Fischerboot_-_thinking-merged-3b-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
Fischerboot_-_thinking-merged-3b-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

thinking-merged-3b - GGUF

Model creator: https://huggingface.co/Fischerboot/
Original model: https://huggingface.co/Fischerboot/thinking-merged-3b/

Name	Quant method	Size
thinking-merged-3b.Q2_K.gguf	Q2_K	1.27GB
thinking-merged-3b.IQ3_XS.gguf	IQ3_XS	1.38GB
thinking-merged-3b.IQ3_S.gguf	IQ3_S	1.44GB
thinking-merged-3b.Q3_K_S.gguf	Q3_K_S	1.44GB
thinking-merged-3b.IQ3_M.gguf	IQ3_M	1.49GB
thinking-merged-3b.Q3_K.gguf	Q3_K	1.57GB
thinking-merged-3b.Q3_K_M.gguf	Q3_K_M	1.57GB
thinking-merged-3b.Q3_K_L.gguf	Q3_K_L	1.69GB
thinking-merged-3b.IQ4_XS.gguf	IQ4_XS	1.71GB
thinking-merged-3b.Q4_0.gguf	Q4_0	1.79GB
thinking-merged-3b.IQ4_NL.gguf	IQ4_NL	1.79GB
thinking-merged-3b.Q4_K_S.gguf	Q4_K_S	1.8GB
thinking-merged-3b.Q4_K.gguf	Q4_K	1.88GB
thinking-merged-3b.Q4_K_M.gguf	Q4_K_M	1.88GB
thinking-merged-3b.Q4_1.gguf	Q4_1	1.95GB
thinking-merged-3b.Q5_0.gguf	Q5_0	2.11GB
thinking-merged-3b.Q5_K_S.gguf	Q5_K_S	2.11GB
thinking-merged-3b.Q5_K.gguf	Q5_K	2.16GB
thinking-merged-3b.Q5_K_M.gguf	Q5_K_M	2.16GB
thinking-merged-3b.Q5_1.gguf	Q5_1	2.28GB
thinking-merged-3b.Q6_K.gguf	Q6_K	2.46GB
thinking-merged-3b.Q8_0.gguf	Q8_0	3.19GB

Original model description:

base_model: [] library_name: transformers tags:

mergekit
merge

Holy Fuck

this model was a proof of concept, it has thinking (and other) tags, which made the quality of the output, really f*ckin good.

(Tested Q8 GGUF)

It does really well as a Q8, its fast as fuck boi, and small.

This is just a lora checkpoint, so once the final produt is done, expect something better.

Link to the final product will be here when its done.

output-model-directory

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:

./3b + ./thinking-3b

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: ./3b+./thinking-3b
merge_method: passthrough