JOSIE TinyLlama 1.1B 32K Base 4bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  JOSIE TinyLlama 1.1B 32K Base 4bit   URL Share it on

  4bit   Autotrain compatible Base model:doctor-shotgun/tiny... Base model:finetune:doctor-sho...   Endpoints compatible   Llama   Mlx   Quantized   Region:us   Safetensors

JOSIE TinyLlama 1.1B 32K Base 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

JOSIE TinyLlama 1.1B 32K Base 4bit Parameters and Internals

LLM NameJOSIE TinyLlama 1.1B 32K Base 4bit
Repository ๐Ÿค—https://huggingface.co/mlx-community/JOSIE-TinyLlama-1.1B-32k-base-4bit 
Base Model(s)  Doctor-Shotgun/TinyLlama-1.1B-32k   Doctor-Shotgun/TinyLlama-1.1B-32k
Model Size1.1b
Required VRAM0.6 GB
Updated2024-09-07
Maintainermlx-community
Model Typellama
Model Files  0.6 GB
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.39.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32024
Torch Data Typefloat16
JOSIE TinyLlama 1.1B 32K Base 4bit (mlx-community/JOSIE-TinyLlama-1.1B-32k-base-4bit)

Best Alternatives to JOSIE TinyLlama 1.1B 32K Base 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...E TinyLlama 1.1B 32K Base 8bit32K / 1.2 GB51
...1B 32K Instruct 8.0bpw H8 EXL232K / 1.2 GB41
...1B 32K Instruct 3.0bpw H6 EXL232K / 0.5 GB50
Athena TinyLlama V0.116K / 2.2 GB140
Tinyllama Coder Py V144K / 2.2 GB60
...lama PY CODER 4bit Lora 4k V124K / 2.2 GB60
TiamaPY V274K / 2.2 GB50
TiamaPY 1.1B V244K / 2.2 GB50
TinyDolphin 2.8 1.1B 4bit Mlx4K / 0.8 GB3841
Polka 1.1B Chat 8bpw EXL24K / 1.2 GB81
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/JOSIE-TinyLlama-1.1B-32k-base-4bit.

Rank the JOSIE TinyLlama 1.1B 32K Base 4bit 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? 35693 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803