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

Tangled Llama 33M 32K Base V0.1 by tangledgroup

 »  All LLMs  »  tangledgroup  »  Tangled Llama 33M 32K Base V0.1   URL Share it on

  21   
  Am   Ar   As   Az   Be   Bg   Bn   Br   Bs   Ca   Conversational   Cs   Cy   Da Dataset:ajibawa-2023/maths-col...   Dataset:arcee-ai/agent-data Dataset:badrex/llm-emoji-datas... Dataset:bigcode/programming-la... Dataset:bigcode/the-stack-smol... Dataset:cognitivecomputations/... Dataset:m-a-p/codefeedback-fil... Dataset:microsoft/orca-math-wo...   Dataset:mlabonne/finetome-100k   Dataset:nampdn-ai/tiny-codes Dataset:nampdn-ai/tiny-textboo...   Dataset:xu-song/cc100-samples   De   El   En   Endpoints compatible   Eo   Es   Et   Eu   Fa   Ff   Fi   Fr   Fy   Ga   Gd   Gl   Gn   Gu   Ha   He   Hi   Hr   Ht   Hu   Hy   Id   Ig   Is   It   Ja   Jv   Ka   Kk   Km   Kn   Ko   Ku   Ky   La   Lg   Li   Litdata   Litgpt   Ln   Lo   Lt   Lv   Mg   Mk   Ml   Mn   Mr   Ms   My   Ne   Nl   No   Ns   Om   Or   Pa   Pl   Ps   Pt   Qu   Region:us   Rm   Ro   Ru   Sa   Safetensors   Sc   Sd   Si   Sk   Sl   So   Sq   Sr   Ss   Su   Sv   Sw   Ta   Te   Th   Tl   Tn   Tr   Ug   Uk   Ur   Uz   Vi   Wo   Xh   Yi   Yo   Zu
Model Card on HF 🤗: https://huggingface.co/tangledgroup/tangled-llama-33m-32k-base-v0.1 

Tangled Llama 33M 32K Base V0.1 Benchmarks

LLME Score: 0.21959
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tangled Llama 33M 32K Base V0.1 (tangledgroup/tangled-llama-33m-32k-base-v0.1)

Tangled Llama 33M 32K Base V0.1 Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model aims to streamline the cognitive reasoning core by eliminating redundant knowledge.
Supported Languages 
en (yes), am (yes), ar (yes), as (yes), az (yes), be (yes), bg (yes), bn (yes), br (yes), bs (yes), ca (yes), cs (yes), cy (yes), da (yes), de (yes), el (yes), eo (yes), es (yes), et (yes), eu (yes), fa (yes), ff (yes), fi (yes), fr (yes), fy (yes), ga (yes), gd (yes), gl (yes), gn (yes), gu (yes), ha (yes), he (yes), hi (yes), hr (yes), ht (yes), hu (yes), hy (yes), id (yes), ig (yes), is (yes), it (yes), ja (yes), jv (yes), ka (yes), kk (yes), km (yes), kn (yes), ko (yes), ku (yes), ky (yes), la (yes), lg (yes), li (yes), ln (yes), lo (yes), lt (yes), lv (yes), mg (yes), mk (yes), ml (yes), mn (yes), mr (yes), ms (yes), my (yes), ne (yes), nl (yes), no (yes), ns (yes), om (yes), or (yes), pa (yes), pl (yes), ps (yes), pt (yes), qu (yes), rm (yes), ro (yes), ru (yes), sa (yes), si (yes), sc (yes), sd (yes), sk (yes), sl (yes), so (yes), sq (yes), sr (yes), ss (yes), su (yes), sv (yes), sw (yes), ta (yes), te (yes), th (yes), tl (yes), tn (yes), tr (yes), ug (yes), uk (yes), ur (yes), uz (yes), vi (yes), wo (yes), xh (yes), yi (yes), yo (yes), zu (yes)
Training Details 
Data Sources:
bigcode/programming-languages-keywords, bigcode/the-stack-smol-xs, nampdn-ai/tiny-textbooks, xu-song/cc100-samples, m-a-p/CodeFeedback-Filtered-Instruction, nampdn-ai/tiny-codes, ajibawa-2023/Maths-College, microsoft/orca-math-word-problems-200k, mlabonne/FineTome-100k, arcee-ai/agent-data, cognitivecomputations/SystemChat-2.0, badrex/llm-emoji-dataset
Data Volume:
9.7B tokens from over 5.2M dataset rows
Context Length:
32768
LLM NameTangled Llama 33M 32K Base V0.1
Repository 🤗https://huggingface.co/tangledgroup/tangled-llama-33m-32k-base-v0.1 
Model Size33m
Required VRAM0.1 GB
Updated2025-02-06
Maintainertangledgroup
Model Typellama
Model Files  0.1 GB
Supported Languagesen am ar as az be bg bn br bs ca cs cy da de el eo es et eu fa ff fi fr fy ga gd gl gn gu ha he hi hr ht hu hy id ig is it ja jv ka kk km kn ko ku ky la lg li ln lo lt lv mg mk ml mn mr ms my ne nl no ns om or pa pl ps pt qu rm ro ru sa si sc sd sk sl so sq sr ss su sv sw ta te th tl tn tr ug uk ur uz vi wo xh yi yo zu
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token</s>
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to Tangled Llama 33M 32K Base V0.1

Best Alternatives
Context / RAM
Downloads
Likes
ReflectionCoder DS 33B16K / 67 GB41824
Chronos Divergence 33B16K / 65 GB1929
Deepseek Wizard 33B Slerp16K / 35.3 GB90
ValidateAI 33B Slerp16K / 35.4 GB110
Deepseek Coder 33B Instruct16K / 66.5 GB14194483
WhiteRabbitNeo 33B V116K / 67 GB130384
ValidateAI 3 33B Ties16K / 66.5 GB70
ValidateAI 2 33B AT16K / 66.5 GB100
...dy Deepseekcoder 33B V16.1 32K16K / 67.1 GB14020
AutoCoder16K / 67 GB9795
Note: green Score (e.g. "73.2") means that the model is better than tangledgroup/tangled-llama-33m-32k-base-v0.1.

Rank the Tangled Llama 33M 32K Base 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? 42629 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