Downloads · 30 days
54
8% of all-time downloads
RichardErkhov/matchaaaaa_-_MN-Tiramisu-12B-gguf
matchaaaaa_-_MN-Tiramisu-12B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
54
8% of all-time downloads
All-time downloads
715
Public
Repo size
124 GB
Likes
0
Public
Click a slice to open those files.
.gguf147 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
MN-Tiramisu-12B - GGUF
| Name | Quant method | Size |
|---|---|---|
| MN-Tiramisu-12B.Q2_K.gguf | Q2_K | 4.46GB |
| MN-Tiramisu-12B.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| MN-Tiramisu-12B.Q3_K.gguf | Q3_K | 5.67GB |
| MN-Tiramisu-12B.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| MN-Tiramisu-12B.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| MN-Tiramisu-12B.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| MN-Tiramisu-12B.Q4_0.gguf | Q4_0 | 6.59GB |
| MN-Tiramisu-12B.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| MN-Tiramisu-12B.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| MN-Tiramisu-12B.Q4_K.gguf | Q4_K | 6.96GB |
| MN-Tiramisu-12B.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| MN-Tiramisu-12B.Q4_1.gguf | Q4_1 | 7.26GB |
| MN-Tiramisu-12B.Q5_0.gguf | Q5_0 | 7.93GB |
| MN-Tiramisu-12B.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| MN-Tiramisu-12B.Q5_K.gguf | Q5_K | 8.13GB |
| MN-Tiramisu-12B.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| MN-Tiramisu-12B.Q5_1.gguf | Q5_1 | 8.61GB |
| MN-Tiramisu-12B.Q6_K.gguf | Q6_K | 9.37GB |
| MN-Tiramisu-12B.Q8_0.gguf | Q8_0 | 12.13GB |
base_model: [flammenai/Mahou-1.3-mistral-nemo-12B] library_name: transformers tags:

This is a really yappity-yappy yapping model that's good for long-form RP. Tried to rein it in with Mahou and give it some more character understanding with Pantheon. Feedback is always welcome.
Native Context Length: 16K/16384 (can be extended using RoPE, YMMV)
<|im_start|>system
{system prompt}<|im_end|>
<|im_start|>user
{message}<|im_end|>
<|im_start|>assistant
{response}
Here are some settings ranges that tend to work for me. They aren't strict values, and there's a bit of leeway in them. Feel free to experiment a bit!
This is a merge of pre-trained language models created using mergekit.
This model was merged using the linear DARE merge method using flammenai/Mahou-1.3-mistral-nemo-12B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: flammenai/Mahou-1.3-mistral-nemo-12B
dtype: bfloat16
merge_method: dare_linear
slices:
- sources:
- layer_range: [0, 40]
model: Gryphe/Pantheon-RP-1.5-12b-Nemo
parameters:
weight: [0.45, 0.35, 0.35, 0.2, 0.2]
- layer_range: [0, 40]
model: Sao10K/MN-12B-Lyra-v1
parameters:
weight: [0.25, 0.3, 0.35, 0.3, 0.2]
- layer_range: [0, 40]
model: nbeerbower/mistral-nemo-gutenberg-12B-v4
parameters:
weight:
- filter: mlp
value: [0.1, 0.2, 0.1, 0.4, 0.5]
- value: [0.1, 0.2, 0.1, 0.2, 0.2]
- layer_range: [0, 40]
model: flammenai/Mahou-1.3-mistral-nemo-12B
parameters:
weight:
- filter: mlp
value: [0.2, 0.15, 0.2, 0.1, 0.1]
- value: [0.2, 0.15, 0.2, 0.3, 0.4]
tokenizer_source: union
And as always, have a great day!