Skip to content

NeamCode v0.3.5.4 — HuggingFace Provider

Choose a tag to compare

View all tags
@Praveengovianalytics Praveengovianalytics released this 11 Mar 03:33
v0.3.5.4
d964815

What's New

HuggingFace Inference API is now NeamCode's 12th LLM provider.

HuggingFace Provider

  • Full chat and streaming support via HuggingFace's OpenAI-compatible Messages API
  • Tool calling support for compatible models
  • Default endpoint: https://router.huggingface.co/v1
  • Environment variable: HF_API_KEY or HUGGINGFACE_API_KEY
  • Default model: meta-llama/Llama-3.1-8B-Instruct
  • Routing tier: fast — ideal for quick tasks at zero cost

Configuration

providers:
  - name: huggingface-default
    type: huggingface
    model: meta-llama/Llama-3.1-8B-Instruct
    apiKeyEnv: HF_API_KEY
    routing:
      tier: fast

Supported Models (via HuggingFace Inference API)

  • meta-llama/Llama-3.1-8B-Instruct
  • meta-llama/Llama-3.1-70B-Instruct
  • mistralai/Mistral-7B-Instruct-v0.3
  • Qwen/Qwen2.5-72B-Instruct
  • HuggingFaceH4/zephyr-7b-beta
  • Any model hosted on HuggingFace Inference API

Provider Count: 12

Ollama, OpenAI, Anthropic, Gemini, DeepSeek, Mistral, HuggingFace, MiniMax, Kimi, Qwen, OpenAI-Compatible, Mock

Tests

  • 7 new unit tests for HuggingFace provider
  • Lazy-loader test updated
  • Integration health check + provider pool tests updated
  • Live verified: chat (1480ms) and streaming (1869ms) with Llama-3.1-8B

Install

macOS / Linux:

curl -fsSL https://github.com/neam-lang/NeamCode/releases/download/v0.3.5.4/install.sh | sh

Windows (PowerShell):

irm https://github.com/neam-lang/NeamCode/releases/download/v0.3.5.4/install.ps1 | iex

Release Packages

Platform Package
macOS arm64 neamcode-v0.3.5.4-macos-arm64.tar.gz
macOS/Linux installer install.sh
Windows installer install.ps1

Full Changelog: v0.3.5.3...v0.3.5.4

Assets 7
Loading