Llama 3.2 3B Sft 2 by tanliboy

 ยป  All LLMs  ยป  tanliboy  ยป  Llama 3.2 3B Sft 2   URL Share it on

  Alignment-handbook   Autotrain compatible Base model:finetune:tanliboy/l... Base model:tanliboy/llama-3.2-...   Conversational Dataset:tanliboy/openhermes-2....   Endpoints compatible   Generated from trainer   Llama   Region:us   Safetensors   Sft   Sharded   Tensorboard   Tensorflow   Trl

Llama 3.2 3B Sft 2 Benchmarks

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

Llama 3.2 3B Sft 2 Parameters and Internals

LLM NameLlama 3.2 3B Sft 2
Repository ๐Ÿค—https://huggingface.co/tanliboy/llama-3.2-3b-sft-2 
Base Model(s)  tanliboy/llama-3.2-3b   tanliboy/llama-3.2-3b
Model Size3b
Required VRAM6.5 GB
Updated2024-10-11
Maintainertanliboy
Model Typellama
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2   0.0 GB
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16
Llama 3.2 3B Sft 2 (tanliboy/llama-3.2-3b-sft-2)

Best Alternatives to Llama 3.2 3B Sft 2

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB280617309
Llama 3.2 3B128K / 6.5 GB71701174
Llama 3.2 Korean Bllossom 3B128K / 6.5 GB29821
Llama 3.2 3B Instruct128K / 6.4 GB1812916
Impish LLAMA 3B128K / 6.5 GB649
Llama 3.2 3B128K / 6.4 GB50015
...kbricks Llama3.2 Korean Cpt 3B128K / 7.2 GB5772
Llama 3.2 3B Instruct128K / 6.5 GB10822
Llama3.2 3B Enigma128K / 12.8 GB906
Magistrate 3.2 3B Base128K / 6.5 GB4211
Note: green Score (e.g. "73.2") means that the model is better than tanliboy/llama-3.2-3b-sft-2.

Rank the Llama 3.2 3B Sft 2 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? 36726 in total.

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