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

Candle TinyLlama 1.1B Chat V1.0 by DanielClough

 »  All LLMs  »  DanielClough  »  Candle TinyLlama 1.1B Chat V1.0   URL Share it on

  11   
  Autotrain compatible Dataset:tinyllama/tinyllama-1....   En   Endpoints compatible   Gguf   Llama   Q4   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DanielClough/Candle_TinyLlama-1.1B-Chat-v1.0 

Candle TinyLlama 1.1B Chat V1.0 Benchmarks

ARC: 33.19 vs 96.7 (so35)-65.7%
HellaSwag: 58.58 vs 95.3 (gpt4)-38.5%
MMLU: 25.21 vs 88.3 (so35)-71.4%
TruthfulQA: 35.82 vs 59 (gpt4)-39.3%
WinoGrande: 58.8 vs 87.5 (gpt4)-32.8%
GSM8K: 1.59 vs 96.4 (so35)-98.4%
LLME Score: 0.20668
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Candle TinyLlama 1.1B Chat V1.0 (DanielClough/Candle_TinyLlama-1.1B-Chat-v1.0)

Candle TinyLlama 1.1B Chat V1.0 Parameters and Internals

Model Type 
text-generation
Additional Notes 
This repo includes `.gguf` built for HuggingFace/Candle. Note: They will not work with `llama.cpp`.
Supported Languages 
language_en (proficient)
LLM NameCandle TinyLlama 1.1B Chat V1.0
Repository 🤗https://huggingface.co/DanielClough/Candle_TinyLlama-1.1B-Chat-v1.0 
Base Model(s)  Sft Tiny Chatbot   snshrivas10/sft-tiny-chatbot
Model Size1.1b
Required VRAM2.2 GB
Updated2025-02-05
MaintainerDanielClough
Model Typellama
Model Files  2.2 GB   0.4 GB   0.5 GB   0.6 GB   0.7 GB   0.6 GB   0.8 GB   0.8 GB   0.8 GB   0.9 GB   1.2 GB   1.2 GB   1.3 GB   2.2 GB: 1-of-1
Supported Languagesen
GGUF QuantizationYes
Quantization Typeq4|gguf
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.35.0
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Candle TinyLlama 1.1B Chat V1.0

Best Alternatives
Context / RAM
Downloads
Likes
TinyllamaMix 1.1B32K / 2.2 GB1462
Palmer 004 240632K / 2.2 GB5740
Palmer 00432K / 2.2 GB441
TinyLlama 1.1B 32K GGUF32K / 0.5 GB1000
Tinyllama Coder Py V134K / 0.7 GB1910
Tinyllama Coder Py V124K / 0.7 GB1900
Tinyllama Coder Py 4bit V104K / 0.7 GB1820
Tinyllama Coder Py 4bit V34K / 1.2 GB1260
Tinyllama Coder Py 4bit V44K / 1.2 GB1050
...llama PY CODER 4bit Lora 4k V54K / 0.7 GB1180
Note: green Score (e.g. "73.2") means that the model is better than DanielClough/Candle_TinyLlama-1.1B-Chat-v1.0.

Rank the Candle TinyLlama 1.1B Chat V1.0 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