You can deploy this model and start earning money today!

RichardErkhov/
martyn_-_llama2-megamerge-dare-13b-v1-gguf

Name: martyn_-_llama2-megamerge-dare-13b-v1-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama2-megamerge-dare-13b-v1 - GGUF

Model creator: https://huggingface.co/martyn/
Original model: https://huggingface.co/martyn/llama2-megamerge-dare-13b-v1/

Name	Quant method	Size
llama2-megamerge-dare-13b-v1.Q2_K.gguf	Q2_K	4.52GB
llama2-megamerge-dare-13b-v1.IQ3_XS.gguf	IQ3_XS	4.99GB
llama2-megamerge-dare-13b-v1.IQ3_S.gguf	IQ3_S	5.27GB
llama2-megamerge-dare-13b-v1.Q3_K_S.gguf	Q3_K_S	5.27GB
llama2-megamerge-dare-13b-v1.IQ3_M.gguf	IQ3_M	5.57GB
llama2-megamerge-dare-13b-v1.Q3_K.gguf	Q3_K	5.9GB
llama2-megamerge-dare-13b-v1.Q3_K_M.gguf	Q3_K_M	5.9GB
llama2-megamerge-dare-13b-v1.Q3_K_L.gguf	Q3_K_L	6.45GB
llama2-megamerge-dare-13b-v1.IQ4_XS.gguf	IQ4_XS	6.54GB
llama2-megamerge-dare-13b-v1.Q4_0.gguf	Q4_0	6.86GB
llama2-megamerge-dare-13b-v1.IQ4_NL.gguf	IQ4_NL	6.9GB
llama2-megamerge-dare-13b-v1.Q4_K_S.gguf	Q4_K_S	6.91GB
llama2-megamerge-dare-13b-v1.Q4_K.gguf	Q4_K	7.33GB
llama2-megamerge-dare-13b-v1.Q4_K_M.gguf	Q4_K_M	7.33GB
llama2-megamerge-dare-13b-v1.Q4_1.gguf	Q4_1	7.61GB
llama2-megamerge-dare-13b-v1.Q5_0.gguf	Q5_0	8.36GB
llama2-megamerge-dare-13b-v1.Q5_K_S.gguf	Q5_K_S	8.36GB
llama2-megamerge-dare-13b-v1.Q5_K.gguf	Q5_K	8.6GB
llama2-megamerge-dare-13b-v1.Q5_K_M.gguf	Q5_K_M	8.6GB
llama2-megamerge-dare-13b-v1.Q5_1.gguf	Q5_1	9.1GB
llama2-megamerge-dare-13b-v1.Q6_K.gguf	Q6_K	9.95GB
llama2-megamerge-dare-13b-v1.Q8_0.gguf	Q8_0	12.88GB

Original model description:

license: llama2 language:

en pipeline_tag: text-generation inference: false tags:
dare
super mario merge
pytorch
llama
llama-2
merge

llama 13b mega merge

The following were merged with hyperparams p=0.1 and lambda=2.

The first entry is the base model.

meta-llama/Llama-2-13b-hf
ajibawa-2023/Code-13B
migtissera/Synthia-13B
meta-math/MetaMath-13B-V1.0
FPHam/Sydney_Overthinker_13b_HF
allenai/tulu-2-dpo-13b
ajibawa-2023/Python-Code-13B
Doctor-Shotgun/cat-v1.0-13b
NeverSleep/Noromaid-13b-v0.1.1

Using https://github.com/martyn/safetensors-merge-supermario

RichardErkhov/martyn_-_llama2-megamerge-dare-13b-v1-gguf

Original model description:

llama 13b mega merge

RichardErkhov/
martyn_-_llama2-megamerge-dare-13b-v1-gguf