Qwen Qwen1.5 7B 1720559943 by jfranklin-foundry

 ยป  All LLMs  ยป  jfranklin-foundry  ยป  Qwen Qwen1.5 7B 1720559943   URL Share it on

  Arxiv:1910.09700   Adapter   Base model:qwen/qwen1.5-7b   Finetuned   Lora   Peft   Region:us   Safetensors

Rank the Qwen Qwen1.5 7B 1720559943 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  
Qwen Qwen1.5 7B 1720559943 (jfranklin-foundry/Qwen-Qwen1.5-7B-1720559943)

Best Alternatives to Qwen Qwen1.5 7B 1720559943

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
...1 Fine Tuned Using Ludwig 4bit60.10K / 0 GB41
Dragoman60.10K / 2.7 GB25710
Mistral Chess60.10K / 2.7 GB1010
Mistral Finetuned DialogSumm47.90K / 0 GB11
...1 Fine Tuned Using Ludwig 4bit40.40K / 0 GB11
Falcon 7B Chat V0.10K / 0 GB6844
...l Alpaca Oa Codealpaca Lora 7B0K / 0 GB039
Bode 7B Alpaca Pt Br0K / 0 GB50137
Llama 7b Ru Turbo Alpaca Lora0K / 0 GB029
Alpaca Lora Ptbr 7B0K / 0 GB1823
Note: green Score (e.g. "73.2") means that the model is better than jfranklin-foundry/Qwen-Qwen1.5-7B-1720559943.

Qwen Qwen1.5 7B 1720559943 Parameters and Internals

LLM NameQwen Qwen1.5 7B 1720559943
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Qwen1.5 7B   Qwen/Qwen1.5-7B
Model Size7b
Required VRAM0 GB
Updated2024-07-13
Maintainerjfranklin-foundry
Model Files  0.0 GB   0.0 GB
Model ArchitectureAdapter
Model Max Length32768
Is Biasednone
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|v_proj
LoRA Alpha8
LoRA Dropout0.1
R Param4
Errorsreplace

What open-source LLMs or SLMs are you in search of? 36243 in total.

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