RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-07 11:56:17 +08:00
commit 1d3112fbdd
24 changed files with 325 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
.gitattributes vendored Normal file
View File

@@ -0,0 +1,57 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
MN-12B-Mag-Mell-R1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

3
MN-12B-Mag-Mell-R1.IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ff3ec4a1a46ed1b01bad3d884956d8e1a8f369e9b98d934050794fa0c434789d
size 5722233536

3
MN-12B-Mag-Mell-R1.IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:12b90e19f8d96833d5d67401f7668e34c6230da4e56a0e465626863c1f800b6b
size 5562079936

3
MN-12B-Mag-Mell-R1.IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7f8155e596ffc7e81229787c6d6531e526182d634e338a6ee70609127ec93d8f
size 5306489536

3
MN-12B-Mag-Mell-R1.IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3559b281fbeb2f1ef5399a266f567cf6ceded3cb14ea8b9e5eafd28431d718b7
size 7143791296

3
MN-12B-Mag-Mell-R1.IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:738e9e2e978b594c7642c823cac14d5c2e45d6b755ba167da1d6f91ef41d1934
size 6800054976

3
MN-12B-Mag-Mell-R1.Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:722b3ddbe52db8f5dca67975112a05b1114477f12f56d461c7ca4df61e183d4c
size 4791048896

3
MN-12B-Mag-Mell-R1.Q3_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:663b6a8f00c6e50df9457903aad9c0583b5fed08ee1526f49be5987d4efdfae1
size 6083091136

3
MN-12B-Mag-Mell-R1.Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4596d4cb07dfe76ccbddced237d3e9969ed320a7df865b25e902dfbdf6b91275
size 6561503936

3
MN-12B-Mag-Mell-R1.Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:663b6a8f00c6e50df9457903aad9c0583b5fed08ee1526f49be5987d4efdfae1
size 6083091136

3
MN-12B-Mag-Mell-R1.Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d18fbf6743aef03159afcef1bdee62e28191733165c6ef4873f47ce034fbe40f
size 5534227136

3
MN-12B-Mag-Mell-R1.Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6cf7f1097dd8b99d68da6b1b8f92f13f77c9e2fc2474208aaca1911f2c51a51b
size 7071701696

3
MN-12B-Mag-Mell-R1.Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c317265a2df5165f1b98dc32a78e20d93884d4fc323e5af2adcb9f4189ebb561
size 7795219136

3
MN-12B-Mag-Mell-R1.Q4_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:30d7f3070efa689d7820cb2ff5ce452c2de2c4c7961830192cb5447843537331
size 7477205696

3
MN-12B-Mag-Mell-R1.Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:30d7f3070efa689d7820cb2ff5ce452c2de2c4c7961830192cb5447843537331
size 7477205696

3
MN-12B-Mag-Mell-R1.Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:512f0241741b03c7d175c7b25bc0c9d00e0f3b5a898a5c13b7475541b2734a3f
size 7120198336

3
MN-12B-Mag-Mell-R1.Q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c14660b522794175f1a9440a0f328bd8ad19e5b8c22e8b6348a8a17c1f8e6bdf
size 8518736576

3
MN-12B-Mag-Mell-R1.Q5_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a4c1ef2c4475162ee8da059728c5a0ac252cdc57b53c5423f629d6d22f6bc93
size 9242254016

3
MN-12B-Mag-Mell-R1.Q5_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:95536af4067b2f2f527af7ab032e87ee4e98b6cb4aefc2a446bd73c5f561d392
size 8727632576

3
MN-12B-Mag-Mell-R1.Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:95536af4067b2f2f527af7ab032e87ee4e98b6cb4aefc2a446bd73c5f561d392
size 8727632576

3
MN-12B-Mag-Mell-R1.Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f955b164e8d3acc711ff893c0b4dc68d8c2e9574ea918a8a5f5b9ad9d4bfc25a
size 8518736576

3
MN-12B-Mag-Mell-R1.Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:203ebf294a244253597c057132c71633e67b17459ba82729269deff770927846
size 10056211136

3
MN-12B-Mag-Mell-R1.Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ed186cda9bfa8b0b20d9f9c0833c5eb5b37a47bd49cb3088d1c4194c5942851e
size 13022370496

202
README.md Normal file
View File

@@ -0,0 +1,202 @@
Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
MN-12B-Mag-Mell-R1 - GGUF
- Model creator: https://huggingface.co/inflatebot/
- Original model: https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [MN-12B-Mag-Mell-R1.Q2_K.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q2_K.gguf) | Q2_K | 4.46GB |
| [MN-12B-Mag-Mell-R1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.IQ3_XS.gguf) | IQ3_XS | 4.94GB |
| [MN-12B-Mag-Mell-R1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.IQ3_S.gguf) | IQ3_S | 5.18GB |
| [MN-12B-Mag-Mell-R1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q3_K_S.gguf) | Q3_K_S | 5.15GB |
| [MN-12B-Mag-Mell-R1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.IQ3_M.gguf) | IQ3_M | 5.33GB |
| [MN-12B-Mag-Mell-R1.Q3_K.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q3_K.gguf) | Q3_K | 5.67GB |
| [MN-12B-Mag-Mell-R1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q3_K_M.gguf) | Q3_K_M | 5.67GB |
| [MN-12B-Mag-Mell-R1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q3_K_L.gguf) | Q3_K_L | 6.11GB |
| [MN-12B-Mag-Mell-R1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.IQ4_XS.gguf) | IQ4_XS | 6.33GB |
| [MN-12B-Mag-Mell-R1.Q4_0.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q4_0.gguf) | Q4_0 | 6.59GB |
| [MN-12B-Mag-Mell-R1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.IQ4_NL.gguf) | IQ4_NL | 6.65GB |
| [MN-12B-Mag-Mell-R1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q4_K_S.gguf) | Q4_K_S | 6.63GB |
| [MN-12B-Mag-Mell-R1.Q4_K.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q4_K.gguf) | Q4_K | 6.96GB |
| [MN-12B-Mag-Mell-R1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q4_K_M.gguf) | Q4_K_M | 6.96GB |
| [MN-12B-Mag-Mell-R1.Q4_1.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q4_1.gguf) | Q4_1 | 7.26GB |
| [MN-12B-Mag-Mell-R1.Q5_0.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q5_0.gguf) | Q5_0 | 7.93GB |
| [MN-12B-Mag-Mell-R1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q5_K_S.gguf) | Q5_K_S | 7.93GB |
| [MN-12B-Mag-Mell-R1.Q5_K.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q5_K.gguf) | Q5_K | 8.13GB |
| [MN-12B-Mag-Mell-R1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q5_K_M.gguf) | Q5_K_M | 8.13GB |
| [MN-12B-Mag-Mell-R1.Q5_1.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q5_1.gguf) | Q5_1 | 8.61GB |
| [MN-12B-Mag-Mell-R1.Q6_K.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q6_K.gguf) | Q6_K | 9.37GB |
| [MN-12B-Mag-Mell-R1.Q8_0.gguf](https://huggingface.co/RichardErkhov/inflatebot_-_MN-12B-Mag-Mell-R1-gguf/blob/main/MN-12B-Mag-Mell-R1.Q8_0.gguf) | Q8_0 | 12.13GB |
Original model description:
---
base_model:
- IntervitensInc/Mistral-Nemo-Base-2407-chatml
- nbeerbower/mistral-nemo-bophades-12B
- nbeerbower/mistral-nemo-wissenschaft-12B
- elinas/Chronos-Gold-12B-1.0
- Fizzarolli/MN-12b-Sunrose
- nbeerbower/mistral-nemo-gutenberg-12B-v4
- anthracite-org/magnum-12b-v2.5-kto
library_name: transformers
tags:
- mergekit
- merge
---
![Made with NovelAI](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1/resolve/main/magmell.png)
*[Welcome, brave one; you've come a long mile.](https://www.youtube.com/watch?v=dgGEuC1F3oE)*
# MN-12B-Mag-Mell-R1
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
[Q4_K_M, Q6_K and Q_8 GGUFs by me](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1-GGUF)
[More available from mradermacher](https://huggingface.co/mradermacher/MN-12B-Mag-Mell-R1-GGUF/tree/main)
## Usage Details
### Sampler Settings
Mag Mell R1 was tested with Temp 1.25 and MinP 0.2. This was fairly stable up to 10K, but this might be too "hot".
If issues with coherency occur, try *in*creasing MinP or *de*creasing Temperature.
Other samplers shouldn't be necessary. XTC was shown to break outputs. DRY should be okay if used sparingly. Other penalty-type samplers should probably be avoided.
### Formatting
The base model for Mag Mell is [Mistral-Nemo-Base-2407-chatml](https://huggingface.co/IntervitensInc/Mistral-Nemo-Base-2407-chatml), and as such ChatML formatting is recommended.
#### After further testing, I can confirm that ChatML works the best. The below can be ignored in the context of this model specifically.
However, many component models still use Mistral's format. As a result, occasionally the word "user" or "assistant" will appear on the bottom of the screen.
__However.__ Some things have come out regarding Mistral's format that should be covered here, and implicates not just Mag Mell, but *all* Mistral-based models since the original Mistral 7B.
*The following information is as correct as I can get it as of September 20th, 2024*
We've had Mistral's tokenizer handling and completions format all wrong. *The templates in your frontend are probably wrong right now.*
MistralAI member Pandora has been going around helping to correct everyone.
Right now, Pandora has opened PRs for ~~[SillyTavern](https://github.com/SillyTavern/SillyTavern/pull/2883)~~ (**MERGED** to Staging. Update and use Mistral V3-Tekken), ~~[KoboldAI Lite](https://github.com/LostRuins/lite.koboldai.net/pull/87)~~ (**MERGED** to dev branch) and ~~[KoboldCPP chat adapters]~~(https://github.com/LostRuins/koboldcpp/pull/1131). (**MERGED**, staged for next release)
*When these are merged*, then the templates in them can be assumed to be completely correct.
Until then, ~~I've [provided templates for SillyTavern on GitHub that should be More Correct than the ones ST currently ships.](https://github.com/inflatebot/SillyTavern-Nemo-Templates)~~ Use Mistral V3-Tekken from SillyTavern Staging.
If you don't want to/can't update, you can get the new prompt template files [here](https://github.com/SillyTavern/SillyTavern/tree/staging/default/content/presets) (in the `context` and `instruct` folders.)
If you experiment with this, please let me know how it goes! The conversation on how to properly implement Mistral is still ongoing.
## Merge Details
Multi-stage SLERP merge, DARE-TIES'd together. Intended to be a general purpose "Best of Nemo" model for any fictional, creative use case. Inspired by hyper-merges like [Tiefighter](https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter) and [Umbral Mind.](https://huggingface.co/Casual-Autopsy/L3-Umbral-Mind-RP-v2.0-8B)
Mag Mell is composed of 3 intermediate parts:
- Hero (RP, kink/trope coverage): [Chronos Gold](https://huggingface.co/elinas/Chronos-Gold-12B-1.0), [Sunrose](https://huggingface.co/Fizzarolli/MN-12b-Sunrose).
- Monk (Intelligence, groundedness): [Bophades](https://huggingface.co/nbeerbower/mistral-nemo-bophades-12B), [Wissenschaft](https://huggingface.co/nbeerbower/mistral-nemo-wissenschaft-12B).
- Deity (Prose, flair): [Gutenberg v4](https://huggingface.co/nbeerbower/mistral-nemo-gutenberg-12B-v4), [Magnum 2.5 KTO](https://huggingface.co/anthracite-org/magnum-v2.5-12b-kto).
I've been dreaming about this merge since Nemo tunes started coming out in earnest. From our testing, Mag Mell demonstrates worldbuilding capabilities unlike any model in its class, comparable to old adventuring models like Tiefighter, and prose that exhibits minimal "slop" (not bad for no finetuning,) frequently devising electrifying metaphors that left us consistently astonished.
Use ChatML formatting. Early testing versions had a tendency to leak tokens, but this should be more or less hammered out.
I don't want to toot my own bugle though; I'm really proud of how this came out, but please leave your feedback, good or bad.
Special thanks as usual to Toaster for his feedback and Fizz for helping fund compute, as well as the KoboldAI Discord for their resources.
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [IntervitensInc/Mistral-Nemo-Base-2407-chatml](https://huggingface.co/IntervitensInc/Mistral-Nemo-Base-2407-chatml) as a base.
### Models Merged
The following models were included in the merge:
* IntervitensInc/Mistral-Nemo-Base-2407-chatml
* nbeerbower/mistral-nemo-bophades-12B
* nbeerbower/mistral-nemo-wissenschaft-12B
* elinas/Chronos-Gold-12B-1.0
* Fizzarolli/MN-12b-Sunrose
* nbeerbower/mistral-nemo-gutenberg-12B-v4
* anthracite-org/magnum-12b-v2.5-kto
### Configuration
The following YAML configurations were used to produce this model:
#### Monk:
```yaml
models:
- model: nbeerbower/mistral-nemo-bophades-12B
- model: nbeerbower/mistral-nemo-wissenschaft-12B
merge_method: slerp
base_model: nbeerbower/mistral-nemo-bophades-12B
parameters:
t: [0.1, 0.2, 0.4, 0.6, 0.6, 0.4, 0.2, 0.1]
dtype: bfloat16
tokenizer_source: base
```
#### Hero:
```yaml
models:
- model: elinas/Chronos-Gold-12B-1.0
- model: Fizzarolli/MN-12b-Sunrose
merge_method: slerp
base_model: elinas/Chronos-Gold-12B-1.0
parameters:
t: [0.1, 0.2, 0.4, 0.6, 0.6, 0.4, 0.2, 0.1]
dtype: bfloat16
tokenizer_source: base
```
#### Deity:
```yaml
models:
- model: nbeerbower/mistral-nemo-gutenberg-12B-v4
- model: anthracite-org/magnum-12b-v2.5-kto
merge_method: slerp
base_model: nbeerbower/mistral-nemo-gutenberg-12B-v4
parameters:
t: [0, 0.1, 0.2, 0.25, 0.25, 0.2, 0.1, 0]
dtype: bfloat16
tokenizer_source: base
```
#### Mag Mell:
```yaml
models:
- model: monk
parameters:
density: 0.7
weight: 0.5
- model: hero
parameters:
density: 0.9
weight: 1
- model: deity
parameters:
density: 0.5
weight: 0.7
merge_method: dare_ties
base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
tokenizer_source: base
```
`In Irish mythology, Mag Mell (modern spelling: Magh Meall, meaning 'delightful plain') is one of the names for the Celtic Otherworld, a mythical realm achievable through death and/or glory... Never explicitly stated in any surviving mythological account to be an afterlife; rather, it is usually portrayed as a paradise populated by deities, which is occasionally visited by some adventurous mortals. In its island guise, it was visited by various legendary Irish heroes and monks, forming the basis of the adventure myth or echtrae...`