5a086353ab
Add end-to-end embedding/sentence-transformer training pipeline using FastSentenceTransformer, SentenceTransformerTrainer, and MultipleNegativesRankingLoss with BatchSamplers.NO_DUPLICATES. Backend: - Add is_embedding_model() detection via HF tags + pipeline_tag - Add /check-embedding/ API route and EmbeddingCheckResponse - Extend derive_model_type() to return "embeddings" - Add _run_embedding_training() in worker.py with progress callbacks, stop handling, LoRA (task_type=FEATURE_EXTRACTION), and model saving - Add is_embedding field to TrainingStartRequest and ModelDetails - Add YAML configs for 5 models: all-MiniLM-L6-v2, bge-m3, embeddinggemma-300m, gte-modernbert-base, Qwen3-Embedding-0.6B Frontend: - Wire isEmbeddingModel flag through store, API types, and mappers - Force packing=false, train_on_completions=false, warmup_ratio=0.03 - Hide packing and train_on_completions checkboxes for embedding models - Auto-set modelType to "embeddings" from backend model_type response
43 lines
1,003 B
Python
43 lines
1,003 B
Python
# SPDX-License-Identifier: AGPL-3.0-only - See /studio/LICENSE.AGPL-3.0
|
|
# Copyright © 2025 Unsloth AI
|
|
|
|
"""
|
|
Model and LoRA configuration handling
|
|
"""
|
|
from .model_config import (
|
|
ModelConfig,
|
|
GgufVariantInfo,
|
|
is_vision_model,
|
|
is_embedding_model,
|
|
detect_audio_type,
|
|
is_audio_input_type,
|
|
VALID_AUDIO_TYPES,
|
|
scan_trained_loras,
|
|
scan_exported_models,
|
|
load_model_defaults,
|
|
get_base_model_from_lora,
|
|
load_model_config,
|
|
list_gguf_variants,
|
|
MODEL_NAME_MAPPING,
|
|
UI_STATUS_INDICATORS,
|
|
)
|
|
from .checkpoints import scan_checkpoints
|
|
|
|
__all__ = [
|
|
'ModelConfig',
|
|
'GgufVariantInfo',
|
|
'is_vision_model',
|
|
'is_embedding_model',
|
|
'detect_audio_type',
|
|
'is_audio_input_type',
|
|
'VALID_AUDIO_TYPES',
|
|
'scan_trained_loras',
|
|
'scan_exported_models',
|
|
'load_model_defaults',
|
|
'get_base_model_from_lora',
|
|
'load_model_config',
|
|
'list_gguf_variants',
|
|
'MODEL_NAME_MAPPING',
|
|
'UI_STATUS_INDICATORS',
|
|
'scan_checkpoints',
|
|
]
|