mesolitica_-_tinyllama-1.1b-4096-fpf-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
mesolitica_-_tinyllama-1.1b-4096-fpf-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

tinyllama-1.1b-4096-fpf - GGUF

Model creator: https://huggingface.co/mesolitica/
Original model: https://huggingface.co/mesolitica/tinyllama-1.1b-4096-fpf/

Name	Quant method	Size
tinyllama-1.1b-4096-fpf.Q2_K.gguf	Q2_K	0.4GB
tinyllama-1.1b-4096-fpf.IQ3_XS.gguf	IQ3_XS	0.44GB
tinyllama-1.1b-4096-fpf.IQ3_S.gguf	IQ3_S	0.47GB
tinyllama-1.1b-4096-fpf.Q3_K_S.gguf	Q3_K_S	0.47GB
tinyllama-1.1b-4096-fpf.IQ3_M.gguf	IQ3_M	0.48GB
tinyllama-1.1b-4096-fpf.Q3_K.gguf	Q3_K	0.51GB
tinyllama-1.1b-4096-fpf.Q3_K_M.gguf	Q3_K_M	0.51GB
tinyllama-1.1b-4096-fpf.Q3_K_L.gguf	Q3_K_L	0.55GB
tinyllama-1.1b-4096-fpf.IQ4_XS.gguf	IQ4_XS	0.57GB
tinyllama-1.1b-4096-fpf.Q4_0.gguf	Q4_0	0.59GB
tinyllama-1.1b-4096-fpf.IQ4_NL.gguf	IQ4_NL	0.6GB
tinyllama-1.1b-4096-fpf.Q4_K_S.gguf	Q4_K_S	0.6GB
tinyllama-1.1b-4096-fpf.Q4_K.gguf	Q4_K	0.62GB
tinyllama-1.1b-4096-fpf.Q4_K_M.gguf	Q4_K_M	0.62GB
tinyllama-1.1b-4096-fpf.Q4_1.gguf	Q4_1	0.65GB
tinyllama-1.1b-4096-fpf.Q5_0.gguf	Q5_0	0.71GB
tinyllama-1.1b-4096-fpf.Q5_K_S.gguf	Q5_K_S	0.71GB
tinyllama-1.1b-4096-fpf.Q5_K.gguf	Q5_K	0.73GB
tinyllama-1.1b-4096-fpf.Q5_K_M.gguf	Q5_K_M	0.73GB
tinyllama-1.1b-4096-fpf.Q5_1.gguf	Q5_1	0.77GB
tinyllama-1.1b-4096-fpf.Q6_K.gguf	Q6_K	0.84GB
tinyllama-1.1b-4096-fpf.Q8_0.gguf	Q8_0	1.09GB

Original model description:

language:

ms

Full Parameter Finetuning TinyLlama-1.1B-intermediate-step-955k-2.0T 4096 context length Mistral on Malaysian text

README at https://github.com/mesolitica/malaya/tree/5.1/session/tiny-llama#4096-context-length

WandB, https://wandb.ai/mesolitica/finetune-tinyllama-1.1B?workspace=user-husein-mesolitica