Modelpublic

RichardErkhov/Xclbr7_-_Hyena-12b-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes313downloads

Model Card

Quantization made by Richard Erkhov.

Request more models

Hyena-12b - GGUF

—Model creator: https://huggingface.co/Xclbr7/
—Original model: https://huggingface.co/Xclbr7/Hyena-12b/

Name	Quant method	Size
Hyena-12b.Q2_K.gguf	Q2_K	4.46GB
Hyena-12b.Q3_K_S.gguf	Q3KS	5.15GB
Hyena-12b.Q3_K.gguf	Q3_K	5.67GB
Hyena-12b.Q3_K_M.gguf	Q3KM	5.67GB
Hyena-12b.Q3_K_L.gguf	Q3KL	6.11GB
Hyena-12b.IQ4_XS.gguf	IQ4_XS	6.33GB
Hyena-12b.Q4_0.gguf	Q4_0	6.59GB
Hyena-12b.IQ4_NL.gguf	IQ4_NL	6.65GB
Hyena-12b.Q4_K_S.gguf	Q4KS	6.63GB
Hyena-12b.Q4_K.gguf	Q4_K	6.96GB
Hyena-12b.Q4_K_M.gguf	Q4KM	6.96GB
Hyena-12b.Q4_1.gguf	Q4_1	7.26GB
Hyena-12b.Q5_0.gguf	Q5_0	7.93GB
Hyena-12b.Q5_K_S.gguf	Q5KS	7.93GB
Hyena-12b.Q5_K.gguf	Q5_K	8.13GB
Hyena-12b.Q5_K_M.gguf	Q5KM	8.13GB
Hyena-12b.Q5_1.gguf	Q5_1	8.61GB
Hyena-12b.Q6_K.gguf	Q6_K	9.37GB
Hyena-12b.Q8_0.gguf	Q8_0	12.13GB

Original model description: --- base_model: Xclbr7/Arcanum-12b language:

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

Uploaded model

—Developed by: Xclbr7
—License: apache-2.0
—Finetuned from model : Xclbr7/Arcanum-12b

This mistral 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"/>