Text Generation
Transformers
Safetensors
English
mistral
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prosing
vivid writing
fiction
roleplaying
float32
swearing
rp
horror
della
Merge
mergekit
conversational
text-generation-inference
Update README.md
Browse files
README.md
CHANGED
|
@@ -77,7 +77,7 @@ widget:
|
|
| 77 |
|
| 78 |

|
| 79 |
|
| 80 |
-
The "Della Edition" meant to test bridging 2501 and 2503 models. See [this
|
| 81 |
|
| 82 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 83 |
|
|
@@ -85,4 +85,210 @@ This is a merge of pre-trained language models created using [mergekit](https://
|
|
| 85 |
### Merge Methods
|
| 86 |
|
| 87 |
This model was merged using the following merge method:
|
| 88 |
-
- [DELLA](https://arxiv.org/abs/2406.11617)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
|
| 78 |

|
| 79 |
|
| 80 |
+
The "Della Edition" meant to test bridging 2501 and 2503 models. See [this post](https://huggingface.co/Naphula/Goetia-24B-v1.3/discussions/1) and [this other post](https://huggingface.co/Naphula/Q0_Bench/discussions/1?not-for-all-audiences=true#6987717c762f0a45f672e250) for more info.
|
| 81 |
|
| 82 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 83 |
|
|
|
|
| 85 |
### Merge Methods
|
| 86 |
|
| 87 |
This model was merged using the following merge method:
|
| 88 |
+
- [DELLA](https://arxiv.org/abs/2406.11617)
|
| 89 |
+
|
| 90 |
+
```yaml
|
| 91 |
+
architecture: MistralForCausalLM
|
| 92 |
+
models:
|
| 93 |
+
- model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
| 94 |
+
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
|
| 95 |
+
parameters:
|
| 96 |
+
density: 0.8
|
| 97 |
+
weight: 0.2
|
| 98 |
+
epsilon: 0.1
|
| 99 |
+
- model: B:\24B\!models--ReadyArt--4.2.0-Broken-Tutu-24b
|
| 100 |
+
parameters:
|
| 101 |
+
density: 0.8
|
| 102 |
+
weight: 0.05
|
| 103 |
+
epsilon: 0.1
|
| 104 |
+
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v2-24B
|
| 105 |
+
parameters:
|
| 106 |
+
density: 0.8
|
| 107 |
+
weight: 0.2
|
| 108 |
+
epsilon: 0.1
|
| 109 |
+
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
| 110 |
+
parameters:
|
| 111 |
+
density: 0.8
|
| 112 |
+
weight: 0.2
|
| 113 |
+
epsilon: 0.1
|
| 114 |
+
- model: B:\24B\!models--TheDrummer--Precog-24B-v1
|
| 115 |
+
parameters:
|
| 116 |
+
density: 0.8
|
| 117 |
+
weight: 0.2
|
| 118 |
+
epsilon: 0.1
|
| 119 |
+
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v3-24B
|
| 120 |
+
parameters:
|
| 121 |
+
density: 0.8
|
| 122 |
+
weight: 0.2
|
| 123 |
+
epsilon: 0.1
|
| 124 |
+
- model: B:\24B\!BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
| 125 |
+
parameters:
|
| 126 |
+
density: 0.8
|
| 127 |
+
weight: 0.2
|
| 128 |
+
epsilon: 0.1
|
| 129 |
+
- model: B:\24B\!models--ReadyArt--Broken-Tutu-24B-Transgression-v2.0
|
| 130 |
+
parameters:
|
| 131 |
+
density: 0.8
|
| 132 |
+
weight: 0.05
|
| 133 |
+
epsilon: 0.1
|
| 134 |
+
- model: B:\24B\!models--trashpanda-org--MS3.2-24B-Mullein-v2
|
| 135 |
+
parameters:
|
| 136 |
+
density: 0.8
|
| 137 |
+
weight: 0.2
|
| 138 |
+
epsilon: 0.1
|
| 139 |
+
# - model: B:\24B\!models--LatitudeGames--Hearthfire-24B
|
| 140 |
+
# parameters:
|
| 141 |
+
# density: 0.8
|
| 142 |
+
# weight: 0.1
|
| 143 |
+
# epsilon: 0.1
|
| 144 |
+
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.2.0
|
| 145 |
+
parameters:
|
| 146 |
+
density: 0.8
|
| 147 |
+
weight: 0.1
|
| 148 |
+
epsilon: 0.1
|
| 149 |
+
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.2.0
|
| 150 |
+
parameters:
|
| 151 |
+
density: 0.8
|
| 152 |
+
weight: 0.1
|
| 153 |
+
epsilon: 0.1
|
| 154 |
+
- model: B:\24B\!models--ConicCat--Mistral-Small-3.2-AntiRep-24B
|
| 155 |
+
parameters:
|
| 156 |
+
density: 0.8
|
| 157 |
+
weight: 0.15
|
| 158 |
+
epsilon: 0.1
|
| 159 |
+
- model: B:\24B\!models--Undi95--MistralThinker-v1.1
|
| 160 |
+
parameters:
|
| 161 |
+
density: 0.8
|
| 162 |
+
weight: 0.02
|
| 163 |
+
epsilon: 0.1
|
| 164 |
+
- model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V2
|
| 165 |
+
parameters:
|
| 166 |
+
density: 0.8
|
| 167 |
+
weight: 0.02
|
| 168 |
+
epsilon: 0.1
|
| 169 |
+
- model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V7.1
|
| 170 |
+
parameters:
|
| 171 |
+
density: 0.8
|
| 172 |
+
weight: 0.1
|
| 173 |
+
epsilon: 0.1
|
| 174 |
+
- model: B:\24B\Morax-24B-v1
|
| 175 |
+
parameters:
|
| 176 |
+
density: 0.8
|
| 177 |
+
weight: 0.02
|
| 178 |
+
epsilon: 0.1
|
| 179 |
+
- model: B:\24B\!models--FlareRebellion--WeirdCompound-v1.7-24b
|
| 180 |
+
parameters:
|
| 181 |
+
density: 0.8
|
| 182 |
+
weight: 0.1
|
| 183 |
+
epsilon: 0.1
|
| 184 |
+
# - model: B:\24B\!models--aixonlab--Eurydice-24b-v3.5
|
| 185 |
+
# parameters:
|
| 186 |
+
# density: 0.8
|
| 187 |
+
# weight: 0.08
|
| 188 |
+
# epsilon: 0.1
|
| 189 |
+
- model: B:\24B\!models--allura-forge--ms32-final-TEXTONLY
|
| 190 |
+
parameters:
|
| 191 |
+
density: 0.8
|
| 192 |
+
weight: 0.15
|
| 193 |
+
epsilon: 0.1
|
| 194 |
+
- model: B:\24B\!models--Delta-Vector--Rei-24B-KTO
|
| 195 |
+
parameters:
|
| 196 |
+
density: 0.8
|
| 197 |
+
weight: 0.15
|
| 198 |
+
epsilon: 0.1
|
| 199 |
+
- model: B:\24B\!models--Doctor-Shotgun--MS3.2-24B-Magnum-Diamond
|
| 200 |
+
parameters:
|
| 201 |
+
density: 0.8
|
| 202 |
+
weight: 0.15
|
| 203 |
+
epsilon: 0.1
|
| 204 |
+
- model: B:\24B\!models--ReadyArt--MS3.2-The-Omega-Directive-24B-Unslop-v2.1
|
| 205 |
+
parameters:
|
| 206 |
+
density: 0.8
|
| 207 |
+
weight: 0.15
|
| 208 |
+
epsilon: 0.1
|
| 209 |
+
# - model: B:\24B\!models--Gryphe--Codex-24B-Small-3.2
|
| 210 |
+
# parameters:
|
| 211 |
+
# density: 0.8
|
| 212 |
+
# weight: 0.1
|
| 213 |
+
# epsilon: 0.1
|
| 214 |
+
# - model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V1.3
|
| 215 |
+
# parameters:
|
| 216 |
+
# density: 0.8
|
| 217 |
+
# weight: 0.15
|
| 218 |
+
# epsilon: 0.1
|
| 219 |
+
- model: B:\24B\!models--arcee-ai--Arcee-Blitz
|
| 220 |
+
parameters:
|
| 221 |
+
density: 0.8
|
| 222 |
+
weight: 0.02
|
| 223 |
+
epsilon: 0.1
|
| 224 |
+
- model: B:\24B\!models--ArliAI--Mistral-Small-24B-ArliAI-RPMax-v1.4
|
| 225 |
+
parameters:
|
| 226 |
+
density: 0.8
|
| 227 |
+
weight: 0.02
|
| 228 |
+
epsilon: 0.1
|
| 229 |
+
# - model: B:\24B\!models--PocketDoc--Dans-PersonalityEngine-V1.3.0-24b
|
| 230 |
+
# parameters:
|
| 231 |
+
# density: 0.8
|
| 232 |
+
# weight: 0.1
|
| 233 |
+
# epsilon: 0.1
|
| 234 |
+
- model: B:\24B\!models--ReadyArt--Dark-Nexus-24B-v2.0
|
| 235 |
+
parameters:
|
| 236 |
+
density: 0.8
|
| 237 |
+
weight: 0.2
|
| 238 |
+
epsilon: 0.1
|
| 239 |
+
- model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V5.1-Pro
|
| 240 |
+
parameters:
|
| 241 |
+
density: 0.8
|
| 242 |
+
weight: 0.15
|
| 243 |
+
epsilon: 0.1
|
| 244 |
+
- model: B:\24B\!models--dphn--Dolphin-Mistral-24B-Venice-Edition
|
| 245 |
+
parameters:
|
| 246 |
+
density: 0.8
|
| 247 |
+
weight: 0.01
|
| 248 |
+
epsilon: 0.1
|
| 249 |
+
- model: B:\24B\!models--TroyDoesAI--BlackSheep-24B
|
| 250 |
+
parameters:
|
| 251 |
+
density: 0.8
|
| 252 |
+
weight: 0.01
|
| 253 |
+
epsilon: 0.1
|
| 254 |
+
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v2
|
| 255 |
+
parameters:
|
| 256 |
+
density: 0.8
|
| 257 |
+
weight: 0.02
|
| 258 |
+
epsilon: 0.1
|
| 259 |
+
- model: B:\24B\!models--PocketDoc--Dans-DangerousWinds-V1.1.1-24b
|
| 260 |
+
parameters:
|
| 261 |
+
density: 0.8
|
| 262 |
+
weight: 0.02
|
| 263 |
+
epsilon: 0.1
|
| 264 |
+
- model: B:\24B\!models--trashpanda-org--MS-24B-Instruct-Mullein-v0
|
| 265 |
+
parameters:
|
| 266 |
+
density: 0.8
|
| 267 |
+
weight: 0.02
|
| 268 |
+
epsilon: 0.1
|
| 269 |
+
- model: B:\24B\!models--OddTheGreat--Circuitry_24B_V.3
|
| 270 |
+
parameters:
|
| 271 |
+
density: 0.8
|
| 272 |
+
weight: 0.1
|
| 273 |
+
epsilon: 0.1
|
| 274 |
+
- model: B:\24B\!models--spacewars123--Space-Wars-24B-v1.00a
|
| 275 |
+
parameters:
|
| 276 |
+
density: 0.8
|
| 277 |
+
weight: 0.02
|
| 278 |
+
epsilon: 0.1
|
| 279 |
+
# Total Donors: 33
|
| 280 |
+
# Total Weights: 3.3
|
| 281 |
+
# Seed: 420
|
| 282 |
+
merge_method: della
|
| 283 |
+
base_model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
| 284 |
+
parameters:
|
| 285 |
+
lambda: 1.0
|
| 286 |
+
normalize: true # key variable to test
|
| 287 |
+
int8_mask: false
|
| 288 |
+
dtype: float32
|
| 289 |
+
out_dtype: bfloat16
|
| 290 |
+
tokenizer:
|
| 291 |
+
source: base
|
| 292 |
+
# chat_template: auto
|
| 293 |
+
name: 📜 Goetia-24B-v1.3
|
| 294 |
+
```
|