Sail Sailor 14B Chat AWQ 4bit Smashed by PrunaAI

 ยป  All LLMs  ยป  PrunaAI  ยป  Sail Sailor 14B Chat AWQ 4bit Smashed   URL Share it on

  4-bit   4bit   Autotrain compatible   Awq Base model:prunaai/sail-sailor... Base model:quantized:prunaai/s...   Conversational   Endpoints compatible   Pruna-ai   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Sail Sailor 14B Chat AWQ 4bit Smashed Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sail Sailor 14B Chat AWQ 4bit Smashed (PrunaAI/sail-Sailor-14B-Chat-AWQ-4bit-smashed)

Sail Sailor 14B Chat AWQ 4bit Smashed Parameters and Internals

Additional Notes 
The smashed model is a compressed version of the SAIL-Sailor-14B-Chat model with focus on reduced inference speed, memory usage, and energy consumption while maintaining efficiency. It uses safetensors format for model storage.
LLM NameSail Sailor 14B Chat AWQ 4bit Smashed
Repository ๐Ÿค—https://huggingface.co/PrunaAI/sail-Sailor-14B-Chat-AWQ-4bit-smashed 
Base Model(s)  ...ilor 14B Chat AWQ 4bit Smashed   PrunaAI/sail-Sailor-14B-Chat-AWQ-4bit-smashed
Model Size14b
Required VRAM9.7 GB
Updated2025-02-05
MaintainerPrunaAI
Model Typeqwen2
Model Files  5.0 GB: 1-of-2   4.7 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq|4bit
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.40.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Quantized Models of the Sail Sailor 14B Chat AWQ 4bit Smashed

Model
Likes
Downloads
VRAM
...ilor 14B Chat AWQ 4bit Smashed059 GB

Best Alternatives to Sail Sailor 14B Chat AWQ 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 Coder 14B Instruct AWQ32K / 10 GB151656
Qwen2.5 14B Instruct AWQ32K / 10 GB1921213
Qwen1.5 14B Chat AWQ32K / 9.7 GB73021
...gent DPO 16K AWQ 4bit 2024053132K / 9.7 GB41
...B Instruct 1M Unsloth Bnb 4bit986K / 14.3 GB2342
Qwen2.5 14B Instruct 1M 8bit986K / 15.7 GB2392
...till Qwen 14B Unsloth Bnb 4bit128K / 13.9 GB918012
QwQ 14B Math V0.2128K / 29.7 GB14715
...k R1 Distill Qwen 14B Bnb 4bit128K / 9.9 GB31563
Qwen Carpmuscle V0.3128K / 29.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/sail-Sailor-14B-Chat-AWQ-4bit-smashed.

Rank the Sail Sailor 14B Chat AWQ 4bit Smashed Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 42577 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227