Hugging Face's logo

allura-org
/
MoE-Girl-1BA-7BT

Text Generation
Transformers
Safetensors
olmoe
axolotl
Mixture of Experts
roleplay
conversational
Inference Endpoints
Model card Files Community
Fizzarolli commited on
Commit
ecfac73
•
1 Parent(s): 1d08343

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ A finetune of OLMoE by AllenAI designed for roleplaying (and maybe general useca
18
  PLEASE do not expect godliness out of this, it's a model with 1 billion active parameters. Expect something more akin to Gemma 2 2B, not Llama 3 8B.
19
 
20
  ## Quants
21
- GGUF:
22
  - [mradermacher's imatrix quants](https://huggingface.co/mradermacher/MoE-Girl-1BA-7BT-i1-GGUF)
23
  - [our static quants](https://huggingface.co/allura-org/MoE-Girl-1BA-7BT-GGUF)
24
 
 
18
  PLEASE do not expect godliness out of this, it's a model with 1 billion active parameters. Expect something more akin to Gemma 2 2B, not Llama 3 8B.
19
 
20
  ## Quants
21
+ GGUF (requires a newish version of llama.cpp, not in kobold atm):
22
  - [mradermacher's imatrix quants](https://huggingface.co/mradermacher/MoE-Girl-1BA-7BT-i1-GGUF)
23
  - [our static quants](https://huggingface.co/allura-org/MoE-Girl-1BA-7BT-GGUF)
24