You can deploy this model and start earning money today!

RichardErkhov/
meditsolutions_-_MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune-gguf

Name: meditsolutions_-_MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune-gguf
Availability: InStock

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune - GGUF

Model creator: https://huggingface.co/meditsolutions/
Original model: https://huggingface.co/meditsolutions/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune/

Name	Quant method	Size
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q2_K.gguf	Q2_K	5.27GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q3_K_S.gguf	Q3_K_S	5.69GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q3_K.gguf	Q3_K	5.82GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q3_K_M.gguf	Q3_K_M	5.82GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q3_K_L.gguf	Q3_K_L	5.94GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.IQ4_XS.gguf	IQ4_XS	6.26GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q4_0.gguf	Q4_0	0.19GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.IQ4_NL.gguf	IQ4_NL	0.94GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q4_K_S.gguf	Q4_K_S	6.4GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q4_K.gguf	Q4_K	6.42GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q4_K_M.gguf	Q4_K_M	6.42GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q4_1.gguf	Q4_1	0.2GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q5_0.gguf	Q5_0	0.21GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q5_K_S.gguf	Q5_K_S	7.07GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q5_K.gguf	Q5_K	7.08GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q5_K_M.gguf	Q5_K_M	7.08GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q5_1.gguf	Q5_1	0.22GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q6_K.gguf	Q6_K	7.78GB
MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune.Q8_0.gguf	Q8_0	0.3GB

Original model description:

license: apache-2.0 base_model:

meditsolutions/MSH-v1-Bielik-v2.3-Instruct-MedIT-merge
speakleash/Bielik-11B-v2.3-Instruct pipeline_tag: text-generation tags:
medit-lite
model-pruning
text-generation language:
pl
en

Marsh Harrier Lite (MSH-Lite)

Marsh Harrier Lite (MSH-Lite) is a compact, efficient version of the MedIT Solutions MSH-v1-Bielik-v2.3-Instruct-MedIT-merge model, reduced to 7 billion parameters using advanced pruning techniques. This pruning retains the core functionality and efficiency of the original model while optimizing for reduced computational resource usage.

Key Features:

Pruned Model: Reduced from 11B to 7B parameters using the pruning method based on the MedIT Solutions LLaMA pruning framework.
Optimized Performance: Despite its reduced size, MSH-Lite delivers competitive performance across a wide array of NLP tasks.
Bilingual Support: Designed to handle both Polish (pl) and English (en) with high fluency.

Technical Details:

Base Model: MSH-v1-Bielik-v2.3-Instruct-MedIT-merge
Parameter Count: 7 billion
Architecture: Derived from Bielik's core architecture, with parameter optimization.
Model Efficiency: Ideal for deployments where computational efficiency is paramount.

Performance Highlights:

To be done.

Acknowledgments:

Gratitude to the SpeakLeash project and ACK Cyfronet AGH for their contributions and collaboration.

RichardErkhov/meditsolutions_-_MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune-gguf