Fischerboot_-_merge-of-the-2b-llama-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
Fischerboot_-_merge-of-the-2b-llama-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

merge-of-the-2b-llama - GGUF

Model creator: https://huggingface.co/Fischerboot/
Original model: https://huggingface.co/Fischerboot/merge-of-the-2b-llama/

Name	Quant method	Size
merge-of-the-2b-llama.Q2_K.gguf	Q2_K	0.73GB
merge-of-the-2b-llama.IQ3_XS.gguf	IQ3_XS	0.81GB
merge-of-the-2b-llama.IQ3_S.gguf	IQ3_S	0.86GB
merge-of-the-2b-llama.Q3_K_S.gguf	Q3_K_S	0.85GB
merge-of-the-2b-llama.IQ3_M.gguf	IQ3_M	0.89GB
merge-of-the-2b-llama.Q3_K.gguf	Q3_K	0.94GB
merge-of-the-2b-llama.Q3_K_M.gguf	Q3_K_M	0.94GB
merge-of-the-2b-llama.Q3_K_L.gguf	Q3_K_L	1.02GB
merge-of-the-2b-llama.IQ4_XS.gguf	IQ4_XS	1.05GB
merge-of-the-2b-llama.Q4_0.gguf	Q4_0	1.1GB
merge-of-the-2b-llama.IQ4_NL.gguf	IQ4_NL	1.11GB
merge-of-the-2b-llama.Q4_K_S.gguf	Q4_K_S	1.11GB
merge-of-the-2b-llama.Q4_K.gguf	Q4_K	1.16GB
merge-of-the-2b-llama.Q4_K_M.gguf	Q4_K_M	1.16GB
merge-of-the-2b-llama.Q4_1.gguf	Q4_1	1.22GB
merge-of-the-2b-llama.Q5_0.gguf	Q5_0	1.33GB
merge-of-the-2b-llama.Q5_K_S.gguf	Q5_K_S	1.33GB
merge-of-the-2b-llama.Q5_K.gguf	Q5_K	1.37GB
merge-of-the-2b-llama.Q5_K_M.gguf	Q5_K_M	1.37GB
merge-of-the-2b-llama.Q5_1.gguf	Q5_1	1.45GB
merge-of-the-2b-llama.Q6_K.gguf	Q6_K	1.58GB
merge-of-the-2b-llama.Q8_0.gguf	Q8_0	2.05GB

Original model description:

base_model:

Fischerboot/2b-tiny-llama-alpaca-instr
Fischerboot/2b-lora-adapter-llama-alpaca library_name: transformers tags:
mergekit
merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Fischerboot/2b-tiny-llama-alpaca-instr + Fischerboot/2b-lora-adapter-llama-alpaca

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: Fischerboot/2b-tiny-llama-alpaca-instr+Fischerboot/2b-lora-adapter-llama-alpaca
merge_method: passthrough
dtype: bfloat16