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

FineTome Llama3.2 1B 0929 by NotASI

 »  All LLMs  »  NotASI  »  FineTome Llama3.2 1B 0929   URL Share it on

  170   
  4bit   Autotrain compatible Base model:finetune:unsloth/ll... Base model:unsloth/llama-3.2-1...   Conversational   Dataset:mlabonne/finetome-100k   En   Endpoints compatible   Instruct   Llama   Llama-3   Model-index   Pytorch   Quantized   Region:us   Safetensors   Sft   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/NotASI/FineTome-Llama3.2-1B-0929 

FineTome Llama3.2 1B 0929 Benchmarks

MMLU Pro: 4.76
GPQA: 3.02
MUSR: 2.66
BBH: 5.74
IFEval: 39.91 vs 88 (so35)-54.6%
MATH Lvl 5: 1.28
LLME Score: 0.25836
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
FineTome Llama3.2 1B 0929 (NotASI/FineTome-Llama3.2-1B-0929)

FineTome Llama3.2 1B 0929 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Instructions for installing and running the model are provided, including dependencies and code samples. This model utilizes Unsloth for faster training and inference.
Training Details 
Data Sources:
mlabonne/FineTome-100k
Methodology:
This model was trained on mlabonne/FineTome-100k for 2 epochs with rslora + qlora, and achieved a final training loss of 0.796700. The model follows the same chat template as the base model one. This Llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Training Time:
2 epochs
LLM NameFineTome Llama3.2 1B 0929
Repository 🤗https://huggingface.co/NotASI/FineTome-Llama3.2-1B-0929 
Base Model(s)  unsloth/Llama-3.2-1B-Instruct-bnb-4bit   unsloth/Llama-3.2-1B-Instruct-bnb-4bit
Model Size1b
Required VRAM2.5 GB
Updated2025-02-05
MaintainerNotASI
Model Typellama
Instruction-BasedYes
Model Files  2.5 GB   2.5 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.45.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to FineTome Llama3.2 1B 0929

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 1B Instruct 4bit128K / 0.7 GB349122412
Llama 3.2 1B Instruct Bnb 4bit128K / 1 GB8850213
Llama Deepsync 1B128K / 2.5 GB3749
Orca Mini V9 5 1B Instruct128K / 2.5 GB3314
... Mini V9 5 1B Instruct Preview128K / 2.5 GB1382
Orca Mini V9 1 1B Instruct128K / 2.5 GB1483
...truct Gptqmodel 4bit Vortex V1128K / 1.6 GB1562
Llama SmolTalk 3.2 1B Instruct128K / 2.5 GB7188
Llama3.2 1b CoT128K / 2.5 GB1660
RP3 1B 1.0128K / 2.5 GB1251
Note: green Score (e.g. "73.2") means that the model is better than NotASI/FineTome-Llama3.2-1B-0929.

Rank the FineTome Llama3.2 1B 0929 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? 42577 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 v20241227
  Support LLM Explorer