You can deploy this model and start earning money today!

RichardErkhov/
MiniLLM_-_MiniPLM-Qwen-1.2B-gguf

Name: MiniLLM_-_MiniPLM-Qwen-1.2B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MiniPLM-Qwen-1.2B - GGUF

Model creator: https://huggingface.co/MiniLLM/
Original model: https://huggingface.co/MiniLLM/MiniPLM-Qwen-1.2B/

Name	Quant method	Size
MiniPLM-Qwen-1.2B.Q2_K.gguf	Q2_K	0.51GB
MiniPLM-Qwen-1.2B.Q3_K_S.gguf	Q3_K_S	0.57GB
MiniPLM-Qwen-1.2B.Q3_K.gguf	Q3_K	0.61GB
MiniPLM-Qwen-1.2B.Q3_K_M.gguf	Q3_K_M	0.61GB
MiniPLM-Qwen-1.2B.Q3_K_L.gguf	Q3_K_L	0.63GB
MiniPLM-Qwen-1.2B.IQ4_XS.gguf	IQ4_XS	0.65GB
MiniPLM-Qwen-1.2B.Q4_0.gguf	Q4_0	0.67GB
MiniPLM-Qwen-1.2B.IQ4_NL.gguf	IQ4_NL	0.67GB
MiniPLM-Qwen-1.2B.Q4_K_S.gguf	Q4_K_S	0.69GB
MiniPLM-Qwen-1.2B.Q4_K.gguf	Q4_K	0.72GB
MiniPLM-Qwen-1.2B.Q4_K_M.gguf	Q4_K_M	0.72GB
MiniPLM-Qwen-1.2B.Q4_1.gguf	Q4_1	0.72GB
MiniPLM-Qwen-1.2B.Q5_0.gguf	Q5_0	0.78GB
MiniPLM-Qwen-1.2B.Q5_K_S.gguf	Q5_K_S	0.79GB
MiniPLM-Qwen-1.2B.Q5_K.gguf	Q5_K	0.81GB
MiniPLM-Qwen-1.2B.Q5_K_M.gguf	Q5_K_M	0.81GB
MiniPLM-Qwen-1.2B.Q5_1.gguf	Q5_1	0.83GB
MiniPLM-Qwen-1.2B.Q6_K.gguf	Q6_K	0.93GB
MiniPLM-Qwen-1.2B.Q8_0.gguf	Q8_0	1.15GB

Original model description:

library_name: transformers license: apache-2.0 datasets:

monology/pile-uncopyrighted
MiniLLM/pile-diff_samp-qwen_1.8B-qwen_104M-r0.5 language:
en metrics:
accuracy pipeline_tag: text-generation

MinPLM-Qwen-1.2B

paper | code

MiniPLM-Qwen-1.2B is a 1.2B model with Qwen achitecture pre-trained from scratch on the Pile using the MiniPLM knowledge distillation framework with the offcial QWen1.5-1.8B as the teacher model.

We also open-source the pre-training corpus refined by Difference Sampling in MiniPLM for reproducibility.

Evaluation

MiniPLM models achieves better performance given the same computation and scales well across model sizes:

Baseline Models

Citation

bibtext

@article{miniplm,
    title={MiniPLM: Knowledge Distillation for Pre-Training Language Models}, 
    author={Yuxian Gu and Hao Zhou and Fandong Meng and Jie Zhou and Minlie Huang},
    journal={arXiv preprint arXiv:2410.17215},
    year={2024}
}

RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf