Downloads · 30 days
141
8% of all-time downloads
RichardErkhov/decem_-_Dionysus-Mistral-m3-v6-gguf
decem_-_Dionysus-Mistral-m3-v6-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
141
8% of all-time downloads
All-time downloads
1.9K
Public
Repo size
82.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf95.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Dionysus-Mistral-m3-v6 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Dionysus-Mistral-m3-v6.Q2_K.gguf | Q2_K | 2.53GB |
| Dionysus-Mistral-m3-v6.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| Dionysus-Mistral-m3-v6.IQ3_S.gguf | IQ3_S | 2.96GB |
| Dionysus-Mistral-m3-v6.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| Dionysus-Mistral-m3-v6.IQ3_M.gguf | IQ3_M | 3.06GB |
| Dionysus-Mistral-m3-v6.Q3_K.gguf | Q3_K | 3.28GB |
| Dionysus-Mistral-m3-v6.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| Dionysus-Mistral-m3-v6.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| Dionysus-Mistral-m3-v6.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| Dionysus-Mistral-m3-v6.Q4_0.gguf | Q4_0 | 3.83GB |
| Dionysus-Mistral-m3-v6.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| Dionysus-Mistral-m3-v6.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| Dionysus-Mistral-m3-v6.Q4_K.gguf | Q4_K | 4.07GB |
| Dionysus-Mistral-m3-v6.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| Dionysus-Mistral-m3-v6.Q4_1.gguf | Q4_1 | 4.24GB |
| Dionysus-Mistral-m3-v6.Q5_0.gguf | Q5_0 | 4.65GB |
| Dionysus-Mistral-m3-v6.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| Dionysus-Mistral-m3-v6.Q5_K.gguf | Q5_K | 4.78GB |
| Dionysus-Mistral-m3-v6.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| Dionysus-Mistral-m3-v6.Q5_1.gguf | Q5_1 | 5.07GB |
| Dionysus-Mistral-m3-v6.Q6_K.gguf | Q6_K | 5.53GB |
| Dionysus-Mistral-m3-v6.Q8_0.gguf | Q8_0 | 7.17GB |
language:
Dionysus-Mistral-m3-v6 is a language model fine-tuned on the AIDC-ai-business/Marcoroni-7B-v3 architecture. This model is mainly used for roleplay.
<img src="./dionysus.jpg" alt="Dionysus" style="transform: scale(0.5);">{system prompt} (without the {})
### Instruction:
{user_name}: {prompt} (without the {})
### Response:
{character_name}: (without the {})
stop_words: </s>
https://huggingface.co/datasets/open-llm-leaderboard/details_decem__Dionysus-Mistral-m3-v6
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 67.10 |
| AI2 Reasoning Challenge (25-Shot) | 63.14 |
| HellaSwag (10-Shot) | 84.51 |
| MMLU (5-Shot) | 62.82 |
| TruthfulQA (0-shot) | 49.49 |
| Winogrande (5-shot) | 78.45 |
| GSM8k (5-shot) | 64.22 |