CoolFace
Modelpublic

Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-8_0bpw_exl2

sourceHugging Facellama3updated 2y agoView on Hugging Face
0likes18downloads
Model Card

Exllamav2 quant (exl2 / 8.0 bpw) made with ExLlamaV2 v0.0.21

Other EXL2 quants: | Quant | Model Size | lm_head | | ----- | ---------- | ------- | |<center>[2.2](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-2_2bpw_exl2)</center> | <center>7777 MB</center> | <center>6</center> | |<center>[2.5](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-2_5bpw_exl2)</center> | <center>8519 MB</center> | <center>6</center> | |<center>[3.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-3_0bpw_exl2)</center> | <center>9944 MB</center> | <center>6</center> | |<center>[3.5](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-3_5bpw_exl2)</center> | <center>11365 MB</center> | <center>6</center> | |<center>[3.75](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-3_75bpw_exl2)</center> | <center>12080 MB</center> | <center>6</center> | |<center>[4.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-4_0bpw_exl2)</center> | <center>12789 MB</center> | <center>6</center> | |<center>[4.25](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-4_25bpw_exl2)</center> | <center>13503 MB</center> | <center>6</center> | |<center>[5.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-5_0bpw_exl2)</center> | <center>15632 MB</center> | <center>6</center> | |<center>[6.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-6_0bpw_exl2)</center> | <center>18594 MB</center> | <center>8</center> | |<center>[6.5](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-6_5bpw_exl2)</center> | <center>19969 MB</center> | <center>8</center> | |<center>[8.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3_SnowStorm_4x8B-8_0bpw_exl2)</center> | <center>24115 MB</center> | <center>8</center> |

<style> .image-container { position: relative; display: inline-block; }

.image-container img { display: block; border-radius: 10px; box-shadow: 0 0 1px rgba(0, 0, 0, 0.3); }

.image-container::before { content: ""; position: absolute; top: 0px; left: 20px; width: calc(100% - 40px); height: calc(100%); background-image: url("https://cdn-uploads.huggingface.co/production/uploads/64f5e51289c121cb864ba464/OuMe79ZQPdCX01rTdfgXn.png"); background-size: cover; filter: blur(10px); z-index: -1; } </style> <br>

<div class="image-container"> <img src="https://cdn-uploads.huggingface.co/production/uploads/64f5e51289c121cb864ba464/OuMe79ZQPdCX01rTdfgXn.png" style="width: 96%; margin: auto;" > </div>

(Maybe i'll change the waifu picture later)

[!NOTE] GGUF/Exl2 quants

Experimental RP-oriented MoE, the idea was to get a model that would be equal to or better than Mixtral 8x7B and it's finetunes in RP/ERP tasks.

Llama 3 SnowStorm 4x8B

base_model: NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS
gate_mode: random
dtype: bfloat16
experts_per_token: 2
experts:
  - source_model: ChaoticNeutrals_Poppy_Porpoise-v0.7-L3-8B
  - source_model: NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS
  - source_model: openlynn_Llama-3-Soliloquy-8B-v2
  - source_model: Sao10K_L3-8B-Stheno-v3.1

Models used

Difference(from ChaoticSoliloquy v1.5)

Vision

llama3_mmproj

image/png

Prompt format: Llama 3