LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Reasoning Llama 3B V0.1 by KingNish

 »  All LLMs  »  KingNish  »  Reasoning Llama 3B V0.1   URL Share it on

  216   
  4bit   Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Conversational Dataset:kingnish/reasoning-bas...   En   Endpoints compatible   Instruct   Llama   Llama-3   Pytorch   Quantized   Reasoning   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/KingNish/Reasoning-Llama-3b-v0.1 

Reasoning Llama 3B V0.1 Benchmarks

LLME Score: 0.26372
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Reasoning Llama 3B V0.1 Parameters and Internals

Model Type 
text generation, reasoning
Additional Notes 
First iteration of the model. Primarily for testing and fine-tuned on a smaller dataset.
Supported Languages 
en (native)
Training Details 
Data Sources:
KingNish/reasoning-base-20k
Data Volume:
10k rows
Methodology:
Finetuning with TRL and Unsloth
Input Output 
Input Format:
Chat template with messages including role and content
Accepted Modalities:
text
Output Format:
Text generation
LLM NameReasoning Llama 3B V0.1
Repository 🤗https://huggingface.co/KingNish/Reasoning-Llama-3b-v0.1 
Base Model(s)  meta-llama/Llama-3.2-3B-Instruct   meta-llama/Llama-3.2-3B-Instruct
Model Size3b
Required VRAM6.5 GB
Updated2024-12-02
MaintainerKingNish
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2   5.0 GB: 1-of-2   1.5 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
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 Typefloat16
Reasoning Llama 3B V0.1 (KingNish/Reasoning-Llama-3b-v0.1)

Best Alternatives to Reasoning Llama 3B V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct Bnb 4bit128K / 2.2 GB21806515
Llama Magpie 3.2 3B Instruct128K / 6.5 GB327
Llama 3.2 3B Instruct 4bit128K / 1.8 GB3527119
Llama Sentient 3.2 3B Instruct128K / 6.5 GB3359
...truct Gptqmodel 4bit Vortex V3128K / 3.2 GB16403
...Llama 3.2 3B Instruct Bnb 4bit128K / 6.5 GB531
Llama 3.2 3B Overthinker128K / 6.5 GB27218
TaraV1 M16B128K / 6.5 GB6240
...nstruct Medical Conversational128K / 6.5 GB10386
ISLEXITAS WELSPUN 7L 29 11 24128K / 6.5 GB250
Note: green Score (e.g. "73.2") means that the model is better than KingNish/Reasoning-Llama-3b-v0.1.

Rank the Reasoning Llama 3B V0.1 Capabilities

🆘 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! 🌟

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? 38765 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer