Edit model card

Image description

Tsunemoto GGUF's of Bucharest-0.2

This is a GGUF quantization of Bucharest-0.2.

Original Repo Link:

Original Repository

Original Model Card:


Built with Axolotl

An instruct based fine tune of migtissera/Tess-10.7B-v1.5b.

It should be used for enterprise tasks that involve reasoning and text comprehension.

This model is trained on a private dataset + Mihaiii/OpenHermes-2.5-1k-longest-curated, which is a subset of HuggingFaceH4/OpenHermes-2.5-1k-longest, which is a subset of teknium/OpenHermes-2.5.

The high GSM8K score is NOT because of the MetaMath dataset.

Prompt Format:

SYSTEM: <ANY SYSTEM CONTEXT>
USER: 
ASSISTANT:

GGUF:

tsunemoto/Bucharest-0.2-GGUF

Downloads last month
42
GGUF
Model size
10.7B params
Architecture
llama

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .