JOSIE 1M Base by Isaak-Carter

 ยป  All LLMs  ยป  Isaak-Carter  ยป  JOSIE 1M Base   URL Share it on

  Autotrain compatible   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow

JOSIE 1M Base Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
JOSIE 1M Base (Goekdeniz-Guelmez/JOSIE_1M_base)

JOSIE 1M Base Parameters and Internals

Model Type 
auto-regressive language model
Additional Notes 
'Token' customized with a context length of 1 million tokens and new special & normal tokens added.
Training Details 
Data Sources:
Books3 filtered data
Data Volume:
800 subset of Books3 documents with 1M plus tokens
Context Length:
1000000
Model Architecture:
transformer
LLM NameJOSIE 1M Base
Repository ๐Ÿค—https://huggingface.co/Goekdeniz-Guelmez/JOSIE_1M_base 
Model Size1m
Required VRAM13.5 GB
Updated2024-12-17
MaintainerIsaak-Carter
Model Typellama
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   3.6 GB: 3-of-3
Model ArchitectureLlamaForCausalLM
Context Length1048576
Model Max Length1048576
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32019
Torch Data Typefloat16

Best Alternatives to JOSIE 1M Base

Best Alternatives
Context / RAM
Downloads
Likes
LWM Text Chat 1M1024K / 13.5 GB1651176
LWM Text 1M1024K / 13.5 GB155828
JOSIE 1M Base1024K / 13.5 GB61
Llama 3.2 1B128K / 2.5 GB10968231441
Llama 3.2 1B Instruct128K / 2.5 GB984114691
MiniThinky V2 1B Llama 3.2128K / 4.9 GB207124
Llama 3.2 1B Instruct128K / 2.5 GB6411156
Llama 3.2 1B128K / 2.5 GB8840925
Dolphin3.0 Llama3.2 1B128K / 2.5 GB394818
Orca Mini V9 6 1B Instruct128K / 2.5 GB413
Note: green Score (e.g. "73.2") means that the model is better than Goekdeniz-Guelmez/JOSIE_1M_base.

Rank the JOSIE 1M Base Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 41301 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227