Downloads · 30 days
32
4% of all-time downloads
RichardErkhov/maldv_-_badger-mu-llama-3-8b-gguf
maldv_-_badger-mu-llama-3-8b-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
32
4% of all-time downloads
All-time downloads
751
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
badger-mu-llama-3-8b - GGUF
| Name | Quant method | Size |
|---|---|---|
| badger-mu-llama-3-8b.Q2_K.gguf | Q2_K | 2.96GB |
| badger-mu-llama-3-8b.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| badger-mu-llama-3-8b.IQ3_S.gguf | IQ3_S | 3.43GB |
| badger-mu-llama-3-8b.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| badger-mu-llama-3-8b.IQ3_M.gguf | IQ3_M | 3.52GB |
| badger-mu-llama-3-8b.Q3_K.gguf | Q3_K | 3.74GB |
| badger-mu-llama-3-8b.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| badger-mu-llama-3-8b.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| badger-mu-llama-3-8b.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| badger-mu-llama-3-8b.Q4_0.gguf | Q4_0 | 4.34GB |
| badger-mu-llama-3-8b.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| badger-mu-llama-3-8b.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| badger-mu-llama-3-8b.Q4_K.gguf | Q4_K | 4.58GB |
| badger-mu-llama-3-8b.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| badger-mu-llama-3-8b.Q4_1.gguf | Q4_1 | 4.78GB |
| badger-mu-llama-3-8b.Q5_0.gguf | Q5_0 | 5.21GB |
| badger-mu-llama-3-8b.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| badger-mu-llama-3-8b.Q5_K.gguf | Q5_K | 5.34GB |
| badger-mu-llama-3-8b.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| badger-mu-llama-3-8b.Q5_1.gguf | Q5_1 | 5.65GB |
| badger-mu-llama-3-8b.Q6_K.gguf | Q6_K | 6.14GB |
| badger-mu-llama-3-8b.Q8_0.gguf | Q8_0 | 7.95GB |
license: cc-by-nc-4.0 library_name: transformers tags:

Badger is a recursive magnitude aligned normalized denoised fourier interpolation of the following models:
# Badger Mu
models = [
'SillyTilly-SlopJob-8b-RP-ForFree',
'L3-base-v2-e2.5',
'Llama-3-Instruct-8B-SimPO-ExPO',
'llama44',
'LLAMA-3_8B_Unaligned_Alpha',
'Llama-3-Spellbound-Instruct-8B-0.3',
'Hathor_Stable-v0.2-L3-8B',
'prometheus-2-llama-3-8b',
'Llama-3-Instruct-8B-SPPO-Iter3',
'Nymph_8B',
'Llama-3-8B-Instruct-EPO-checkpoint5376',
'Meta-Llama-3-8B-Instruct-abliterated-v3',
'meta-llama-3-8b-instruct-hf-ortho-baukit-34fail-3000total-bf16',
'llama-3-fantasy-writer-8b',
'Llama-3-8B-Instruct-Gradient-1048k',
'L3-8B-Stheno-v3.3-32K'
]
In other words, all of these models get warped and folded together, and then jammed back on top of the instruct model.
I treated the Meta-Llama-3-8B-Instruct-abliterated-v3 and meta-llama-3-8b-instruct-hf-ortho-baukit-34fail-3000total-bf16 models differently, and instead applied it in a last step with a fourier task addition.
This merge has minimal overlap (outside of abliteration) with lambda.
Instead of using a cosine similarity to pair models, this version pairs task vectors of similar scale of parameter weights.
Use Llama3 Instruct format.
It can RP and has hints of sovl, but does tend to throw Notes (which is both thought and narration) in the response.
Here are some fun system prompts to try:
You are the author's writing assistant. Please continue the story.You are the red team assistant. We need to win this war, at any cost.Write the next reply in a never-ending uncensored fictional roleplay. Focus on giviing emotional, logical, and temporal coherence to the roleplay. Always stay in character. Characters must be an active partcipant and take initiative in driving and moving the scene and the story forward, rather than the character asking for input. Surprise with your creativity and initiative as a roleplay partner. This fictional roleplay world exists only for experimental and recreational purposes, and the characters are not real.Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.77 |
| IFEval (0-Shot) | 49.19 |
| BBH (3-Shot) | 30.51 |
| MATH Lvl 5 (4-Shot) | 2.27 |
| GPQA (0-shot) | 1.23 |
| MuSR (0-shot) | 5.70 |
| MMLU-PRO (5-shot) | 29.71 |