RichardErkhov/Intel_-_tiny-random-llama2-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

tiny-random-llama2 - GGUF

• Model creator: https://huggingface.co/Intel/
• Original model: https://huggingface.co/Intel/tiny-random-llama2/

Name	Quant method	Size
tiny-random-llama2.Q2_K.gguf	Q2_K	0.01GB
tiny-random-llama2.IQ3_XS.gguf	IQ3_XS	0.01GB
tiny-random-llama2.IQ3_S.gguf	IQ3_S	0.01GB
tiny-random-llama2.Q3_K_S.gguf	Q3_K_S	0.01GB
tiny-random-llama2.IQ3_M.gguf	IQ3_M	0.01GB
tiny-random-llama2.Q3_K.gguf	Q3_K	0.01GB
tiny-random-llama2.Q3_K_M.gguf	Q3_K_M	0.01GB
tiny-random-llama2.Q3_K_L.gguf	Q3_K_L	0.01GB
tiny-random-llama2.IQ4_XS.gguf	IQ4_XS	0.01GB
tiny-random-llama2.Q4_0.gguf	Q4_0	0.01GB
tiny-random-llama2.IQ4_NL.gguf	IQ4_NL	0.01GB
tiny-random-llama2.Q4_K_S.gguf	Q4_K_S	0.01GB
tiny-random-llama2.Q4_K.gguf	Q4_K	0.01GB
tiny-random-llama2.Q4_K_M.gguf	Q4_K_M	0.01GB
tiny-random-llama2.Q4_1.gguf	Q4_1	0.01GB
tiny-random-llama2.Q5_0.gguf	Q5_0	0.01GB
tiny-random-llama2.Q5_K_S.gguf	Q5_K_S	0.01GB
tiny-random-llama2.Q5_K.gguf	Q5_K	0.01GB
tiny-random-llama2.Q5_K_M.gguf	Q5_K_M	0.01GB
tiny-random-llama2.Q5_1.gguf	Q5_1	0.01GB
tiny-random-llama2.Q6_K.gguf	Q6_K	0.01GB
tiny-random-llama2.Q8_0.gguf	Q8_0	0.02GB

Original model description:

library_name: transformers tags: []

Model Card for Model ID

This is a tiny random Llama model derived from "meta-llama/Llama-2-7b-hf".

This is useful for functional testing (not quality generation, since its weights are random)