RichardErkhov/Delcos_-_Starling-LM-11B-alpha-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Starling-LM-11B-alpha - GGUF

• Model creator: https://huggingface.co/Delcos/
• Original model: https://huggingface.co/Delcos/Starling-LM-11B-alpha/

Name	Quant method	Size
Starling-LM-11B-alpha.Q2_K.gguf	Q2_K	3.95GB
Starling-LM-11B-alpha.IQ3_XS.gguf	IQ3_XS	4.39GB
Starling-LM-11B-alpha.IQ3_S.gguf	IQ3_S	4.63GB
Starling-LM-11B-alpha.Q3_K_S.gguf	Q3_K_S	4.61GB
Starling-LM-11B-alpha.IQ3_M.gguf	IQ3_M	4.78GB
Starling-LM-11B-alpha.Q3_K.gguf	Q3_K	5.13GB
Starling-LM-11B-alpha.Q3_K_M.gguf	Q3_K_M	5.13GB
Starling-LM-11B-alpha.Q3_K_L.gguf	Q3_K_L	5.58GB
Starling-LM-11B-alpha.IQ4_XS.gguf	IQ4_XS	5.75GB
Starling-LM-11B-alpha.Q4_0.gguf	Q4_0	6.0GB
Starling-LM-11B-alpha.IQ4_NL.gguf	IQ4_NL	6.06GB
Starling-LM-11B-alpha.Q4_K_S.gguf	Q4_K_S	6.04GB
Starling-LM-11B-alpha.Q4_K.gguf	Q4_K	6.38GB
Starling-LM-11B-alpha.Q4_K_M.gguf	Q4_K_M	6.38GB
Starling-LM-11B-alpha.Q4_1.gguf	Q4_1	6.65GB
Starling-LM-11B-alpha.Q5_0.gguf	Q5_0	7.31GB
Starling-LM-11B-alpha.Q5_K_S.gguf	Q5_K_S	7.31GB
Starling-LM-11B-alpha.Q5_K.gguf	Q5_K	7.5GB
Starling-LM-11B-alpha.Q5_K_M.gguf	Q5_K_M	7.5GB
Starling-LM-11B-alpha.Q5_1.gguf	Q5_1	7.96GB
Starling-LM-11B-alpha.Q6_K.gguf	Q6_K	8.7GB
Starling-LM-11B-alpha.Q8_0.gguf	Q8_0	11.27GB

Original model description:

license: cc-by-nc-nd-4.0 language: - en library_name: transformers pipeline_tag: text-generation tags: - starling - mistral

Starling, now with more parameters.

This is the 11b version of Starling. More details soon.

PENDING

Description:

PENDING

Uncensored

Main Goals:

Prompt Template:

For optimal interaction, use this template:

Recommended Settings:

Benchmarks:

PENDING

Training Data:

PENDING