What are the hardware requirements for Minicpm 2B Sft Bf16 Llamafied 16K?

Minicpm 2B Sft Bf16 Llamafied 16K requires approximately 6 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Minicpm 2B Sft Bf16 Llamafied 16K and how large is it?

Minicpm 2B Sft Bf16 Llamafied 16K is developed by NurtureAI, a model with 2b 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 Minicpm 2B Sft Bf16 Llamafied 16K?

Minicpm 2B Sft Bf16 Llamafied 16K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Minicpm 2B Sft Bf16 Llamafied 16K by NurtureAI — VRAM 6GB, 16K context

Name: Minicpm 2B Sft Bf16 Llamafied 16K
Author: NurtureAI

Minicpm 2B Sft Bf16 Llamafied 16K is an open-source language model by NurtureAI. Features: 2b LLM, VRAM: 6GB, Context: 16K, License: apache-2.0, LLM Explorer Score: 0.12.

Autotrain compatible Conversational En Endpoints compatible Llama Minicpm Modelbest Region:us Safetensors Sharded Tensorflow Thunlp Zh

Model Card on HF 🤗: https://huggingface.co/NurtureAI/minicpm-2b-sft-bf16-llamafied-16k

Minicpm 2B Sft Bf16 Llamafied 16K Parameters and Internals

Model Type

text generation, multimodal

Use Cases

Areas:

Research, Commercial applications

Applications:

Text generation, Code generation

Primary Use Cases:

Multimodal applications, Smartphone deployment

Limitations:

Model may experience hallucinations due to size, Prompt sensitivity, Inconsistent results

Considerations:

Evaluation and verifying output is the user's responsibility.

Additional Notes

MiniCPM's inference speed is significantly faster than human verbal speed when deployed on smartphones.

Supported Languages

en (Proficient), zh (Proficient)

Training Details

Methodology:

Special training methods include SFT and DPO on MiniCPM-2B. Parameter efficient finetuning can be conducted with low resource GPUs.

Input Output

Input Format:

Standard prompt input

Accepted Modalities:

text, image

Output Format:

text

Performance Tips:

Specify the data type in 'from_pretrained' to avoid computation errors.

LLM Name	Minicpm 2B Sft Bf16 Llamafied 16K
Repository 🤗	https://huggingface.co/NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
Model Size	2b
Required VRAM	6 GB
Updated	2024-12-08
Maintainer	NurtureAI
Model Type	llama
Model Files	5.0 GB: 1-of-2 1.0 GB: 2-of-2
Supported Languages	en zh
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	122753
Torch Data Type	bfloat16

Rank the Minicpm 2B Sft Bf16 Llamafied 16K 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 Minicpm 2B Sft Bf16 Llamafied 16K

Best Alternatives	Context / RAM	Downloads	Likes
Llama 2B Hf 32768 Fpf	32K / 3.8 GB	8	1
...de Toolcall Slm 2B Safetensors	8K / 3.4 GB	0	1
Aitana 2B SI Instruct	8K / 4.5 GB	52	0
Aitana 2B S Base IP 1.0	8K / 4.5 GB	186	0
Aitana 2B SI Instruct Aligned	8K / 4.5 GB	19	0
Aitana 2B S IP Instruct	8K / 4.5 GB	13	0
Aitana 2B S Instruct Aligned	8K / 6.9 GB	10	0
Aitana 2B S IP Base	8K / 4.5 GB	13	0
Salamandra 2B Fft Trenes	8K / 4.5 GB	32	0
SmolLM2 MedIT Upscale 2B	8K / 4.2 GB	6	5

Note: green Score (e.g. "73.2") means that the model is better than NurtureAI/minicpm-2b-sft-bf16-llamafied-16k.