 1 comment
21.		Finetuned Mistral 7B outperforms finetuned Zephyr 7B (monsterapi.ai)
		2 points by gauravvij137 on Dec 19, 2023 \| past \| 1 comment
22.		SDXL image generation using speech (colab.research.google.com)
		1 point by gauravvij137 on Nov 14, 2023 \| past \| 1 comment
23.		Llama Index and MonsterAPI for RAG Q&A on business docs with limited budget (monsterapi.ai)
		1 point by gauravvij137 on Sept 14, 2023 \| past \| 1 comment
24.		A comprehensive guide on finetuning Llama 2 LLM (monsterapi.ai)
		1 point by gauravvij137 on Aug 1, 2023 \| past \| 1 comment
25.		GATO – A general purpose AI agent that can perform 450 tasks (qblocks.cloud)
		2 points by gauravvij137 on June 27, 2022 \| past
26.		Cost of building the biggest supercomputer (Fugaku) in 2020 (qblocks.medium.com)
		2 points by gauravvij137 on May 19, 2022 \| past
27.		I generated 752 cold business email leads in 15 minutes (medium.com/gauravvij)
		4 points by gauravvij137 on Feb 27, 2019 \| past
28.		Movense – 360 product spins within minutes (movense.com)
		2 points by gauravvij137 on Feb 21, 2018 \| past

HN For You