Experimental Features

This section contains features that extend halo-forge beyond code generation training into new domains.

Status: These modalities support real training runs, but readiness is tracked by internal qualification tiers rather than broad “stable” claims.

Modality Training Capability Matrix

All modality train commands also support --resume-from-cycle and persist canonical artifacts: cycle_<n>/model, cycle_<n>/checkpoint_state.json, latest_checkpoint.json, final_model, and training_summary.json. If a modality is temporarily re-gated to prototype, add --allow-prototype-train as a compatibility override.

Readiness tiers used internally and surfaced in the UI:

• experimental: launch path exists, but qualification evidence is incomplete
• qualified: contract and artifact checks pass, but the full train+eval gate is still pending
• production_ready: deterministic train+eval qualification passed, including resume/relaunch and baseline checks

Vision-Language (VLM)

Train vision-language models using RLVR with perception-aware verification.

Quick Start

# Full pipeline
halo-forge vlm sft --dataset llava --model Qwen/Qwen2-VL-2B-Instruct --output models/vlm_sft
halo-forge vlm train --model models/vlm_sft --dataset textvqa --cycles 6 --output models/vlm_raft --seed 42
halo-forge vlm benchmark --model models/vlm_raft --dataset docvqa --limit 100

# Quick RAFT (skip SFT)
halo-forge vlm train --model Qwen/Qwen2-VL-7B-Instruct --dataset textvqa --cycles 6 --seed 42

Supported Models

Datasets

Verification Architecture

The VisionVerifier uses multi-stage verification:

• Perception (0.3): Object detection, OCR, spatial reasoning
• Reasoning (0.4): Structure, consistency, grounding
• Output (0.3): Exact match, fuzzy match, semantic similarity

Audio-Language

Train audio models (ASR, TTS, Classification) using RLVR with task-specific verification.

Quick Start

# Full pipeline
halo-forge audio sft --dataset librispeech_sft --model openai/whisper-small --output models/audio_sft
halo-forge audio train --model models/audio_sft --dataset librispeech --task asr --cycles 4 --seed 42
halo-forge audio benchmark --model models/audio_raft --dataset librispeech --limit 100

# Quick RAFT
halo-forge audio train --model openai/whisper-small --dataset librispeech --task asr --cycles 4 --seed 42

Supported Models

Reward Structure (ASR)

Reasoning and Math

Train models on mathematical reasoning with SymPy-based verification.

Quick Start

# Full pipeline
halo-forge reasoning sft --dataset metamath --model Qwen/Qwen2.5-3B-Instruct --output models/reasoning_sft
halo-forge reasoning train --model models/reasoning_sft --dataset gsm8k --cycles 4 --seed 42
halo-forge reasoning benchmark --model models/reasoning_raft --dataset gsm8k --limit 100

# Quick RAFT
halo-forge reasoning train --model Qwen/Qwen2.5-7B-Instruct --dataset gsm8k --cycles 4 --seed 42

Datasets

Reward Structure

Agentic / Tool Calling

Train models for reliable function/tool calling with schema-aware verification.

Quick Start

# Full pipeline
halo-forge agentic sft --dataset xlam_sft --model Qwen/Qwen2.5-7B-Instruct --output models/agentic_sft
halo-forge agentic train --model models/agentic_sft --dataset xlam --cycles 5 --seed 42
halo-forge agentic benchmark --model models/agentic_raft --dataset xlam --limit 100

# Quick RAFT
halo-forge agentic train --model Qwen/Qwen2.5-7B-Instruct --dataset xlam --cycles 5 --seed 42

Reward Structure

Data Format

halo-forge uses the Hermes format, standard for Qwen2.5 and NousHermes:

<|im_start|>assistant
<tool_call>
{"name": "get_weather", "arguments": {"location": "Paris"}}
</tool_call><|im_end|>

Inference Optimization

Optimize trained models for deployment with quantization and export.

Quick Start

# Optimize
halo-forge inference optimize \
  --model models/raft/final \
  --target-precision int4 \
  --output models/optimized

# Export to GGUF
halo-forge inference export \
  --model models/optimized \
  --format gguf \
  --quantization Q4_K_M \
  --output model.gguf

# Benchmark
halo-forge inference benchmark --model models/optimized --num-prompts 20

Quantization Options

GGUF Quantization Types

Readiness Levels

Feedback

If you encounter issues or have suggestions:

1. Check the Troubleshooting guide
2. Review the Changelog for recent changes
3. Open an issue on GitHub with reproduction steps