Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-2_2bpw_exl2

Exllamav2 quant (exl2 / 2.2 bpw) made with ExLlamaV2 v0.1.1

Other EXL2 quants: | Quant | Model Size | lm_head | | ----- | ---------- | ------- | |<center>[2.2](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-2_2bpw_exl2)</center> | <center>7777 MB</center> | <center>6</center> | |<center>[2.5](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-2_5bpw_exl2)</center> | <center>8520 MB</center> | <center>6</center> | |<center>[3.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-3_0bpw_exl2)</center> | <center>9941 MB</center> | <center>6</center> | |<center>[3.5](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-3_5bpw_exl2)</center> | <center>11366 MB</center> | <center>6</center> | |<center>[3.75](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-3_75bpw_exl2)</center> | <center>12066 MB</center> | <center>6</center> | |<center>[4.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-4_0bpw_exl2)</center> | <center>12789 MB</center> | <center>6</center> | |<center>[4.25](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-4_25bpw_exl2)</center> | <center>13504 MB</center> | <center>6</center> | |<center>[5.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-5_0bpw_exl2)</center> | <center>15640 MB</center> | <center>6</center> | |<center>[6.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-6_0bpw_exl2)</center> | <center>18586 MB</center> | <center>8</center> | |<center>[6.5](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-6_5bpw_exl2)</center> | <center>20007 MB</center> | <center>8</center> | |<center>[8.0](https://huggingface.co/Zoyd/xxx777xxxASD_L3-SnowStorm-v1.15-4x8B-A-8_0bpw_exl2)</center> | <center>24101 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/64f5e51289c121cb864ba464/8eG7GxTvcbxyVFQf5GF3C.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/64f5e51289c121cb864ba464/8eG7GxTvcbxyVFQf5GF3C.png" style="width: 96%; margin: auto;" > </div>

[!NOTE] GGUF

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.

There's:

• —v1.15A <- You're here
• —v1.15B

Llama 3 SnowStorm v1.15A 4x8B

base_model: NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS
gate_mode: random
dtype: bfloat16
experts_per_token: 2
experts:
  - source_model: Nitral-AI_Poppy_Porpoise-1.0-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

• —Nitral-AI/Poppy_Porpoise-1.0-L3-8B
• —NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
• —openlynn/Llama-3-Soliloquy-8B-v2
• —Sao10K/L3-8B-Stheno-v3.1

Difference(from SnowStorm v1.0)

• —Update from ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B to Nitral-AI/Poppy_Porpoise-0.85-L3-8B

Vision

llama3_mmproj

Prompt format: Llama 3

Open LLM Leaderboard Evaluation Results

Detailed results can be found here