Browse deepinfra models:

All categories and models you can try out and directly use in deepinfra:
Search

Category/text-generation

Text generation AI models can generate coherent and natural-sounding human language text, making them useful for a variety of applications from language translation to content creation.

There are several types of text generation AI models, including rule-based, statistical, and neural models. Neural models, and in particular transformer-based models like GPT, have achieved state-of-the-art results in text generation tasks. These models use artificial neural networks to analyze large text corpora and learn the patterns and structures of language.

While text generation AI models offer many exciting possibilities, they also present some challenges. For example, it's essential to ensure that the generated text is ethical, unbiased, and accurate, to avoid potential harm or negative consequences.

Austism/chronos-hermes-13b-v2 cover image
4k
$0.22 / Mtoken
  • text-generation

This offers the imaginative writing style of chronos while still retaining coherency and being capable. Outputs are long and utilize exceptional prose. Supports a maxium context length of 4096. The model follows the Alpaca prompt format.

EleutherAI/gpt-j-6B cover image
2k
$0.0005 / sec
  • text-generation

GPT-J 6B is a 6 billion parameter transformer model trained using Ben Wang's Mesh Transformer JAX. It was trained on the Pile, a large-scale curated dataset created by EleutherAI. The model consists of 28 layers with a model dimension of 4096, and a feedforward dimension of 16384.

EleutherAI/gpt-neo-1.3B cover image
2k
$0.0005 / sec
  • text-generation

We present GPT-Neo 1.3B, a transformer model designed using EleutherAI's replication of the GPT-3 architecture. With 1.3B parameters, this model was trained on the large-scale curated dataset, Pile, for 380 billion tokens over 362,000 steps. Its intended use is for text generation, where it learns an inner representation of the English language and can generate texts from a prompt.

EleutherAI/gpt-neo-125M cover image
2k
$0.0005 / sec
  • text-generation

A transformer model trained on the Pile dataset for masked autoregressive language modeling. With 125 million parameters, our model is capable of generating high-quality text given a prompt. However, we acknowledge potential limitations and biases in the model's responses, particularly regarding profanity and offensiveness, and advise users to exercise caution when deploying the model for real-world applications.

EleutherAI/gpt-neo-2.7B cover image
2k
$0.0005 / sec
  • text-generation

We present GPT-Neo 2.7B, a transformer model designed using EleutherAI's replication of the GPT-3 architecture. With 2.7B parameters, this model was trained on the large-scale curated dataset, Pile, for 420 billion tokens over 400,000 steps. GPT-Neo 2.7B achieves state-of-the-art results on various benchmarks, including linguistic reasoning, physical and scientific reasoning, and down-stream applications.

EleutherAI/pythia-12b cover image
2k
$0.0005 / sec
  • text-generation

The Pythia Scaling Suite includes 16 models (2 per size) with sizes ranging from 70M to 12B parameters, trained on the Pile dataset. The models are designed for interpretability research and match or exceed performance of similar models. The suite includes 154 intermediate checkpoints per model.

EleutherAI/pythia-2.8b cover image
2k
$0.0005 / sec
  • text-generation

Pythia Scaling Suite is a collection of models for interpretability research, containing 8 models from 70M to 12B, with two models per size (one trained on Pile and the other on deduped Pile). The models are designed for scientific research, esp interpretability research. The model matches or exceeds performance of similar models like OPT and GPT-Neo.

Phind/Phind-CodeLlama-34B-v2 cover image
4k
$0.60 / Mtoken
  • text-generation

Phind-CodeLlama-34B-v2 is an open-source language model that has been fine-tuned on 1.5B tokens of high-quality programming-related data and achieved a pass@1 rate of 73.8% on HumanEval. It is multi-lingual and proficient in Python, C/C++, TypeScript, Java, and more. It has been trained on a proprietary dataset of instruction-answer pairs instead of code completion examples. The model is instruction-tuned on the Alpaca/Vicuna format to be steerable and easy-to-use. It accepts the Alpaca/Vicuna instruction format and can generate one completion for each prompt.

Salesforce/codegen-16B-mono cover image
2k
$0.0005 / sec
  • text-generation

CodeGen is a family of autoregressive language models for program synthesis, trained on a Python programming language dataset. The models are capable of extracting features from given natural language and programming language texts, and calculating the likelihood of them. They are intended for and best at program synthesis, that is, generating executable code given English prompts. The evaluation results show that CodeGen achieves state-of-the-art performance on two code generation benchmarks, HumanEval and MTPB.

bigcode/starcoder cover image
8k
$0.0005 / sec
  • text-generation

A 15.5B parameter model trained on 80+ programming languages from The Stack (v1.2) dataset, using a GPT-2 architecture with multi-query attention and Fill-in-the-Middle objective. The model is capable of generating code snippets provided some context, but the generated code is not guaranteed to work as intended and may contain bugs or exploits. The model is licensed under the BigCode OpenRAIL-M v1 license agreement.

codellama/CodeLlama-34b-Instruct-hf cover image
4k
$0.60 / Mtoken
  • text-generation

Code Llama is a state-of-the-art LLM capable of generating code, and natural language about code, from both code and natural language prompts. This particular instance is the 34b instruct variant

gpt2 cover image
1k
$0.0005 / sec
  • text-generation

GPT-2 is a transformer-based language model developed by OpenAI that utilizes a causal language modeling (CLM) objective. It was trained on a 40GB dataset called WebText, which consists of texts from various websites, excluding Wikipedia. Without fine-tuning, GPT-2 achieved impressive zero-shot results on several benchmark datasets such as LAMBADA, CBT-CN, CBT-NE, WikiText2, PTB, enwiki8, and text8.

meta-llama/Llama-2-13b-chat-hf cover image
4k
$0.22 / Mtoken
  • text-generation

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 repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format.

mistralai/Mistral-7B-Instruct-v0.1 cover image
32k
$0.13 / Mtoken
  • text-generation

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.