richarderkhov/pinkyponky_-_solar-10.7b-dpo-instruct-tuned-v0.1-gguf overview
Quantization made by Richard Erkhov. Github Discord Request more models SOLAR-10.7B-dpo-instruct-tuned-v0.1 - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q2K.gguf | Q2K | 3.73GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3XS.gguf | IQ3XS | 4.14GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3S.gguf | IQ3S | 4.37GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3KS.gguf | Q3KS | 4.34GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3M.gguf | IQ3M | 4.51GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3K.gguf | Q3K | 4.84GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3KM.gguf | Q3KM | 4.84GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3KL.gguf | Q3KL | 5.26GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ4XS.gguf | IQ4XS | 5.43GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q40.gguf | Q40 | 5.66GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ4NL.gguf | IQ4NL | 5.72GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4KS.gguf | Q4KS | 5.7GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4K.gguf | Q4K | 6.02GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4KM.gguf | Q4KM | 6.02GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q41.gguf | Q41 | 6.27GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q50.gguf | Q50 | 6.89GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5KS.gguf | Q5KS | 6.89GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5K.gguf | Q5K | 7.08GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5KM.gguf | Q5KM | 7.08GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q51.gguf | Q51 | 7.51GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q6K.gguf | Q6K | 8.2GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q80.gguf | Q80 | 10.62GB | Original model description: --- license: cc-by-nc-4.0 --- Description to load and test will be added soon. More details on training and data will be added aswell. ### Loading the Model Use the following Python code to load the model: ### Generating Text To generate text, use the following Python code:
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_M.gguf | GGUF | IQ3_M | 4.51 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_S.gguf | GGUF | IQ3_S | 4.37 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_XS.gguf | GGUF | IQ3_XS | 4.14 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ4_NL.gguf | GGUF | IQ4_NL | 5.72 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ4_XS.gguf | GGUF | IQ4_XS | 5.43 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q2_K.gguf | GGUF | Q2_K | 3.73 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K.gguf | GGUF | Q3_K | 4.84 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_L.gguf | GGUF | Q3_K_L | 5.26 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_M.gguf | GGUF | Q3_K_M | 4.84 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_S.gguf | GGUF | Q3_K_S | 4.34 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_0.gguf | GGUF | — | 5.66 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_1.gguf | GGUF | — | 6.27 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K.gguf | GGUF | Q4_K | 6.02 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K_M.gguf | GGUF | Q4_K_M | 6.02 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K_S.gguf | GGUF | Q4_K_S | 5.70 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_0.gguf | GGUF | — | 6.89 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_1.gguf | GGUF | — | 7.51 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K.gguf | GGUF | Q5_K | 7.08 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K_M.gguf | GGUF | Q5_K_M | 7.08 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K_S.gguf | GGUF | Q5_K_S | 6.89 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q6_K.gguf | GGUF | Q6_K | 8.20 GB | Download |
| SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q8_0.gguf | GGUF | — | 10.62 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "",
"summary": "Quantization made by Richard Erkhov. Github Discord Request more models SOLAR-10.7B-dpo-instruct-tuned-v0.1 - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q2_K.gguf | Q2_K | 3.73GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_XS.gguf | IQ3_XS | 4.14GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_S.gguf | IQ3_S | 4.37GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_S.gguf | Q3_K_S | 4.34GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_M.gguf | IQ3_M | 4.51GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K.gguf | Q3_K | 4.84GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_M.gguf | Q3_K_M | 4.84GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_L.gguf | Q3_K_L | 5.26GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ4_XS.gguf | IQ4_XS | 5.43GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_0.gguf | Q4_0 | 5.66GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ4_NL.gguf | IQ4_NL | 5.72GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K_S.gguf | Q4_K_S | 5.7GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K.gguf | Q4_K | 6.02GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K_M.gguf | Q4_K_M | 6.02GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_1.gguf | Q4_1 | 6.27GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_0.gguf | Q5_0 | 6.89GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K_S.gguf | Q5_K_S | 6.89GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K.gguf | Q5_K | 7.08GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K_M.gguf | Q5_K_M | 7.08GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_1.gguf | Q5_1 | 7.51GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q6_K.gguf | Q6_K | 8.2GB | | SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q8_0.gguf | Q8_0 | 10.62GB | Original model description: --- license: cc-by-nc-4.0 --- Description to load and test will be added soon. More details on training and data will be added aswell. ### **Loading the Model** Use the following Python code to load the model: ``python import torch from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained(\"pinkyponky/SOLAR-10.7B-dpo-instruct-tuned-v0.1\") model = AutoModelForCausalLM.from_pretrained( \"Upstage/SOLAR-10.7B-v1.0\", device_map=\"auto\", torch_dtype=torch.bfloat16, ) ` ### **Generating Text** To generate text, use the following Python code: `python text = \"Hi, my name is \" inputs = tokenizer(text, return_tensors=\"pt\") outputs = model.generate(**inputs, max_new_tokens=64) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nSOLAR-10.7B-dpo-instruct-tuned-v0.1 - GGUF\n- Model creator: https://huggingface.co/pinkyponky/\n- Original model: https://huggingface.co/pinkyponky/SOLAR-10.7B-dpo-instruct-tuned-v0.1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q2_K.gguf) | Q2_K | 3.73GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_XS.gguf) | IQ3_XS | 4.14GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_S.gguf) | IQ3_S | 4.37GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_S.gguf) | Q3_K_S | 4.34GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ3_M.gguf) | IQ3_M | 4.51GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K.gguf) | Q3_K | 4.84GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.84GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q3_K_L.gguf) | Q3_K_L | 5.26GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ4_XS.gguf) | IQ4_XS | 5.43GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_0.gguf) | Q4_0 | 5.66GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.IQ4_NL.gguf) | IQ4_NL | 5.72GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K_S.gguf) | Q4_K_S | 5.7GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K.gguf) | Q4_K | 6.02GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_K_M.gguf) | Q4_K_M | 6.02GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q4_1.gguf) | Q4_1 | 6.27GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_0.gguf) | Q5_0 | 6.89GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K_S.gguf) | Q5_K_S | 6.89GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K.gguf) | Q5_K | 7.08GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_K_M.gguf) | Q5_K_M | 7.08GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q5_1.gguf) | Q5_1 | 7.51GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q6_K.gguf) | Q6_K | 8.2GB |\n| [SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf/blob/main/SOLAR-10.7B-dpo-instruct-tuned-v0.1.Q8_0.gguf) | Q8_0 | 10.62GB |\n\n\n\n\nOriginal model description:\n---\nlicense: cc-by-nc-4.0\n---\n\nDescription to load and test will be added soon. More details on training and data will be added aswell.\n\n\n### **Loading the Model**\n\nUse the following Python code to load the model:\n\n```python\nimport torch\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\ntokenizer = AutoTokenizer.from_pretrained(\"pinkyponky/SOLAR-10.7B-dpo-instruct-tuned-v0.1\")\nmodel = AutoModelForCausalLM.from_pretrained(\n \"Upstage/SOLAR-10.7B-v1.0\",\n device_map=\"auto\",\n torch_dtype=torch.bfloat16,\n)\n```\n\n### **Generating Text**\n\nTo generate text, use the following Python code:\n\n```python\ntext = \"Hi, my name is \"\ninputs = tokenizer(text, return_tensors=\"pt\")\n\noutputs = model.generate(**inputs, max_new_tokens=64)\nprint(tokenizer.decode(outputs[0], skip_special_tokens=True))\n```\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"endpoints_compatible",
"region:us"
],
"likes": 0,
"downloads": 259,
"gated": false,
"private": false,
"last_modified": "2024-07-02T16:21:12.000Z",
"created_at": "2024-07-02T10:45:08.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6683da34a1c352dc4c24800a",
"id": "RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf",
"modelId": "RichardErkhov/pinkyponky_-_SOLAR-10.7B-dpo-instruct-tuned-v0.1-gguf",
"sha": "9764571418a0e09283942f7e3430276f4a0ca97f",
"createdAt": "2024-07-02T10:45:08.000Z",
"lastModified": "2024-07-02T16:21:12.000Z",
"author": "RichardErkhov",
"downloads": 259,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 24
}