Quantization made by Richard Erkhov.
G2-9B-Blackout-R1 - GGUF
- Model creator: https://huggingface.co/inflatebot/
- Original model: https://huggingface.co/inflatebot/G2-9B-Blackout-R1/
Name | Quant method | Size |
---|---|---|
G2-9B-Blackout-R1.Q2_K.gguf | Q2_K | 3.54GB |
G2-9B-Blackout-R1.IQ3_XS.gguf | IQ3_XS | 3.86GB |
G2-9B-Blackout-R1.IQ3_S.gguf | IQ3_S | 4.04GB |
G2-9B-Blackout-R1.Q3_K_S.gguf | Q3_K_S | 4.04GB |
G2-9B-Blackout-R1.IQ3_M.gguf | IQ3_M | 4.19GB |
G2-9B-Blackout-R1.Q3_K.gguf | Q3_K | 4.43GB |
G2-9B-Blackout-R1.Q3_K_M.gguf | Q3_K_M | 4.43GB |
G2-9B-Blackout-R1.Q3_K_L.gguf | Q3_K_L | 4.78GB |
G2-9B-Blackout-R1.IQ4_XS.gguf | IQ4_XS | 4.86GB |
G2-9B-Blackout-R1.Q4_0.gguf | Q4_0 | 5.07GB |
G2-9B-Blackout-R1.IQ4_NL.gguf | IQ4_NL | 5.1GB |
G2-9B-Blackout-R1.Q4_K_S.gguf | Q4_K_S | 5.1GB |
G2-9B-Blackout-R1.Q4_K.gguf | Q4_K | 5.37GB |
G2-9B-Blackout-R1.Q4_K_M.gguf | Q4_K_M | 5.37GB |
G2-9B-Blackout-R1.Q4_1.gguf | Q4_1 | 5.55GB |
G2-9B-Blackout-R1.Q5_0.gguf | Q5_0 | 6.04GB |
G2-9B-Blackout-R1.Q5_K_S.gguf | Q5_K_S | 6.04GB |
G2-9B-Blackout-R1.Q5_K.gguf | Q5_K | 6.19GB |
G2-9B-Blackout-R1.Q5_K_M.gguf | Q5_K_M | 6.19GB |
G2-9B-Blackout-R1.Q5_1.gguf | Q5_1 | 6.52GB |
G2-9B-Blackout-R1.Q6_K.gguf | Q6_K | 7.07GB |
G2-9B-Blackout-R1.Q8_0.gguf | Q8_0 | 9.15GB |
Original model description:
base_model:
- crestf411/gemma2-9B-sunfall-v0.5.2
- IntervitensInc/gemma-2-9b-chatml
- anthracite-org/magnum-v3-9b-chatml library_name: transformers tags:
- mergekit
- merge
A lot of punch in a little package.
GGUFs available courtesy of mradermacher
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
A simple task-arithmetic merge of Magnum-v3-9B with just a pinch of Sunfall, to loosen it up a little bit. Does the horny real good, but also has a depth of character that Magnum lacked. Uses ChatML formatting, which in and of itself is a massive upgrade to Gemma2. (Who ships a model without a system prompt in 2024? Come on, Google.)
Merge Method
This model was merged using the task arithmetic merge method using IntervitensInc/gemma-2-9b-chatml as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: anthracite-org/magnum-v3-9b-chatml
parameters:
weight: 1
- model: crestf411/gemma2-9B-sunfall-v0.5.2
parameters:
weight: 0.3
merge_method: task_arithmetic
base_model: IntervitensInc/gemma-2-9b-chatml
dtype: float32
tokenizer_source: base
parameters:
normalize: true
.300 AAC Blackout is an intermediate cartridge designed for use in the M4 Carbine, packing a significantly larger projectile into a cartridge compatible with 5.56mm NATO magazines, only requiring a barrel change.
- Downloads last month
- 217