LLM EXPLORER 59,420 MODELS INDEXED

Sailor 14B Chat by sail

By sail · 27 downloads
HF Repo ↗ Copy URL

Sailor 14B Chat is an open-source language model by sail. Features: 14b LLM, VRAM: 28.4GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.12.

  Arxiv:2404.03608 Base model:finetune:sail/sailo...   Base model:sail/sailor-14b   Chat   Conversational Dataset:cohereforai/aya collec... Dataset:cohereforai/aya datase... Dataset:huggingfaceh4/ultracha...   Dataset:open-orca/openorca   Dataset:openbmb/ultrafeedback   En   Endpoints compatible   Id   Instruct   Instruction   Lo   Ms   Multilingual   Pytorch   Qwen2   Region:us   Safetensors   Sailor   Sea   Sft   Sharded   Tensorflow   Th   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/sail/Sailor-14B-Chat 

Sailor 14B Chat Parameters and Internals

Model Type 
multilingual, chat, instruction
Use Cases 
Areas:
research, commercial applications
Applications:
question answering, commonsense reasoning
Primary Use Cases:
Text generation in SEA languages
Supported Languages 
en (proficient), zh (proficient), id (SEA), th (SEA), vi (SEA), ms (SEA), lo (SEA)
Training Details 
Data Sources:
SlimPajama, SkyPile, CC100, MADLAD-400
Data Volume:
200B to 400B tokens
Methodology:
Continually pre-training with instruction tuning
Training Time:
200B tokens: other models, 400B tokens: Qwen1.5-0.5B model
Input Output 
Input Format:
System and assistant prompt messages
Accepted Modalities:
text
Output Format:
Textual response
LLM NameSailor 14B Chat
Repository 🤗https://huggingface.co/sail/Sailor-14B-Chat 
Base Model(s)  Sailor 14B   sail/Sailor-14B
Model Size14b
Required VRAM28.4 GB
Updated2026-08-08
Maintainersail
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   3.5 GB: 6-of-6   4.9 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   3.5 GB: 6-of-6
Supported Languagesen zh id th vi ms lo
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Sailor 14B Chat

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB10388342
T3Q Qwen2.5 14B V1.0 E3986K / 29.7 GB85228
ZYH LLM Qwen2.5 14B V4986K / 29.7 GB278
Qwen2.5 14B 1M YOYO V3986K / 29.7 GB2544
Qwen2.5 14B YOYO V4986K / 29.7 GB205
Qwen2.5 14B YOYO Latest V2986K / 29.7 GB1290
ZYH LLM Qwen2.5 14B V3986K / 29.7 GB238
...14B Instruct 1M GRPO Reasoning986K / 29.7 GB114
Impish QWEN 14B 1M986K / 29.7 GB5626
Q2.5 14B Instruct 1M Harmony986K / 29.7 GB31
Note: green Score (e.g. "73.2") means that the model is better than sail/Sailor-14B-Chat.