Downloads · 30 days
8
9% of all-time downloads
ChaoticSoliloquy-4x8B-6bpw-h6-exl2
JayhC/ChaoticSoliloquy-4x8B-6bpw-h6-exl2
ChaoticSoliloquy-4x8B-6bpw-h6-exl2 is a text generation model from JayhC. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.
<br/<br/ 6bpw/h6 exl2 quantization of xxx777xxxASD/ChaoticSoliloquy-4x8B using default exllamav2 calibration dataset.
All-time downloads
94
Public
Repo size
19.4 GB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors19.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- llama3
- Model type
- mixtral
- Access
- Public
- Created
- Apr 24, 2024
- Updated
- Apr 24, 2024
- SHA
- 61435a25
Try a prompt
Model card
From the Hugging Face model README
<br/><br/> 6bpw/h6 exl2 quantization of xxx777xxxASD/ChaoticSoliloquy-4x8B using default exllamav2 calibration dataset.
ORIGINAL CARD:
(Maybe i'll change the waifu picture later)
Experimental RP-oriented MoE, the idea was to get a model that would be equal to or better than the Mixtral 8x7B and it's finetunes in RP/ERP tasks.
ChaoticSoliloquy-4x8B
base_model: jeiku_Chaos_RP_l3_8B
gate_mode: random
dtype: bfloat16
experts_per_token: 2
experts:
- source_model: ChaoticNeutrals_Poppy_Porpoise-v0.6-L3-8B
- source_model: jeiku_Chaos_RP_l3_8B
- source_model: openlynn_Llama-3-Soliloquy-8B
- source_model: Sao10K_L3-Solana-8B-v1
Models used
- ChaoticNeutrals/Poppy_Porpoise-v0.6-L3-8B
- jeiku/Chaos_RP_l3_8B
- openlynn/Llama-3-Soliloquy-8B
- Sao10K/L3-Solana-8B-v1
Vision
Prompt format: Llama 3
- Task
- Text Generation
- Library
- transformers
- Type
- mixtral
- License
- llama3
- Languages
- en
- Created
- Apr 24, 2024
- Updated
- Apr 24, 2024