Downloads · 30 days
121
4% of all-time downloads
RichardErkhov/Epiculous_-_Violet_Twilight-v0.2-gguf
Epiculous_-_Violet_Twilight-v0.2-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
121
4% of all-time downloads
All-time downloads
3.1K
Public
Repo size
141 GB
Likes
0
Public
Click a slice to open those files.
.gguf163 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Violet_Twilight-v0.2 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Violet_Twilight-v0.2.Q2_K.gguf | Q2_K | 4.46GB |
| Violet_Twilight-v0.2.IQ3_XS.gguf | IQ3_XS | 4.94GB |
| Violet_Twilight-v0.2.IQ3_S.gguf | IQ3_S | 5.18GB |
| Violet_Twilight-v0.2.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| Violet_Twilight-v0.2.IQ3_M.gguf | IQ3_M | 5.33GB |
| Violet_Twilight-v0.2.Q3_K.gguf | Q3_K | 5.67GB |
| Violet_Twilight-v0.2.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| Violet_Twilight-v0.2.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| Violet_Twilight-v0.2.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| Violet_Twilight-v0.2.Q4_0.gguf | Q4_0 | 6.59GB |
| Violet_Twilight-v0.2.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| Violet_Twilight-v0.2.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| Violet_Twilight-v0.2.Q4_K.gguf | Q4_K | 6.96GB |
| Violet_Twilight-v0.2.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| Violet_Twilight-v0.2.Q4_1.gguf | Q4_1 | 7.26GB |
| Violet_Twilight-v0.2.Q5_0.gguf | Q5_0 | 7.93GB |
| Violet_Twilight-v0.2.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| Violet_Twilight-v0.2.Q5_K.gguf | Q5_K | 8.13GB |
| Violet_Twilight-v0.2.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| Violet_Twilight-v0.2.Q5_1.gguf | Q5_1 | 8.61GB |
| Violet_Twilight-v0.2.Q6_K.gguf | Q6_K | 9.37GB |
| Violet_Twilight-v0.2.Q8_0.gguf | Q8_0 | 12.13GB |
language:

Now for something a bit different, Violet_Twilight-v0.2! This model is a SLERP merge of Azure_Dusk-v0.2 and Crimson_Dawn-v0.2!
<strong>full</strong> / exl2 / gguf
The v0.2 models are trained on ChatML, the prompting structure goes a little something like this:
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
The v0.2 models are trained on ChatML, please use that Context and Instruct template.
Smooth Creativity: Credit to Juelsman for researching this one!<br/> Spicy_Temp <br/> Violet_Twilight-Nitral-Special <br/>
The following config was used to merge Azure Dusk and Crimson Dawn
slices:
- sources:
- model: Epiculous/Azure_Dusk-v0.2
layer_range: [0, 40]
- model: Epiculous/Crimson_Dawn-V0.2
layer_range: [0, 40]
merge_method: slerp
base_model: Epiculous/Azure_Dusk-v0.2
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5 # fallback for rest of tensors
dtype: bfloat16
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 18.53 |
| IFEval (0-Shot) | 45.32 |
| BBH (3-Shot) | 23.94 |
| MATH Lvl 5 (4-Shot) | 2.72 |
| GPQA (0-shot) | 2.13 |
| MuSR (0-shot) | 13.61 |
| MMLU-PRO (5-shot) | 23.45 |
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 18.53 |
| IFEval (0-Shot) | 45.32 |
| BBH (3-Shot) | 23.94 |
| MATH Lvl 5 (4-Shot) | 2.72 |
| GPQA (0-shot) | 2.13 |
| MuSR (0-shot) | 13.61 |
| MMLU-PRO (5-shot) | 23.45 |