Vikhrmodels Vikhr 7B Instruct 0.4 4bits by RichardErkhov

 ยป  All LLMs  ยป  RichardErkhov  ยป  Vikhrmodels Vikhr 7B Instruct 0.4 4bits   URL Share it on

  4-bit   Autotrain compatible   Bitsandbytes   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow

Vikhrmodels Vikhr 7B Instruct 0.4 4bits Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Vikhrmodels Vikhr 7B Instruct 0.4 4bits Parameters and Internals

LLM NameVikhrmodels Vikhr 7B Instruct 0.4 4bits
Repository ๐Ÿค—https://huggingface.co/RichardErkhov/Vikhrmodels_-_Vikhr-7B-instruct_0.4-4bits 
Model Size7b
Required VRAM5.2 GB
Updated2024-09-07
MaintainerRichardErkhov
Model Typellama
Instruction-BasedYes
Model Files  4.6 GB: 1-of-2   0.6 GB: 2-of-2
Model ArchitectureLlamaForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size79099
Torch Data Typefloat16
Vikhrmodels Vikhr 7B Instruct 0.4 4bits (RichardErkhov/Vikhrmodels_-_Vikhr-7B-instruct_0.4-4bits)

Best Alternatives to Vikhrmodels Vikhr 7B Instruct 0.4 4bits

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2 7B 32K Instruct32K / 13.5 GB12856160
Qwen2 7B Instruct Llama32K / 15.2 GB42
Qwen2 7B Instruct Mistral32K / 15.2 GB51
AIRIC The Mistral32K / 14.4 GB6757
Vikhr 7B Instruct 0.332K / 14.6 GB394
... Samantha Philosopher 7B Slerp32K / 13.4 GB42
Vikhr 7B Instruct Merged32K / 14.6 GB44
Clinical Ehr Prototype 0.132K / 14.4 GB142
...stral 7B Instruct V0.1 Sharded32K / 14.4 GB154413
... Llama2 7B 32K Instructions V232K / 13.5 GB141
Note: green Score (e.g. "73.2") means that the model is better than RichardErkhov/Vikhrmodels_-_Vikhr-7B-instruct_0.4-4bits.

Rank the Vikhrmodels Vikhr 7B Instruct 0.4 4bits 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? 35693 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803