Qwen2 7B Alpacha Merged 4bit by dbands

 ยป  All LLMs  ยป  dbands  ยป  Qwen2 7B Alpacha Merged 4bit   URL Share it on

  Merged Model   4-bit   4bit   Autotrain compatible Base model:unsloth/qwen2-7b-bn...   Bitsandbytes   Conversational   En   Endpoints compatible   License:apache-2.0   Quantized   Qwen2   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth

Rank the Qwen2 7B Alpacha Merged 4bit 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  
Qwen2 7B Alpacha Merged 4bit (dbands/Qwen2-7b-Alpacha-merged_4bit)

Best Alternatives to Qwen2 7B Alpacha Merged 4bit

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Qwen2 7B Bnb 4bit128K / 5.5 GB79422
PiSSA Qwen2 7B 4bit R128 5iter128K / 5.9 GB520
...lphin 2.9.2 Qwen2 7B Bpw6 EXL2128K / 6.4 GB11
Qwen2 7B 8bit128K / 8.1 GB61
Qwen2 7B Alpacha Merged 16bit128K / 15.2 GB80
...odeQwen1.5 7B Chat EXL2 5.0bpw64K / 5.1 GB90
...odeQwen1.5 7B Chat EXL2 8.0bpw64K / 7.5 GB94
CodeQwen1.5 7B EXL2 8.0bpw64K / 7.5 GB11
Qwen2 7B Instruct 4bit32K / 4.3 GB1150
...en2 7B Instruct 4.0bpw H6 EXL232K / 4.8 GB51

Qwen2 7B Alpacha Merged 4bit Parameters and Internals

LLM NameQwen2 7B Alpacha Merged 4bit
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Qwen2 7B Bnb 4bit   unsloth/Qwen2-7B-bnb-4bit
Merged ModelYes
Model Size7b
Required VRAM5.6 GB
Updated2024-06-24
Maintainerdbands
Model Typeqwen2
Model Files  4.5 GB: 1-of-2   1.1 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size152064
Initializer Range0.02
Torch Data Typebfloat16
Errorsreplace

What open-source LLMs or SLMs are you in search of? 34902 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801