Modelpublic

RichardErkhov/Limby_-_qwenfloat16-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes527downloads

Model Card

Quantization made by Richard Erkhov.

Request more models

qwenfloat16 - GGUF

—Model creator: https://huggingface.co/Limby/
—Original model: https://huggingface.co/Limby/qwenfloat16/

Name	Quant method	Size
qwenfloat16.Q2_K.gguf	Q2_K	0.32GB
qwenfloat16.IQ3_XS.gguf	IQ3_XS	0.32GB
qwenfloat16.IQ3_S.gguf	IQ3_S	0.32GB
qwenfloat16.Q3_K_S.gguf	Q3KS	0.32GB
qwenfloat16.IQ3_M.gguf	IQ3_M	0.32GB
qwenfloat16.Q3_K.gguf	Q3_K	0.33GB
qwenfloat16.Q3_K_M.gguf	Q3KM	0.33GB
qwenfloat16.Q3_K_L.gguf	Q3KL	0.34GB
qwenfloat16.IQ4_XS.gguf	IQ4_XS	0.33GB
qwenfloat16.Q4_0.gguf	Q4_0	0.33GB
qwenfloat16.IQ4_NL.gguf	IQ4_NL	0.33GB
qwenfloat16.Q4_K_S.gguf	Q4KS	0.36GB
qwenfloat16.Q4_K.gguf	Q4_K	0.37GB
qwenfloat16.Q4_K_M.gguf	Q4KM	0.37GB
qwenfloat16.Q4_1.gguf	Q4_1	0.35GB
qwenfloat16.Q5_0.gguf	Q5_0	0.37GB
qwenfloat16.Q5_K_S.gguf	Q5KS	0.38GB
qwenfloat16.Q5_K.gguf	Q5_K	0.39GB
qwenfloat16.Q5_K_M.gguf	Q5KM	0.39GB
qwenfloat16.Q5_1.gguf	Q5_1	0.39GB
qwenfloat16.Q6_K.gguf	Q6_K	0.47GB
qwenfloat16.Q8_0.gguf	Q8_0	0.49GB

Original model description: --- base_model: unsloth/qwen2.5-0.5b-instruct-bnb-4bit language:

—en license: apache-2.0 tags:
—text-generation-inference
—transformers
—unsloth
—qwen2
—trl
—sft ---

Uploaded model

—Developed by: Limby
—License: apache-2.0
—Finetuned from model : unsloth/qwen2.5-0.5b-instruct-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>