YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
Tiger-Gemma-9B-v2 - GGUF
- Model creator: https://huggingface.co/TheDrummer/
- Original model: https://huggingface.co/TheDrummer/Tiger-Gemma-9B-v2/
Name | Quant method | Size |
---|---|---|
Tiger-Gemma-9B-v2.Q2_K.gguf | Q2_K | 3.54GB |
Tiger-Gemma-9B-v2.IQ3_XS.gguf | IQ3_XS | 3.86GB |
Tiger-Gemma-9B-v2.IQ3_S.gguf | IQ3_S | 4.04GB |
Tiger-Gemma-9B-v2.Q3_K_S.gguf | Q3_K_S | 4.04GB |
Tiger-Gemma-9B-v2.IQ3_M.gguf | IQ3_M | 4.19GB |
Tiger-Gemma-9B-v2.Q3_K.gguf | Q3_K | 4.43GB |
Tiger-Gemma-9B-v2.Q3_K_M.gguf | Q3_K_M | 4.43GB |
Tiger-Gemma-9B-v2.Q3_K_L.gguf | Q3_K_L | 4.78GB |
Tiger-Gemma-9B-v2.IQ4_XS.gguf | IQ4_XS | 4.86GB |
Tiger-Gemma-9B-v2.Q4_0.gguf | Q4_0 | 5.07GB |
Tiger-Gemma-9B-v2.IQ4_NL.gguf | IQ4_NL | 5.1GB |
Tiger-Gemma-9B-v2.Q4_K_S.gguf | Q4_K_S | 5.1GB |
Tiger-Gemma-9B-v2.Q4_K.gguf | Q4_K | 5.37GB |
Tiger-Gemma-9B-v2.Q4_K_M.gguf | Q4_K_M | 5.37GB |
Tiger-Gemma-9B-v2.Q4_1.gguf | Q4_1 | 5.55GB |
Tiger-Gemma-9B-v2.Q5_0.gguf | Q5_0 | 6.04GB |
Tiger-Gemma-9B-v2.Q5_K_S.gguf | Q5_K_S | 6.04GB |
Tiger-Gemma-9B-v2.Q5_K.gguf | Q5_K | 6.19GB |
Tiger-Gemma-9B-v2.Q5_K_M.gguf | Q5_K_M | 6.19GB |
Tiger-Gemma-9B-v2.Q5_1.gguf | Q5_1 | 6.52GB |
Tiger-Gemma-9B-v2.Q6_K.gguf | Q6_K | 7.07GB |
Tiger-Gemma-9B-v2.Q8_0.gguf | Q8_0 | 9.15GB |
Original model description:
Tiger Gemma 9B v2
Decensored Gemma 9B. No refusals so far. No apparent brain damage.
Links
- Original: https://huggingface.co/TheDrummer/Tiger-Gemma-9B-v2
- GGUF: https://huggingface.co/TheDrummer/Tiger-Gemma-9B-v2-GGUF
What's New with v2?
It's a simple decensor but with a lighter touch, allowing it to be as Gemma as possible.
In memory of Tiger (the happy street cat on the right)
- Downloads last month
- 126
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.