| Model Type | Models |
|---|---|
| Qwen Models | qwen-2.5-14b-instruct qwen2.5-32b qwen2-7B-instruct qwen2.5-7b-coder qwen-2-0.5b-instruct qwen2-1.5-instruct bling-qwen-0.5b bling-qwen-1.5b |
| Llama-Based Models | llama-3.2-3b-onnx-qnn llama-3.2-3b-instruct-onnx llama-2-chat llama-3.1-instruct llama-3.2-ib-instruct tiny-llama-chat bling-tiny-llama llama-3.1-instruct llama-2-7b-chat llama-3.2-1b-instruct tiny-llama-chat llama-3-8b-instruct |
| Phi Models | phi-3.5 phi-3-vision phi-3 bling-phi-3 bling-phi-3 bling-phi-3.5 |
| Mistral Models | mistral-7b-instruct-v0.3 openhermes-2.5-mistral |
| Gemma Models | gemma-2b-it gemma-2-9b-instruct gemma-2-27b-instruct |
| Dragon Models | dragon-mistral-0.3 dragon-llama-3.1 dragon-mistral-0.3 dragon-yi-answer-tool dragon-llama-answer-tool dragon-mistral-answer-tool dragon-yi-9b dragon-qwen-7b |
| Slim Models | slim-extract-phi-3 slim-boolean-phi-3 slim-summary-phi-3 slim-emotions slim-topics slim-sql slim-summary-tiny slim-sentiment slim-extract-tiny slim-intent slim-tags slim-ratings slim-ner slim-extract-qwen-nano slim-sa-ner-phi-3 slim-xsum-phi-3 slim-boolean-phi-3 slim-sentiment-tool slim-sentiment slim-extract-tool slim-summary-tool slim-boolean-tool slim-tags-tool slim-xsum-tool slim-emotions-tool slim-topics-tool slim-sql-tool slim-extract-phi-3 slim-extract-qwen-1.5b slim-ner-tool slim-sa-ner-tool slim-tags-3b-tool slim-summary-phi-3 slim-extract-tiny-tool slim-ratings-tool slim-intent-tool slim-category-tool slim-nli-tool slim-q-gen-phi-3-tool slim-summary-tiny-tool slim-qa-gen-phi-3-tool slim-qa-gen-tiny-tool |
| StableLM Models | bling-stablelm-3b |
| Jina Models | jina-reranker-turbo jina-reranker-tiny |
| Specialized Models | unitary-unbiased-toxic-roberta valurank-distilroberta-bias |
| Other Models | protectai-prompt-injection zephyr-7b-beta starling-1m-7b-alpha miniCPM-V-2_6 bling-answer-tool |
DRAGON Models
Production-grade RAG-optimized 6-7B parameter models - "Delivering RAG on ...". Fine-tuned for question-answering, fact-based uses in RAG workflows. Uses the context provided to answer yes/no and multiple-choice questions. Trained to reduce hallucinations.
SLIM Models
Function-calling, structured output models for classifying and clustering tasks. Designed to be used in an AI Agent workflow either alone or stacked together. 10+ Structured Language Instruction Models (SLIMs) for almost every classifying task.
Custom Models
Expert custom model training services for your company and your domain. Full-service custom model fine-tuning from datasets to training (and beyond). Services include small specialized models (7B and under) and embedding models.
Industry BERT Models
Industry and specialized domain finetuned BERT embedding models. Specialized domains include: Insurance, SEC documents, Contracts & Asset Management.
SLIM GGUF
Quantized GGUF "tool" implementations of SLIM Models. Provide "gguf" and "tool" versions of many SLIM, DRAGON, and BLING models, optimized for CPU deployment. GGUF Generative Model class - support for Stable-LM-3B, CUDA build options, and better control over sampling strategies.
BLING Models
