VinAIResearch/PhoGPT

• highreadme#1

  Emphasize instruction-following capability in README introduction

  Why:

  CURRENT

  We open-source a state-of-the-art 4B-parameter generative model series for Vietnamese, which includes the base pre-trained monolingual model PhoGPT-4B and its chat variant, PhoGPT-4B-Chat. The base model, PhoGPT-4B, with exactly 3.7B parameters, is pre-trained from scratch on a Vietnamese corpus of 102B tokens, with an 8192 context length, employing a vocabulary of 20K token types. The chat variant, PhoGPT-4B-Chat, is the modeling output obtained by fine-tuning PhoGPT-4B on a dataset of 70K instructional prompts and their responses, along with an additional 290K conversations. We demonstrate its superior performance compared to previous open-source models.

  COPY-PASTE FIX

  Copy

  We open-source a state-of-the-art 4B-parameter generative model series for Vietnamese, which includes the base pre-trained monolingual model PhoGPT-4B and its chat variant, PhoGPT-4B-Chat, which is specifically designed for instruction following. The base model, PhoGPT-4B, with exactly 3.7B parameters, is pre-trained from scratch on a Vietnamese corpus of 102B tokens, with an 8192 context length, employing a vocabulary of 20K token types. The chat variant, PhoGPT-4B-Chat, is the modeling output obtained by fine-tuning PhoGPT-4B on a dataset of 70K instructional prompts and their responses, along with an additional 290K conversations. We demonstrate its superior performance compared to previous open-source models.

  OpenDoneDismiss
• mediumhomepage#2

  Add the technical report URL as the repository homepage

  Why:

  COPY-PASTE FIX

  Copy

  https://arxiv.org/abs/2310.04673

  OpenDoneDismiss
• lowtopics#3

  Add 'chat-model' to repository topics

  Why:

  CURRENT

  generative-pre-trained-transformer, gpt, instruction-following, llm, phogpt, vietnamese, vietnamese-nlp

  COPY-PASTE FIX

  Copy

  generative-pre-trained-transformer, gpt, instruction-following, llm, phogpt, vietnamese, vietnamese-nlp, chat-model

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  What are the best open-source generative language models for Vietnamese text generation?

  you: #1
  AI recommended (in order):

  1. PhoGPT ← you
  2. ViT5
  3. BLOOM
  4. mT5
  5. LLaMA / LLaMA 2
  6. GPT-J
  Show full AI answer
• CATEGORY QUERY

  Seeking a large language model capable of instruction following for Vietnamese natural language processing.

  you: not recommended
  AI recommended (in order):

  1. GPT-4
  2. GPT-3.5 Turbo
  3. Claude 3 Opus
  4. Claude 3 Sonnet
  5. Gemini 1.5 Pro
  6. Mistral Large
  7. ViLLM

  AI recommended 7 alternatives but never named VinAIResearch/PhoGPT. This is the gap to close.

  Show full AI answer

• Metadata completeness

  warn

  Suggestion:

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of VinAIResearch/PhoGPT?

  pass
  ✓AI named VinAIResearch/PhoGPT explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts VinAIResearch/PhoGPT in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named VinAIResearch/PhoGPT explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo VinAIResearch/PhoGPT solve, and who is the primary audience?

  pass
  ✓AI named VinAIResearch/PhoGPT explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?