Modelpublic

RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes515downloads

Model Card

Quantization made by Richard Erkhov.

illuni-llama-2-ko-7b-test - GGUF

Name	Quant method	Size
illuni-llama-2-ko-7b-test.Q2_K.gguf	Q2_K	2.42GB
illuni-llama-2-ko-7b-test.IQ3_XS.gguf	IQ3_XS	2.67GB
illuni-llama-2-ko-7b-test.IQ3_S.gguf	IQ3_S	2.81GB
illuni-llama-2-ko-7b-test.Q3_K_S.gguf	Q3KS	2.81GB
illuni-llama-2-ko-7b-test.IQ3_M.gguf	IQ3_M	2.97GB
illuni-llama-2-ko-7b-test.Q3_K.gguf	Q3_K	3.14GB
illuni-llama-2-ko-7b-test.Q3_K_M.gguf	Q3KM	3.14GB
illuni-llama-2-ko-7b-test.Q3_K_L.gguf	Q3KL	3.42GB
illuni-llama-2-ko-7b-test.IQ4_XS.gguf	IQ4_XS	3.47GB
illuni-llama-2-ko-7b-test.Q4_0.gguf	Q4_0	3.64GB
illuni-llama-2-ko-7b-test.IQ4_NL.gguf	IQ4_NL	3.66GB
illuni-llama-2-ko-7b-test.Q4_K_S.gguf	Q4KS	3.67GB
illuni-llama-2-ko-7b-test.Q4_K.gguf	Q4_K	3.88GB
illuni-llama-2-ko-7b-test.Q4_K_M.gguf	Q4KM	3.88GB
illuni-llama-2-ko-7b-test.Q4_1.gguf	Q4_1	4.03GB
illuni-llama-2-ko-7b-test.Q5_0.gguf	Q5_0	4.42GB
illuni-llama-2-ko-7b-test.Q5_K_S.gguf	Q5KS	4.42GB
illuni-llama-2-ko-7b-test.Q5_K.gguf	Q5_K	4.54GB
illuni-llama-2-ko-7b-test.Q5_K_M.gguf	Q5KM	4.54GB
illuni-llama-2-ko-7b-test.Q5_1.gguf	Q5_1	4.8GB
illuni-llama-2-ko-7b-test.Q6_K.gguf	Q6_K	5.24GB

Original model description: --- language:

—ko basemodel: beomi/llama-2-ko-7b license: mit pipelinetag: question-answering tags:
—instruct
—instruction
—llama-2 ---

llama2-7b

<usr>
{Instruction}

<bot>
{Answer}