100+ Open-source LLMs Ready to Use
The largest selection of models for fine-tuning and serving
Predibase offers the largest selection of open-source models for fine-tuning and serving across serverless and dedicated endpoints. Check out our current list of supported models and guidance on how to bring your own models in the table below.
Name | Description | Context Window | Always On |
---|---|---|---|
BioMistral 7B | BioMistral is a suite of Mistral-based further pre-trained open source models suited for the medical domains and pre-trained using textual data from PubMed Central Open Access. This is the base 7B model. | 2,048 | |
CodeLlama 7B | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the 7B base version. | 16,000 | |
CodeLlama 7B Instruct | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the 7B instruct-tuned version. | 16,000 | |
CodeLlama 7B Python | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the 7B Python specialist version. | 16,000 | |
CodeLlama 13B | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the 13B base version. | 16,000 | |
CodeLlama 13B Instruct Serverless | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the instruction-tuned 13B model. | 4,096 | |
CodeLlama 34B | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the 34B base version. | 16,000 | |
CodeLlama 13B Python | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the 13B Python specialist version. | 16,000 | |
CodeLlama 34B Instruct | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the 34B instruct-tuned version. | 16,000 | |
CodeLlama 34B Python | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the 34B Python specialist version. | 16,000 | |
CodeLlama 34B Python v1 - Phind | Fine-tuned CodeLlama-34B and CodeLlama-34B-Python on an internal Phind dataset. | 16,000 | |
CodeLlama 34B v1 - Phind | Fine-tuned CodeLlama-34B and CodeLlama-34B-Python on an internal Phind dataset. | 16,000 | |
CodeLlama 34B v2 - Phind | Fine-tuned Phind-CodeLlama-34B-v1 on an additional 1.5B tokens high-quality programming-related data. | 16,000 | |
CodeLlama 70B | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the 70B base version. | 4,096 | |
CodeLlama 70B Instruct Serverless | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the instruction-tuned 70B model. | 4,096 | |
CodeLlama 70B Python | Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the 70B Python specialist version. | 100,000 | |
Gemma 2B Serverless | This is the 2B base version of the Gemma model. | 8,192 | |
Gemma 2B Instruct Serverless | This is the 2B instruction-tuned version of the Gemma model. | 8,192 | |
Gemma 7B Serverless | This is the 7B base version of the Gemma model | 8,192 | |
Gemma 7B Instruct Serverless | This is the 7B instruction-tuned version of the Gemma model. | 8,192 | |
GPT2 | GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. | 1,024 | |
GPT2 Medium | GPT-2 Medium is the 355M parameter version of GPT-2, a transformer-based language model created and released by OpenAI. | 1,024 | |
GPT2 Large | GPT-2 Large is the 774M parameter version of GPT-2, a transformer-based language model created and released by OpenAI. | 1,024 | |
GPT2 XL | GPT-2 XL is the 1.5B parameter version of GPT-2, a transformer-based language model created and released by OpenAI. | 1,024 | |
Llama 2 7B Serverless | Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the base 7B model. | 4,096 | |
Llama 2 7B Chat Serverless | Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the instruction tuned 7B model. | 4,096 | |
Llama 2 13B Serverless | Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the base 13B model. | 4,096 | |
Llama 2 13B Chat Serverless | Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the instruction-tuned 13B model. | 4,096 | |
Llama 2 70B Serverless | Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the base 70B model. | 4,096 | |
Llama 2 70B Chat Serverless | Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the instruction-tuned 70B model. | 4,096 | |
Llama 3 8B Serverless | Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. This is the base 8B parameter model. | 8,192 | |
Llama 3 8B Instruct Serverless | Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. This is the instruction-tuned 8B parameter model. | 8,192 | |
Llama 3 70B Serverless | Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. This is the base 70B parameter model. | 8,192 | |
Llama 3 70B Instruct Serverless | Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. This is the instruction tuned 70B parameter model. | 8,192 | |
Llama Guard 2 8B | Meta Llama Guard 2 is an 8B parameter Llama 3-based [1] LLM safeguard model. | 8,192 | |
Meditron 7B | Meditron is a suite of open-source medical Large Language Models (LLMs). Meditron-7B is a 7 billion parameters model adapted to the medical domain from Llama-2-7B through continued pretraining on a comprehensively curated medical corpus, including selected PubMed articles, abstracts, a new dataset of internationally-recognized medical guidelines, and general domain data from RedPajama-v1. | 2,000 | |
Meditron 70B | Meditron is a suite of open-source medical Large Language Models (LLMs). Meditron-70B is a 70 billion parameters model adapted to the medical domain from Llama-2-70B through continued pretraining on a comprehensively curated medical corpus, including selected PubMed articles, abstracts, a new dataset of internationally-recognized medical guidelines, and general domain data from RedPajama-v1. | 2,000 | |
Mixtral 8x7B Instruct v01 Serverless | The Mixtral-8x7B-instruct-v0.1 Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. | 32,768 | |
Mistral 7B Instruct v02 Serverless | The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2. | 32,768 | |
Mistral 7B Serverless | The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. | 32,768 | |
Mistral 7B Instruct Serverless | The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets. | 32,768 | |
Mixtral 8x7B v01 | The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. | 32,768 | |
Phi 2 Serverless | Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as Phi-1.5, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). | 2,048 | |
Phi 3 4k Instruct Serverless | The Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets. This is the 4k context window instruct version of the model. | 4,000 | |
Qwen 14B | Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. This is the 14B base version. | 32,000 | |
Qwen 32B | Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. This is the 32B base version. | 32,000 | |
Qwen 72B | Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. This is the 72B base version. | 32,000 | |
Zephyr 7B Beta | Zephyr-7B-β is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO). | 32,768 |
Bring Your Own Model
Predibase is the only platform that allows you to take nearly any standard base or fine-tuned LLM from HuggingFace and serve it as a dedicated deployment on state-of-the-art managed infra.