What are the hardware requirements for Lila 103B L2?

Lila 103B L2 requires approximately 206.2 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Lila 103B L2 and how large is it?

Lila 103B L2 is developed by Sao10K, a model with 103b 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 Lila 103B L2?

Lila 103B L2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Lila 103B L2 by Sao10K — VRAM 206.2GB, 4K context

Name: Lila 103B L2
Author: Sao10K

Lila 103B L2 is an open-source language model by Sao10K. Features: 103b LLM, VRAM: 206.2GB, Context: 4K, License: cc-by-nc-4.0.

Autotrain compatible En Endpoints compatible License:cc-by-nc-4.0 Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Sao10K/Lila-103B-L2

Lila 103B L2 Parameters and Internals

LLM Name	Lila 103B L2
Repository 🤗	https://huggingface.co/Sao10K/Lila-103B-L2
Model Size	103b
Required VRAM	206.2 GB
Updated	2024-07-04
Maintainer	Sao10K
Model Type	llama
Model Files	9.8 GB: 1-of-21 10.0 GB: 2-of-21 9.8 GB: 3-of-21 9.8 GB: 4-of-21 9.6 GB: 5-of-21 9.7 GB: 6-of-21 9.6 GB: 7-of-21 9.6 GB: 8-of-21 10.0 GB: 9-of-21 9.6 GB: 10-of-21 9.8 GB: 11-of-21 9.8 GB: 12-of-21 10.0 GB: 13-of-21 10.0 GB: 14-of-21 9.9 GB: 15-of-21 9.9 GB: 16-of-21 9.8 GB: 17-of-21 9.9 GB: 18-of-21 9.8 GB: 19-of-21 10.0 GB: 20-of-21 9.8 GB: 21-of-21
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	cc-by-nc-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the Lila 103B L2 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

Quantized Models of the Lila 103B L2

Model	Likes	Downloads	VRAM
Lila 103B L2 GGUF	2	71	43 GB
Lila 103B L2 AWQ	1	9	54 GB
Lila 103B L2 GPTQ	1	8	52 GB

Best Alternatives to Lila 103B L2

Best Alternatives	Context / RAM	Downloads	Likes
Dark Miqu 103B	31K / 206.4 GB	30	2
BigWeave V15 103B	31K / 206.6 GB	85	2
Midnight Miqu 103B V1.5	31K / 206.4 GB	33	28
Midnight Miqu 103B V1.0	31K / 206.4 GB	85	16
Midnight Rose 103B V2.0.3	4K / 206.6 GB	93	13
OmegaDolphin 103B V0.1	4K / 175.6 GB	6	1
KitchenSink 103b	4K / 178.6 GB	13	9
Midnight Rose 103B V1.0	4K / 206.6 GB	11	3
Aurora Nights 103B V1.0	4K / 206.6 GB	6	14
Rogue Rose 103B V0.2	4K / 206.5 GB	12	33

Note: green Score (e.g. "73.2") means that the model is better than Sao10K/Lila-103B-L2.