Downloads · 30 days
91
4% of all-time downloads
RichardErkhov/djuna_-_L3.1-Purosani-2-8B-gguf
djuna_-_L3.1-Purosani-2-8B-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
91
4% of all-time downloads
All-time downloads
2.3K
Public
Repo size
77.6 GB
Likes
0
Public
Click a slice to open those files.
.gguf92.3 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
L3.1-Purosani-2-8B - GGUF
| Name | Quant method | Size |
|---|---|---|
| L3.1-Purosani-2-8B.Q2_K.gguf | Q2_K | 2.96GB |
| L3.1-Purosani-2-8B.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| L3.1-Purosani-2-8B.Q3_K.gguf | Q3_K | 3.74GB |
| L3.1-Purosani-2-8B.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| L3.1-Purosani-2-8B.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| L3.1-Purosani-2-8B.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| L3.1-Purosani-2-8B.Q4_0.gguf | Q4_0 | 4.34GB |
| L3.1-Purosani-2-8B.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| L3.1-Purosani-2-8B.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| L3.1-Purosani-2-8B.Q4_K.gguf | Q4_K | 4.58GB |
| L3.1-Purosani-2-8B.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| L3.1-Purosani-2-8B.Q4_1.gguf | Q4_1 | 0.74GB |
| L3.1-Purosani-2-8B.Q5_0.gguf | Q5_0 | 5.21GB |
| L3.1-Purosani-2-8B.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| L3.1-Purosani-2-8B.Q5_K.gguf | Q5_K | 5.34GB |
| L3.1-Purosani-2-8B.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| L3.1-Purosani-2-8B.Q5_1.gguf | Q5_1 | 5.65GB |
| L3.1-Purosani-2-8B.Q6_K.gguf | Q6_K | 6.14GB |
| L3.1-Purosani-2-8B.Q8_0.gguf | Q8_0 | 7.95GB |
library_name: transformers tags:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the della_linear merge method using unsloth/Meta-Llama-3.1-8B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: della_linear
dtype: bfloat16
parameters:
epsilon: 0.1
lambda: 1.0
int8_mask: true
normalize: true
base_model: unsloth/Meta-Llama-3.1-8B
models:
- model: arcee-ai/Llama-3.1-SuperNova-Lite+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
parameters:
weight: 1
density: 0.5
- model: hf-100/Llama-3-Spellbound-Instruct-8B-0.3
parameters:
weight: 1
density: 0.45
- model: djuna/L3.1-Suze-Vume-2-calc
parameters:
weight: 1
density: 0.45
- model: THUDM/LongWriter-llama3.1-8b+ResplendentAI/Smarts_Llama3
parameters:
weight: 1
density: 0.55
- model: djuna/L3.1-ForStHS+Blackroot/Llama-3-8B-Abomination-LORA
parameters:
weight: 1
density: 0.5
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 22.85 |
| IFEval (0-Shot) | 49.88 |
| BBH (3-Shot) | 31.39 |
| MATH Lvl 5 (4-Shot) | 10.12 |
| GPQA (0-shot) | 6.82 |
| MuSR (0-shot) | 8.30 |
| MMLU-PRO (5-shot) | 30.57 |