PUMA Vault

Etiqueta: open-weights

12 artículos con esta etiqueta.

  • 15 jun 2026

    Natural Language Processing with Transformers: Building Language Applications with Hugging Face

    • literature
    • transformers
    • hugging-face
    • nlp
    • fine-tuning
    • quantization
    • ollama
    • open-weights
    • mistral
    • gemma
    • bert
    • puma-core
    • book
    • implementation
    • python
    • literature-note
    • moc
  • 15 jun 2026

    LN-Tools — Evaluated open-weights families run in GGUF Q4_K_M: Qwen 2.5 (1.5b/3b/7b

    • literature-tools
    • puma
    • reference
    • baseline
    • open-weights
  • 15 jun 2026

    PN — Evaluated model: gemma3:12b

    • permanent-note
    • puma
    • local-llm
    • open-weights
    • benchmark
  • 15 jun 2026

    PN — Evaluated model: gemma3:1b

    • permanent-note
    • puma
    • local-llm
    • open-weights
    • benchmark
  • 15 jun 2026

    PN — Evaluated model: gemma3:4b

    • permanent-note
    • puma
    • local-llm
    • open-weights
    • benchmark
  • 15 jun 2026

    PN — Evaluated model: gemma4:e2b

    • permanent-note
    • puma
    • local-llm
    • open-weights
    • benchmark
  • 15 jun 2026

    PN — Evaluated model: llama3.1:8b

    • permanent-note
    • puma
    • local-llm
    • open-weights
    • benchmark
  • 15 jun 2026

    PN — Evaluated model: mistral:7b

    • permanent-note
    • puma
    • local-llm
    • open-weights
    • benchmark
  • 15 jun 2026

    PN — Evaluated model: qwen2.5:1.5b

    • permanent-note
    • puma
    • local-llm
    • open-weights
    • benchmark
  • 15 jun 2026

    PN — Evaluated model: qwen2.5:3b

    • permanent-note
    • puma
    • local-llm
    • open-weights
    • benchmark
  • 15 jun 2026

    PN — Evaluated model: qwen2.5:7b

    • permanent-note
    • puma
    • local-llm
    • open-weights
    • benchmark
  • 15 jun 2026

    RES — Nine candidate open-weights models were selected (1B-12B across four families)

    • result-note
    • puma
    • methodology
    • open-weights

Creado con Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community