V3 by hieunguyenminh

 ยป  All LLMs  ยป  hieunguyenminh  ยป  V3   URL Share it on

  4-bit   Autotrain compatible Base model:thebloke/mistral-7b...   Conversational Dataset:hieunguyenminh/rolepla...   Endpoints compatible   Generated from trainer   Gptq   Instruct   License:apache-2.0   Lora   Mistral   Quantized   Region:us   Safetensors   Sft   Tensorboard   Trl

V3 Benchmarks

Rank the V3 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  
V3 (hieunguyenminh/v3)

Best Alternatives to V3

Best Alternatives
HF Rank
Mistral 7B Instruct 4bit0K / 0.2 GB210
Legaleval Mistral 4bit Adapter0K / 0.2 GB70
... F16 Finetuned Therapy Chatbot0K / 0.3 GB80
Unsloth Vinallama0K / 14.4 GB250
...ral 7B Stepback Prompt Unsloth0K / 14.4 GB210
Full V4 Astromistral Final32K / 4.5 GB120
...B Instruct Finetuning Japanese0K / 0 GB260
Stuco Task Generator0K / 0 GB190
...ral 7B Instruct V0.2 Jawakrama0K / 0 GB130
...ama2 Finetuned Spiderdata Copy0K / 0 GB50

V3 Parameters and Internals

LLM NameV3
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Mistral 7B Instruct V0.2 GPTQ   TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
Model Size7b
Required VRAM0 GB
Model Files  0.0 GB   0.0 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureAutoModelForCausalLM
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token</s>
LoRA ModelYes
PEFT Target Modulesv_proj|q_proj
LoRA Alpha16
LoRA Dropout0.05
R Param16

What open-source LLMs or SLMs are you in search of? 36560 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024040901