What are the hardware requirements for JOSIE 1M Base?

JOSIE 1M Base requires approximately 13.5 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed JOSIE 1M Base and how large is it?

JOSIE 1M Base is developed by Isaak-Carter, a model with 1m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate JOSIE 1M Base?

JOSIE 1M Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

JOSIE 1M Base by Isaak-Carter — VRAM 13.5GB, 1024K context

Name: JOSIE 1M Base
Author: Isaak-Carter

JOSIE 1M Base is an open-source language model by Isaak-Carter. Features: 1m LLM, VRAM: 13.5GB, Context: 1024K, LLM Explorer Score: 0.11.

Autotrain compatible Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/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 Name	JOSIE 1M Base
Repository 🤗	https://huggingface.co/Goekdeniz-Guelmez/JOSIE_1M_base
Model Size	1m
Required VRAM	13.5 GB
Updated	2024-12-17
Maintainer	Isaak-Carter
Model Type	llama
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 3.6 GB: 3-of-3
Model Architecture	LlamaForCausalLM
Context Length	1048576
Model Max Length	1048576
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32019
Torch Data Type	float16

Rank the JOSIE 1M Base capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to JOSIE 1M Base

Best Alternatives	Context / RAM	Downloads	Likes
ISA 02 Nano Llama 3.2 1B	1024K / 2.5 GB	47	3
LWM Text 1M	1024K / 13.5 GB	1149	29
LWM Text Chat 1M	1024K / 13.5 GB	57	173
JOSIE 1M Base	1024K / 13.5 GB	6	1
MiniCPM5 1B MegaMerge Final	512K / 2.2 GB	0	1
MiniCPM5 1B	128K / 2.2 GB	354385	868
Llama 3.2 1B Instruct	128K / 2.5 GB	212072	100
...1B Claude Opus Fable5 Thinking	128K / 2.2 GB	6165	166
Llama 3.2 1B Instruct	128K / 2.5 GB	10114634	1549
LlaMa3.2 1B Instruct	128K / 4.9 GB	14	0

Note: green Score (e.g. "73.2") means that the model is better than Goekdeniz-Guelmez/JOSIE_1M_base.