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

Tinyllama Coder Py 4bit V10 by Ramikan-BR

 »  All LLMs  »  Ramikan-BR  »  Tinyllama Coder Py 4bit V10   URL Share it on

  91   
  4bit   Autotrain compatible Base model:adapter:unsloth/tin... Base model:unsloth/tinyllama-c...   Code   Codegen   Conversational Dataset:ramikan-br/data-oss in...   En   Endpoints compatible   Gguf   Instruct   Llama   Lora   Peft   Quantized   Region:us   Safetensors   Sft   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Ramikan-BR/tinyllama-coder-py-4bit-v10 

Tinyllama Coder Py 4bit V10 Benchmarks

ARC: 34.39 vs 96.7 (so35)-64.4%
HellaSwag: 56.34 vs 95.3 (gpt4)-40.9%
MMLU: 26.42 vs 88.3 (so35)-70.1%
TruthfulQA: 38.45 vs 59 (gpt4)-34.8%
WinoGrande: 58.09 vs 87.5 (gpt4)-33.6%
GSM8K: 0.53 vs 96.4 (so35)-99.5%
LLME Score: 0.24671
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tinyllama Coder Py 4bit V10 (Ramikan-BR/tinyllama-coder-py-4bit-v10)

Tinyllama Coder Py 4bit V10 Parameters and Internals

Model Type 
text-generation, Python Coder
Additional Notes 
The model was refined using Unsloath. The dataset ise-uiuc/Magicoder-OSS-Instruct-75K was adjusted, leaving only data on Python and divided into 10 parts, each refinement occurred for 2 epochs, using Adafactor optimizer or AdamW_8bit (Adafactor seems to deliver less loss).
Supported Languages 
en (NLP)
Training Details 
Data Sources:
Ramikan-BR/data-oss_instruct-decontaminated_python.jsonl
Methodology:
The model was refined using Unsloath.
LLM NameTinyllama Coder Py 4bit V10
Repository 🤗https://huggingface.co/Ramikan-BR/tinyllama-coder-py-4bit-v10 
Base Model(s)  Tinyllama Chat Bnb 4bit   unsloth/tinyllama-chat-bnb-4bit
Model Size1.1b
Required VRAM0.7 GB
Updated2024-12-21
MaintainerRamikan-BR
Model Typellama
Instruction-BasedYes
Model Files  2.2 GB   2.2 GB   0.7 GB   1.2 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|4bit
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Rank the Tinyllama Coder Py 4bit V10 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? 40013 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 v20241217
  Support LLM Explorer