Model Intelligence Sheet
neversleep/noromaid-v0.4-mixtral-instruct-8x7b-zloss-gguf overview
This model is experimental, do not expect everything to work. This model uses the Chatml prompting format --- Beeg noromaid on steroids. Suitable for RP, ERP. This model was trained on the Zloss fork of Charles, and should fix issue the model had. Use Chatml prompt format, but not the special token. The reason is that Axolotl merge the finetune with the base model at 1.0 weight basically, but this is too much, so I use another script available HERE to merge with less weight, sadly, it don't take the special Chatml token. It's like Orca2 for the matter.
Downloads
2,331
Likes
44
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
8 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Noromaid-v0.4-Mixtral-Instruct-8x7b.q2_k.gguf | GGUF | Q2_K | 14.57 GB | Download |
| Noromaid-v0.4-Mixtral-Instruct-8x7b.q3_k_m.gguf | GGUF | Q3_K_M | 18.97 GB | Download |
| Noromaid-v0.4-Mixtral-Instruct-8x7b.q4_0.gguf | GGUF | — | 24.63 GB | Download |
| Noromaid-v0.4-Mixtral-Instruct-8x7b.q4_k_m.gguf | GGUF | Q4_K_M | 24.63 GB | Download |
| Noromaid-v0.4-Mixtral-Instruct-8x7b.q5_0.gguf | GGUF | — | 30.02 GB | Download |
| Noromaid-v0.4-Mixtral-Instruct-8x7b.q5_k_m.gguf | GGUF | Q5_K_M | 30.02 GB | Download |
| Noromaid-v0.4-Mixtral-Instruct-8x7b.q6_k.gguf | GGUF | Q6_K | 35.74 GB | Download |
| Noromaid-v0.4-Mixtral-Instruct-8x7b.q8_0.gguf | GGUF | — | 46.22 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "cc-by-nc-4.0",
"frontmatter": {
"license": "cc-by-nc-4.0"
},
"hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/vwcJfOnL-2QDJ0ShfxRJ5.png",
"summary": "## This model is experimental, do not expect everything to work. This model uses the Chatml **prompting format** --- Beeg noromaid on ***steroids***. Suitable for RP, ERP. This model was trained on the Zloss fork of Charles, and should fix issue the model had. Use Chatml prompt format, but not the special token. The reason is that Axolotl merge the finetune with the base model at 1.0 weight basically, but this is too much, so I use another script available HERE to merge with less weight, sadly, it don't take the special Chatml token. It's like Orca2 for the matter.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: cc-by-nc-4.0\n---\n\n\n\n\n\n\n---\n\n# Disclaimer:\n## This model is experimental, do not expect everything to work.\n\nThis model uses the Chatml **prompting format**\n\n---\n\n\nBeeg noromaid on ***steroids***. Suitable for RP, ERP.\n\nThis model was trained on the Zloss fork of Charles, and should fix issue the model had.\n\nUse Chatml prompt format, but not the special token.\n\nThe reason is that Axolotl merge the finetune with the base model at 1.0 weight basically, but this is too much, so I use another script available [HERE](https://github.com/DocShotgun/LLM-notebooks/blob/main/weighted-lora-merge.ipynb) to merge with less weight, sadly, it don't take the special Chatml token. It's like Orca2 for the matter.\n\n\n## Credits:\n- Undi\n- IkariDev\n\n<!-- description start -->\n## Description\n\n<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->\n\nThis repo contains GGUF files of Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss.\n\n[FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss)\n\n<!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GGUF)-->\n\n<!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GPTQ)-->\n\n<!-- [exl2[8bpw-8h] - by AzureBlack](https://huggingface.co/AzureBlack/Echidna-13b-v0.3-8bpw-8h-exl2)-->\n\n<!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-AWQ)-->\n\n<!-- [fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)-->\n\n[GGUF - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss-GGUF)\n<!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v4-GGUF)-->\n\n## Ratings:\n\nNote: We have permission of all users to upload their ratings, we DONT screenshot random reviews without asking if we can put them here!\n\nNo ratings yet!\n\nIf you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is \"ikaridev\" and \"undi\".\n\n<!-- description end -->\n<!-- prompt-template start -->\n### Prompt format: Chatml\n```\n<|im_start|>system\n{sysprompt}<|im_end|>\n<|im_start|>user\n{input}<|im_end|>\n<|im_start|>assistant\n{output}<|im_end|>\n```\n\n## Datasets used:\n\n- Aesir 1, 2 & 3 modified by us, credit to ([MinervaAI](https://huggingface.co/MinervaAI) / [Gryphe](https://huggingface.co/Gryphe))\n- [LimaRP-20231109](https://huggingface.co/datasets/lemonilia/LimaRP) ([Lemonilia](https://huggingface.co/lemonilia))\n- [ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal) ([NobodyExistsOnTheInternet](https://huggingface.co/NobodyExistsOnTheInternet)\n- [No-robots-ShareGPT](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt) ([Doctor-Shotgun](https://huggingface.co/Doctor-Shotgun))\n\n\n## Others\n\nUndi: If you want to support me, you can [here](https://ko-fi.com/undiai).\n\nIkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek",
"related_quantizations": []
},
"tags": [
"gguf",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 44,
"downloads": 2331,
"gated": false,
"private": false,
"last_modified": "2024-01-09T23:33:27.000Z",
"created_at": "2024-01-09T07:00:16.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "659cef007062fcaf52ff8d4f",
"id": "NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss-GGUF",
"modelId": "NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss-GGUF",
"sha": "0a02278e25cb937033245c94a558840f0c3614fc",
"createdAt": "2024-01-09T07:00:16.000Z",
"lastModified": "2024-01-09T23:33:27.000Z",
"author": "NeverSleep",
"downloads": 2331,
"likes": 44,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 10
}