%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Openthaigpt 1.0.0 70b Chat
OpenThaiGPT 70b 1.0.0 is a 70-billion-parameter Thai chat model based on LLaMA v2, specifically fine-tuned for Thai language instructions, significantly enhancing Thai language processing capabilities.
Large Language Model Supports Multiple Languages#Thai Large Language Model#70 billion parameters#Multi-turn dialogue
Downloads 137
Release Time : 4/5/2024
Model Overview
This is a leading Thai large language model that excels in multiple Thai language exams, supports multi-turn dialogue and Retrieval-Augmented Generation (RAG), and is suitable for complex Thai language understanding and generation tasks.
Model Features
Leading Thai language processing capability
Achieves the highest average scores in multiple Thai language exams, surpassing all other open-source Thai LLMs.
First 70-billion-parameter open-source Thai LLM
Scores higher than OpenAI GPT 3.5, Google Gemini, and Claude 3 Haiku in Thai language exams.
Multi-turn dialogue support
Capable of handling complex multi-turn dialogue scenarios.
Retrieval-Augmented Generation (RAG) support
Can generate richer responses by incorporating external information.
Optimized generation speed
Generation speed improved tenfold by adding 10,000 common Thai vocabulary words.
Model Capabilities
Thai text generation
Multi-turn dialogue
Retrieval-Augmented Generation
Thai language understanding
Instruction following
Use Cases
Education
Thai exam tutoring
Helps students prepare for Thai language-related exams
Excels in multiple Thai language exams
Customer service
Thai customer service chatbot
Handles inquiries and issues from Thai-speaking customers
Capable of understanding complex Thai instructions and providing accurate responses
Content creation
Thai content generation
Generates high-quality Thai articles, reports, etc.
Produces natural and fluent Thai text
ð ðđð OpenThaiGPT 70b 1.0.0
OpenThaiGPT 70b 1.0.0 is an advanced Thai language chat model. It's based on LLaMA v2, fine - tuned for Thai instructions. With over 10,000 common Thai words added to its dictionary, it significantly boosts response speed.
ð Quick Start
To start using OpenThaiGPT 70b 1.0.0, you can follow the steps in the "How to use" section below.
âĻ Features
- Leading - edge Thai language LLM: Sets new benchmarks by achieving the highest average scores across several Thai language exams when compared to all other open - source Thai LLMs.
- The First 70b Thai opensource LLM: Achieves a higher score on Thai exams than OpenAI GPT 3.5, Google Gemini, and Claude 3 Haiku.
- Support for extended conversations: Enables conversations across multiple turns.
- Support for Retrieval Augmented Generation (RAG): Facilitates enriched response generation.
- Tenfold increase in generation speeds: Thanks to the addition of 10,000 frequently used Thai words to the model's dictionary.
- Pretrained on a large Thai language corpus: Pretrained upon a foundation of more than 65 billion Thai language words and fine - tuned with over 1 million Thai instruction examples.
- Large input context handling: Capable of understanding and processing input contexts of up to 4096 Thai words, allowing for detailed and complex instructions.
Benchmark on OpenThaiGPT Eval
Please take a look at OTG 13b (April 2024) for this model's evaluation result.
| Exams | OTG 7b (Aug 2023) | OTG 13b (Dec 2023) | OTG 7b (April 2024) | OTG 13b (April 2024) | OTG 70b (April 2024) | SeaLLM 7b v1 | SeaLLM 7b v2 | SeaLion 7b | WanchanGLM 7b | Sailor - 7b - Chat | TyphoonGPT 7b Instruct | GPT3.5 | GPT4 | Gemini Pro | Gemini 1.5 | Claude 3 Haiku | Claude 3 Sonnet | Claude 3 Opus |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| A - Level | 17.50% | 34.17% | 25.00% | 30.83% | 45.83% | 18.33% | 34.17% | 21.67% | 17.50% | 40.00% | 37.50% | 38.33% | 65.83% | 56.67% | 55.83% | 58.33% | 59.17% | 77.50% |
| TGAT | 24.00% | 22.00% | 22.00% | 36.00% | 36.00% | 14.00% | 28.00% | 24.00% | 16.00% | 34.00% | 30.00% | 28.00% | 44.00% | 22.00% | 28.00% | 36.00% | 34.00% | 46.00% |
| TPAT1 | 22.50% | 47.50% | 42.50% | 27.50% | 62.50% | 22.50% | 27.50% | 22.50% | 17.50% | 40.00% | 47.50% | 45.00% | 52.50% | 52.50% | 50.00% | 52.50% | 50.00% | 62.50% |
| thai_investment_consultant_exams | 8.00% | 28.00% | 76.00% | 84.00% | 68.00% | 16.00% | 28.00% | 24.00% | 16.00% | 24.00% | 32.00% | 40.00% | 64.00% | 52.00% | 32.00% | 44.00% | 64.00% | 72.00% |
| facebook_beleble_tha_200 | 25.00% | 45.00% | 34.50% | 39.50% | 70.00% | 13.50% | 51.00% | 27.00% | 24.50% | 63.00% | 51.50% | 50.00% | 72.50% | 65.00% | 74.00% | 63.50% | 77.00% | 90.00% |
| xcopa_th_200 | 45.00% | 56.50% | 49.50% | 51.50% | 74.50% | 26.50% | 47.00% | 51.50% | 48.50% | 68.50% | 65.00% | 64.00% | 82.00% | 68.00% | 74.00% | 64.00% | 80.00% | 86.00% |
| xnli2.0_th_200 | 33.50% | 34.50% | 39.50% | 31.00% | 47.00% | 21.00% | 43.00% | 37.50% | 33.50% | 16.00% | 20.00% | 50.00% | 69.00% | 53.00% | 54.50% | 50.00% | 68.00% | 68.50% |
| ONET M3 | 17.85% | 38.86% | 34.11% | 39.36% | 56.15% | 15.58% | 23.92% | 21.79% | 19.56% | 21.37% | 28.03% | 37.91% | 49.97% | 55.99% | 57.41% | 52.73% | 40.60% | 63.87% |
| ONET M6 | 21.14% | 28.87% | 22.53% | 23.32% | 42.85% | 15.09% | 19.48% | 16.96% | 20.67% | 28.64% | 27.46% | 34.44% | 46.29% | 45.53% | 50.23% | 34.79% | 38.49% | 48.56% |
| AVERAGE SCORE | 23.83% | 37.27% | 38.40% | 40.33% | 55.87% | 18.06% | 33.56% | 27.44% | 23.75% | 37.28% | 37.67% | 43.07% | 60.68% | 52.30% | 52.89% | 50.65% | 56.81% | 68.32% |
Thai language multiple choice exams, Test on unseen test set, Zero - shot learning. Benchmark source code and exams information: https://github.com/OpenThaiGPT/openthaigpt_eval
(Updated on: 7 April 2024)
Benchmark on M3Exam evaluated by an external party (Float16.cloud)
| Models | ENGLISH (M3EXAM) | THAI (M3EXAM) |
|---|---|---|
| OTG - 7b | 40.92 % | 25.14 % |
| OTG - 13b | 53.69 % | 36.49 % |
| OTG - 70b | 72.58 % | 48.29 % |
| GPT - 3.5 - turbo - 0613* | - | 34.1 % |
| GPT - 4 - 0613* | - | 56.0 % |
More information: https://blog.float16.cloud/the - first - 70b - thai - llm/
ð License
- Source Code: Licensed under the Apache Software License 2.0.
- Weight: Allows for research and Commercial uses.
Sponsors
Supports
- Official website: https://openthaigpt.aieat.or.th
- Facebook page: https://web.facebook.com/groups/openthaigpt
- A Discord server for discussion and support here
- E - mail: kobkrit@aieat.or.th
ðŧ Usage Examples
Prompt Format
The prompt format is based on Llama2 with a small modification (Adding "###" to specify the context part)
<s>[INST] <<SYS>
{system_prompt}
<</SYS>>
{human_turn1}###{context_turn1} [/INST]{assistant_turn1}</s><s>{human_turn2}###{context_turn2} [/INST] ...
System prompt:
You are a question answering assistant. Answer the question as truthful and helpful as possible āļāļļāļāļāļ·āļāļāļđāđāļāđāļ§āļĒāļāļāļāļāļģāļāļēāļĄ āļāļāļāļāļāļāļģāļāļēāļĄāļāļĒāđāļēāļāļāļđāļāļāđāļāļāđāļĨāļ°āļĄāļĩāļāļĢāļ°āđāļĒāļāļāđāļāļĩāđāļŠāļļāļ
Basic Usage
Single Turn Conversation Example
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible āļāļļāļāļāļ·āļāļāļđāđāļāđāļ§āļĒāļāļāļāļāļģāļāļēāļĄ āļāļāļāļāļāļāļģāļāļēāļĄāļāļĒāđāļēāļāļāļđāļāļāđāļāļāđāļĨāļ°āļĄāļĩāļāļĢāļ°āđāļĒāļāļāđāļāļĩāđāļŠāļļāļ
<</SYS>>
āļŠāļ§āļąāļŠāļāļĩāļāļĢāļąāļ [/INST]
Advanced Usage
Single Turn Conversation with Context (RAG) Example
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible āļāļļāļāļāļ·āļāļāļđāđāļāđāļ§āļĒāļāļāļāļāļģāļāļēāļĄ āļāļāļāļāļāļāļģāļāļēāļĄāļāļĒāđāļēāļāļāļđāļāļāđāļāļāđāļĨāļ°āļĄāļĩāļāļĢāļ°āđāļĒāļāļāđāļāļĩāđāļŠāļļāļ
<</SYS>>
āļāļĢāļļāļāđāļāļāļĄāļĩāļāļ·āđāļāļāļĩāđāđāļāđāļēāđāļĢāđ###āļāļĢāļļāļāđāļāļāļĄāļŦāļēāļāļāļĢ āđāļāđāļāđāļĄāļ·āļāļāļŦāļĨāļ§āļ āļāļāļĢāđāļĨāļ°āļĄāļŦāļēāļāļāļĢāļāļĩāđāļĄāļĩāļāļĢāļ°āļāļēāļāļĢāļĄāļēāļāļāļĩāđāļŠāļļāļāļāļāļāļāļĢāļ°āđāļāļĻāđāļāļĒ āļāļĢāļļāļāđāļāļāļĄāļŦāļēāļāļāļĢāļĄāļĩāļāļ·āđāļāļāļĩāđāļāļąāđāļāļŦāļĄāļ 1,568.737 āļāļĢ.āļāļĄ. āļĄāļĩāļāļĢāļ°āļāļēāļāļĢāļāļēāļĄāļāļ°āđāļāļĩāļĒāļāļĢāļēāļĐāļāļĢāļāļ§āđāļē 8 āļĨāđāļēāļāļāļ [/INST]
Multi Turn Conversation Example
First turn
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible āļāļļāļāļāļ·āļāļāļđāđāļāđāļ§āļĒāļāļāļāļāļģāļāļēāļĄ āļāļāļāļāļāļāļģāļāļēāļĄāļāļĒāđāļēāļāļāļđāļāļāđāļāļāđāļĨāļ°āļĄāļĩāļāļĢāļ°āđāļĒāļāļāđāļāļĩāđāļŠāļļāļ
<</SYS>>
āļŠāļ§āļąāļŠāļāļĩāļāļĢāļąāļ [/INST]
Second turn
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible āļāļļāļāļāļ·āļāļāļđāđāļāđāļ§āļĒāļāļāļāļāļģāļāļēāļĄ āļāļāļāļāļāļāļģāļāļēāļĄāļāļĒāđāļēāļāļāļđāļāļāđāļāļāđāļĨāļ°āļĄāļĩāļāļĢāļ°āđāļĒāļāļāđāļāļĩāđāļŠāļļāļ
<</SYS>>
āļŠāļ§āļąāļŠāļāļĩāļāļĢāļąāļ [/INST]āļŠāļ§āļąāļŠāļāļĩāļāđāļ° āļĄāļĩāļāļģāļāļēāļĄāļāļ°āđāļĢ āļāļēāļĄāđāļāđāđāļĨāļĒ</s><s>āļāļāļŠāļđāļāļĢāļāļģāļŠāđāļĄāļāļģāļŦāļāđāļāļĒ [/INST]
Third turn
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible āļāļļāļāļāļ·āļāļāļđāđāļāđāļ§āļĒāļāļāļāļāļģāļāļēāļĄ āļāļāļāļāļāļāļģāļāļēāļĄāļāļĒāđāļēāļāļāļđāļāļāđāļāļāđāļĨāļ°āļĄāļĩāļāļĢāļ°āđāļĒāļāļāđāļāļĩāđāļŠāļļāļ
<</SYS>>
āļŠāļ§āļąāļŠāļāļĩāļāļĢāļąāļ [/INST]āļŠāļ§āļąāļŠāļāļĩāļāđāļ° āļĄāļĩāļāļģāļāļēāļĄāļāļ°āđāļĢ āļāļēāļĄāđāļāđāđāļĨāļĒ</s><s>āļāļāļŠāļđāļāļĢāļāļģāļŠāđāļĄāļāļģāļŦāļāđāļāļĒ [/INST]āđāļāđāđāļĨāļĒāļāđāļ° āļŠāđāļĄāļāļģāđāļāđāļāđāļĄāļāļđāļāļĩāđāļāļģāļāđāļēāļĒāđāļĨāļ°āļāļĢāđāļāļĒ āļĄāļēāđāļĢāļīāđāļĄāļāļąāļāđāļĨāļĒāļāļ°āļāļ°</s><s>āđāļĢāļīāđāļĄāđāļāđāđāļĨāļĒ [/INST]
Fourth turn
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible āļāļļāļāļāļ·āļāļāļđāđāļāđāļ§āļĒāļāļāļāļāļģāļāļēāļĄ āļāļāļāļāļāļāļģāļāļēāļĄāļāļĒāđāļēāļāļāļđāļāļāđāļāļāđāļĨāļ°āļĄāļĩāļāļĢāļ°āđāļĒāļāļāđāļāļĩāđāļŠāļļāļ
<</SYS>>
āļŠāļ§āļąāļŠāļāļĩāļāļĢāļąāļ [/INST]āļŠāļ§āļąāļŠāļāļĩāļāđāļ° āļĄāļĩāļāļģāļāļēāļĄāļāļ°āđāļĢ āļāļēāļĄāđāļāđāđāļĨāļĒ</s><s>āļāļāļŠāļđāļāļĢāļāļģāļŠāđāļĄāļāļģāļŦāļāđāļāļĒ [/INST]āđāļāđāđāļĨāļĒāļāđāļ° āļŠāđāļĄāļāļģāđāļāđāļāđāļĄāļāļđāļāļĩāđāļāļģāļāđāļēāļĒāđāļĨāļ°āļāļĢāđāļāļĒ āļĄāļēāđāļĢāļīāđāļĄāļāļąāļāđāļĨāļĒāļāļ°āļāļ°</s><s>āđāļĢāļīāđāļĄāđāļāđāđāļĨāļĒ [/INST]
āļāļģāđāļāļĒāđāļāđāļāđāļĄāļāļđāļāļĩāđāđāļāļĢāđ āļāđāļāļļāđāļāđāļāļĒ āļāđāļ§āļĒāļĢāļŠāļāļēāļāļīāļāļĩāđāļāļĨāļĄāļāļĨāđāļāļĄ āļŦāļ§āļēāļ āđāļāļĢāļĩāđāļĒāļ§ āđāļāđāļĄ āđāļāđāļ āļāļĢāļāļĢāļŠ āļ§āļąāļāļāļĩāđāđāļĢāļēāļāļ°āļĄāļēāļāļģāļŠāđāļĄāļāļģāļāđāļ§āļĒāļāļąāļāļāđāļ° āļŠāļīāđāļāđāļĢāļāļāļĩāđāļāđāļāļāļĄāļĩāļāļ·āļāđāļāļĢāļ·āđāļāļāļāļĢāļļāļāļāļąāļāļāļĩāđ
- āļĄāļ°āļĨāļ°āļāļāļāļīāļ 1 āļĨāļđāļ
- āļāļļāđāļāđāļŦāđāļ 1/2 āļāđāļ§āļĒ
- āļāļĢāļ°āđāļāļĩāļĒāļĄ 3 āļāļĨāļĩāļ
- āļāļĢāļīāļāļāļĩāđāļŦāļāļđ 3 āđāļĄāđāļ
- āļāđāļģāļāļēāļĨāļāļĩāđāļ 1 āļāđāļāļāđāļāđāļ°
- āļāđāļģāļāļĨāļē 2 āļāđāļāļāđāļāđāļ°
- āļĄāļ°āļāļēāļ§ 1 āļĨāļđāļ
- āļāļēāļāļēāļ§āļāļąāđāļ§ 1/4 āļāđāļ§āļĒ
āļ§āļīāļāļĩāļāļģāļĄāļĩāļāļąāļāļāļĩāđāļāđāļ°
1. āđāļĢāļīāđāļĄāļāļēāļāļĨāđāļēāļāļĄāļ°āļĨāļ°āļāļāđāļŦāđāļŠāļ°āļāļēāļ āđāļĨāđāļ§āđāļāđāļĄāļĩāļāļāļāļāđāļāļĨāļ·āļāļ āđāļāļēāđāļŠāđāļāļāļ āļŦāļąāđāļāđāļāđāļāđāļŠāđāļāļāļēāļāđ āđāļāļĢāļĩāļĒāļĄāđāļ§āđ
2. āļāļģāļāļļāđāļāđāļŦāđāļāđāļŦāđāļĨāļ°āđāļāļĩāļĒāļ āđāļĨāđāļ§āļāļąāļāļāļķāđāļāļāļąāļāđāļ§āđ
3. āđāļāđāļāļĢāļāļŦāļīāļāļŦāļĢāļ·āļāđāļāļĢāļ·āđāļāļāļāļąāđāļ āļāļāļāļĢāļīāļāļāļĩāđāļŦāļāļđāļāļąāļāļāļĢāļ°āđāļāļĩāļĒāļĄāđāļŦāđāļĨāļ°āđāļāļĩāļĒāļ
4. āđāļŠāđāļāļļāđāļāđāļŦāđāļāļāļĩāđāļāļģāđāļĨāđāļ§āļĨāļāđāļāļāļŠāļĄ āļāļēāļĄāļāđāļ§āļĒāļāđāļģāļāļēāļĨāļāļĩāđāļ āļāđāļģāļāļĨāļē āļĄāļ°āļāļēāļ§ āđāļĨāļ°āđāļŠāđāļāļĄāļ°āļĨāļ°āļāļ āļāļĨāļļāļāđāļāļĨāđāļēāđāļŦāđāđāļāđāļēāļāļąāļ
5. āļāļīāļĄāļĢāļŠāđāļŦāđāđāļāđāļĢāļŠāļŦāļ§āļēāļ āđāļāļĢāļĩāđāļĒāļ§ āđāļāđāļĄ āđāļāđāļ āļāļēāļāļāļąāđāļāļāļąāļāļāļķāđāļāđāļŠāļīāļĢāđāļāļāļĢāđāļāļĄāļāļąāļāļŠāļ āļāļēāļāļī āļāļ°āļŦāļĨāđāļģāļāļĨāļĩ āļāļąāđāļ§āļāļāļ āđāļāļĢāļāļ āļāļąāļāļāļļāđāļ</s><s>āļāļāļāļāļļāļāļāļĢāļąāļ [/INST]
Multi Turn Conversation with Context (RAG) Example
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible āļāļļāļāļāļ·āļāļāļđāđāļāđāļ§āļĒāļāļāļāļāļģāļāļēāļĄ āļāļāļāļāļāļāļģāļāļēāļĄāļāļĒāđāļēāļāļāļđāļāļāđāļāļāđāļĨāļ°āļĄāļĩāļāļĢāļ°āđāļĒāļāļāđāļāļĩāđāļŠāļļāļ
<</SYS>>
āļāļĢāļļāļāđāļāļāļĄāļĩāļāļ·āđāļāļāļĩāđāđāļāđāļēāđāļĢāđ###āļāļĢāļļāļāđāļāļāļĄāļŦāļēāļāļāļĢ āđāļāđāļāđāļĄāļ·āļāļāļŦāļĨāļ§āļ āļāļāļĢāđāļĨāļ°āļĄāļŦāļēāļāļāļĢāļāļĩāđāļĄāļĩāļāļĢāļ°āļāļēāļāļĢāļĄāļēāļāļāļĩāđāļŠāļļāļāļāļāļāļāļĢāļ°āđāļāļĻāđāļāļĒ āļāļĢāļļāļāđāļāļāļĄāļŦāļēāļāļāļĢāļĄāļĩāļāļ·āđāļāļāļĩāđāļāļąāđāļāļŦāļĄāļ 1,568.737 āļāļĢ.āļāļĄ. āļĄāļĩāļāļĢāļ°āļāļēāļāļĢāļāļēāļĄāļāļ°āđāļāļĩāļĒāļāļĢāļēāļĐāļāļĢāļāļ§āđāļē 8 āļĨāđāļēāļāļāļ [/INST]
āļāļĢāļļāļāđāļāļāļĄāļŦāļēāļāļāļĢāļĄāļĩāļāļ·āđāļāļāļĩāđāļāļąāđāļāļŦāļĄāļ 1,568.737 āļāļĢ.āļāļĄ.</s><s>āđāļĨāļ°āļāļĢāļ°āļāļēāļāļĢāļĨāđāļ° [/INST]
How to use
Huggingface
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Ensure CUDA is available
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print(f"Using device: {device}")
# Init Model
model_path="openthaigpt/openthaigpt-1.0.0-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.float16)
model.to(device)
# Prompt
prompt = "āļŠāļ§āļąāļŠāļāļĩāļāļĢāļąāļ OpenThaiGPT"
llama_prompt = f"<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible āļāļļāļāļāļ·āļāļāļđāđāļāđāļ§āļĒāļāļāļāļāļģāļāļēāļĄ āļāļāļāļāļāļāļģāļāļēāļĄāļāļĒāđāļēāļāļāļđāļāļāđāļāļāđāļĨāļ°āļĄāļĩāļāļĢāļ°āđāļĒāļāļāđāļāļĩāđāļŠāļļāļ<</SYS>>\n\n{prompt} [/INST]"
inputs = tokenizer.encode(llama_prompt, return_tensors="pt")
inputs = inputs.to(device)
Phi 2 GGUF
Other
Phi-2 is a small yet powerful language model developed by Microsoft, featuring 2.7 billion parameters, focusing on efficient inference and high-quality text generation.
Large Language Model Supports Multiple Languages
P
TheBloke
41.5M
205
Roberta Large
MIT
A large English language model pre-trained with masked language modeling objectives, using improved BERT training methods
Large Language Model English
R
FacebookAI
19.4M
212
Distilbert Base Uncased
Apache-2.0
DistilBERT is a distilled version of the BERT base model, maintaining similar performance while being more lightweight and efficient, suitable for natural language processing tasks such as sequence classification and token classification.
Large Language Model English
D
distilbert
11.1M
669
Llama 3.1 8B Instruct GGUF
Meta Llama 3.1 8B Instruct is a multilingual large language model optimized for multilingual dialogue use cases, excelling in common industry benchmarks.
Large Language Model English
L
modularai
9.7M
4
Xlm Roberta Base
MIT
XLM-RoBERTa is a multilingual model pretrained on 2.5TB of filtered CommonCrawl data across 100 languages, using masked language modeling as the training objective.
Large Language Model Supports Multiple Languages
X
FacebookAI
9.6M
664
Roberta Base
MIT
An English pre-trained model based on Transformer architecture, trained on massive text through masked language modeling objectives, supporting text feature extraction and downstream task fine-tuning
Large Language Model English
R
FacebookAI
9.3M
488
Opt 125m
Other
OPT is an open pre-trained Transformer language model suite released by Meta AI, with parameter sizes ranging from 125 million to 175 billion, designed to match the performance of the GPT-3 series while promoting open research in large-scale language models.
Large Language Model English
O
facebook
6.3M
198
1
A pretrained model based on the transformers library, suitable for various NLP tasks
Large Language Model
Transformers
Transformers1
unslothai
6.2M
1
Llama 3.1 8B Instruct
Llama 3.1 is Meta's multilingual large language model series, featuring 8B, 70B, and 405B parameter scales, supporting 8 languages and code generation, with optimized multilingual dialogue scenarios.
Large Language Model Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesL
meta-llama
5.7M
3,898
T5 Base
Apache-2.0
The T5 Base Version is a text-to-text Transformer model developed by Google with 220 million parameters, supporting multilingual NLP tasks.
Large Language Model Supports Multiple Languages
T
google-t5
5.4M
702
Featured Recommended AI Models
ÂĐ 2025AIbase