It 5.2 Fp16 Cp by Vikhrmodels

 ยป  All LLMs  ยป  Vikhrmodels  ยป  It 5.2 Fp16 Cp   URL Share it on

  Arxiv:2405.13929   Autotrain compatible   Conversational   En   Endpoints compatible   Fp16   Llama   Quantized   Region:us   Ru   Safetensors   Sharded   Tensorflow

It 5.2 Fp16 Cp Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
It 5.2 Fp16 Cp (Vikhrmodels/it-5.2-fp16-cp)

It 5.2 Fp16 Cp Parameters and Internals

Model Type 
text generation
Supported Languages 
ru (Russian), en (English)
Release Notes 
Version:
0.5
Notes:
Added a lot more data to sft, now json and multiturn work more stable on long context and hard prompts.
LLM NameIt 5.2 Fp16 Cp
Repository ๐Ÿค—https://huggingface.co/Vikhrmodels/it-5.2-fp16-cp 
Model Size7.6b
Required VRAM15.2 GB
Updated2025-02-05
MaintainerVikhrmodels
Model Typellama
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.7 GB: 3-of-4   0.6 GB: 4-of-4
Supported Languagesru en
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size79097
Torch Data Typefloat16

Best Alternatives to It 5.2 Fp16 Cp

Best Alternatives
Context / RAM
Downloads
Likes
It 5.4 Fp16 Orpo V232K / 15.2 GB467
It 5.3 Fp16 32K32K / 15.2 GB410
It 5.3 Fp1632K / 15.2 GB00

Rank the It 5.2 Fp16 Cp 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