Search: github.com/mistralai | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

61.

SelfExtend Attention for Mistral

github.com/sdan

2 years ago

3 points

62.

Show HN: Made a batching LLM API for a project. Mistral 200 tk/s on RTX 3090

github.com/epolewski

2 years ago

3 points

63.

MLX: Fine-tune Llama 7B or Mistral 7B with 32GB

github.com/ml-explore

3 years ago

3 points

64.

Show HN: Mistral NeMO Agent to get the best builds in League of Legends

github.com/uscneps

a year ago

2 points

65.

Show HN: MistralOCR with Web Search ADK Agent App

github.com/Astrodevil

a year ago

2 points

66.

Fine-tune large models like Mistral-7B, Llama-2-13B, Phi-2, or Qwen-14B for free

github.com/Locutusque

2 years ago

2 points

67.

Ollama Pre-release v0.3.0. Support Llama 3.1 and Mistral Large 2

github.com/ollama

2 years ago

2 points

68.

Show HN: Just Open Sourced my Medical Q&A built on Mistral7B

github.com/manooshree

2 years ago

2 points

69.

Show HN: OnnxStream running TinyLlama and Mistral 7B, with CUDA support

github.com/vitoplantamura

2 years ago

2 points

70.

Mistral 7B OpenOrca outclasses Llama 2 13B variants

github.com/Troyanovsky

3 years ago

2 points

71.

Dialoqbase v0.0.32 Now Supports Mistral Model

github.com/n4ze3m

3 years ago

1 points

72.

Benchmarked Llama2 and mistral across popular inference engines and precisions

github.com/premAI-io

2 years ago

1 points

73.

Local PDF Chat Application with Mistral 7B LLM

github.com/SonicWarrior1

2 years ago

1 points

74.

Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks

github.com/antoinezambelli

a month ago

687 points

75.

Show HN: I built a free in-browser Llama 3 chatbot powered by WebGPU

2 years ago

547 points

76.

Show HN: TokenDagger – A tokenizer faster than OpenAI's Tiktoken

github.com/M4THYOU

a year ago

281 points

77.

Show HN: Open source alternative to ChatGPT and ChatPDF-like AI tools

github.com/SecureAI-Tools

3 years ago

234 points

78.

Show HN: Cactus – Ollama for Smartphones

github.com/cactus-compute

a year ago

231 points

79.

Show HN: Qwen-2.5-32B is now the best open source OCR model

github.com/getomni-ai

a year ago

211 points

80.

Show HN: Knowledge graph of restaurants and chefs, built using LLMs

theophilecantelob.re

a year ago

201 points

81.

Launch HN: Continue (YC S23) – Create custom AI code assistants

hub.continue.dev

a year ago

178 points

82.

Show HN: Onit – Source-available ChatGPT Desktop with local mode, Claude, Gemini

github.com/synth-inc

a year ago

174 points

83.

Show HN: Any-LLM – Lightweight router to access any LLM Provider

github.com/mozilla-ai

a year ago

125 points

84.

Show HN: I open-sourced my Go and Next B2B SaaS Starter (deploy anywhere, MIT)

github.com/moasq

6 months ago

83 points

85.

Show HN: Torrix, self hosted, LLM Observability,(no Postgres, no Redis)

github.com/torrix-ai

a month ago

74 points

86.

Show HN: Phospho – Text Analytics for LLM Apps (Posthog for Prompts)

github.com/phospho-app

2 years ago

59 points

87.

Show HN: Panza: A personal email assistant, trained and running on-device

github.com/IST-DASLab

2 years ago

49 points

88.

Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts

10 months ago

31 points

89.

Show HN: GEITje-7B – A New Large Open Dutch Language Model

github.com/Rijgersberg

3 years ago

20 points

90.

Show HN: A web-app to explore topics using LLM

github.com/charstorm

2 years ago

20 points