Finetuned mistralai/Mistral-Small-Instruct-2409 on RP and creative writing and some regular questions generated by Opus at 8192 context.

Refusals removed from dataset.

Slop removed to some extent.

Prompt Template:

<s>[INST] {input} [/INST] {output}</s>

Licence: MRL-0.1

(Non-comercial use due to the Opus data and inheritied MRL license)

GGUF quants:

gghfez/SeminalRP-22b-GGUF

Downloads last month: 3

Safetensors

Model size

22.2B params

Tensor type

BF16

Inference Providers NEW

This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Model tree for gghfez/SeminalRP-22b

Base model

mistralai/Mistral-Small-Instruct-2409

Finetuned

(23)

this model

Merges

1 model

Quantizations

3 models