What are the hardware requirements for InternLM2 Math Plus 7B 4bit?

InternLM2 Math Plus 7B 4bit requires approximately 5.2 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed InternLM2 Math Plus 7B 4bit and how large is it?

InternLM2 Math Plus 7B 4bit is developed by lee-ite, a model with 7b 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 InternLM2 Math Plus 7B 4bit?

InternLM2 Math Plus 7B 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

InternLM2 Math Plus 7B 4bit by lee-ite — VRAM 5.2GB, 8K context

Name: InternLM2 Math Plus 7B 4bit
Author: lee-ite

InternLM2 Math Plus 7B 4bit is an open-source language model by lee-ite. Features: 7b LLM, VRAM: 5.2GB, Context: 8K, License: apache-2.0, Quantized.

Arxiv:2402.06332 4-bit 4bit Awq Conversational Custom code En Feature-extraction Internlm2 License:apache-2.0 Math Pytorch Quantized Region:us Sharded Zh

Model Card on HF 🤗: https://huggingface.co/lee-ite/InternLM2-Math-Plus-7B-4bit

InternLM2 Math Plus 7B 4bit Parameters and Internals

LLM Name	InternLM2 Math Plus 7B 4bit
Repository 🤗	https://huggingface.co/lee-ite/InternLM2-Math-Plus-7B-4bit
Base Model(s)	Internlm2 Math Plus 7B internlm/internlm2-math-plus-7b
Model Size	7b
Required VRAM	5.2 GB
Updated	2024-07-04
Maintainer	lee-ite
Model Type	internlm2
Model Files	2.0 GB: 1-of-3 2.0 GB: 2-of-3 1.2 GB: 3-of-3
Supported Languages	en zh
Quantization Type	4bit
Model Architecture	InternLM2ForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.41.1
Is Biased	0
Tokenizer Class	InternLM2Tokenizer
Padding Token	</s>
Vocabulary Size	92544
Torch Data Type	float16

Rank the InternLM2 Math Plus 7B 4bit 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 InternLM2 Math Plus 7B 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Internlm2 5 7B Chat 8bit	32K / 8.2 GB	103	3
Internlm2 5 7B Chat 4bit	32K / 5.2 GB	75	5
Internlm2 5 7B Chat 4bit	32K / 4.3 GB	15	2
Internlm2 5 7B	256K / 15.5 GB	3236	18
Internlm2 5 7B Chat 1M	256K / 15.4 GB	396	72
Internlm2 5 7B Chat	32K / 15.4 GB	132413	201
Internlm2 7B	32K / 15.5 GB	23773	43
ChemLLM 7B Chat 1 5 SFT	32K / 15.4 GB	4796	6
Internlm2 Chat 7B	32K / 15.4 GB	68687	83
Internlm2 Base 7B	32K / 15.5 GB	19872	10

Note: green Score (e.g. "73.2") means that the model is better than lee-ite/InternLM2-Math-Plus-7B-4bit.