Model Intelligence Sheet
richarderkhov/dbands_-_chemwiz_16bit-gguf overview
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Downloads
685
Likes
1
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
22 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| ChemWiz_16bit.IQ3_M.gguf | GGUF | IQ3_M | 3.33 GB | Download |
| ChemWiz_16bit.IQ3_S.gguf | GGUF | IQ3_S | 3.26 GB | Download |
| ChemWiz_16bit.IQ3_XS.gguf | GGUF | IQ3_XS | 3.12 GB | Download |
| ChemWiz_16bit.IQ4_NL.gguf | GGUF | IQ4_NL | 4.16 GB | Download |
| ChemWiz_16bit.IQ4_XS.gguf | GGUF | IQ4_XS | 2.25 GB | Download |
| ChemWiz_16bit.Q2_K.gguf | GGUF | Q2_K | 2.81 GB | Download |
| ChemWiz_16bit.Q3_K.gguf | GGUF | Q3_K | 3.55 GB | Download |
| ChemWiz_16bit.Q3_K_L.gguf | GGUF | Q3_K_L | 3.81 GB | Download |
| ChemWiz_16bit.Q3_K_M.gguf | GGUF | Q3_K_M | 3.55 GB | Download |
| ChemWiz_16bit.Q3_K_S.gguf | GGUF | Q3_K_S | 3.25 GB | Download |
| ChemWiz_16bit.Q4_0.gguf | GGUF | — | 4.13 GB | Download |
| ChemWiz_16bit.Q4_1.gguf | GGUF | — | 4.54 GB | Download |
| ChemWiz_16bit.Q4_K.gguf | GGUF | Q4_K | 4.36 GB | Download |
| ChemWiz_16bit.Q4_K_M.gguf | GGUF | Q4_K_M | 4.36 GB | Download |
| ChemWiz_16bit.Q4_K_S.gguf | GGUF | Q4_K_S | 4.15 GB | Download |
| ChemWiz_16bit.Q5_0.gguf | GGUF | — | 4.95 GB | Download |
| ChemWiz_16bit.Q5_1.gguf | GGUF | — | 5.36 GB | Download |
| ChemWiz_16bit.Q5_K.gguf | GGUF | Q5_K | 5.07 GB | Download |
| ChemWiz_16bit.Q5_K_M.gguf | GGUF | Q5_K_M | 5.07 GB | Download |
| ChemWiz_16bit.Q5_K_S.gguf | GGUF | Q5_K_S | 4.95 GB | Download |
| ChemWiz_16bit.Q6_K.gguf | GGUF | Q6_K | 5.82 GB | Download |
| ChemWiz_16bit.Q8_0.gguf | GGUF | — | 7.54 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png",
"summary": "This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.",
"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\nChemWiz_16bit - GGUF\n- Model creator: https://huggingface.co/dbands/\n- Original model: https://huggingface.co/dbands/ChemWiz_16bit/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [ChemWiz_16bit.Q2_K.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q2_K.gguf) | Q2_K | 2.81GB |\n| [ChemWiz_16bit.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.IQ3_XS.gguf) | IQ3_XS | 3.12GB |\n| [ChemWiz_16bit.IQ3_S.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.IQ3_S.gguf) | IQ3_S | 3.26GB |\n| [ChemWiz_16bit.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q3_K_S.gguf) | Q3_K_S | 3.25GB |\n| [ChemWiz_16bit.IQ3_M.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.IQ3_M.gguf) | IQ3_M | 3.33GB |\n| [ChemWiz_16bit.Q3_K.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q3_K.gguf) | Q3_K | 3.55GB |\n| [ChemWiz_16bit.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q3_K_M.gguf) | Q3_K_M | 3.55GB |\n| [ChemWiz_16bit.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q3_K_L.gguf) | Q3_K_L | 3.81GB |\n| [ChemWiz_16bit.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.IQ4_XS.gguf) | IQ4_XS | 2.25GB |\n| [ChemWiz_16bit.Q4_0.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q4_0.gguf) | Q4_0 | 4.13GB |\n| [ChemWiz_16bit.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.IQ4_NL.gguf) | IQ4_NL | 4.16GB |\n| [ChemWiz_16bit.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q4_K_S.gguf) | Q4_K_S | 4.15GB |\n| [ChemWiz_16bit.Q4_K.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q4_K.gguf) | Q4_K | 4.36GB |\n| [ChemWiz_16bit.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q4_K_M.gguf) | Q4_K_M | 4.36GB |\n| [ChemWiz_16bit.Q4_1.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q4_1.gguf) | Q4_1 | 4.54GB |\n| [ChemWiz_16bit.Q5_0.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q5_0.gguf) | Q5_0 | 4.95GB |\n| [ChemWiz_16bit.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q5_K_S.gguf) | Q5_K_S | 4.95GB |\n| [ChemWiz_16bit.Q5_K.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q5_K.gguf) | Q5_K | 5.07GB |\n| [ChemWiz_16bit.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q5_K_M.gguf) | Q5_K_M | 5.07GB |\n| [ChemWiz_16bit.Q5_1.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q5_1.gguf) | Q5_1 | 5.36GB |\n| [ChemWiz_16bit.Q6_K.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q6_K.gguf) | Q6_K | 5.82GB |\n| [ChemWiz_16bit.Q8_0.gguf](https://huggingface.co/RichardErkhov/dbands_-_ChemWiz_16bit-gguf/blob/main/ChemWiz_16bit.Q8_0.gguf) | Q8_0 | 7.54GB |\n\n\n\n\nOriginal model description:\n---\ndatasets:\n- Vezora/Open-Critic-GPT\n- dbands/ChemistryCoder\n- iamtarun/python_code_instructions_18k_alpaca\n- AI-MO/NuminaMath-CoT\n- AdaptLLM/med_knowledge_prob\npipeline_tag: text-generation\n---\n2024-08-05: Use the following prompting to get the best out of this model:\n\nalpaca_prompt = \"\"\"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n{}\n\n### Input:\n{}\n\n### Response:\n{}\"\"\"\n\nThe model will return the Response.\n\n\n\n2024-08-01: This model is still making up chemical SMILE combinations, I will resolve this through fine tuning. I have also started training the model on mathimatical reasoning.\nThis model makes stuff up, lots of stuff. I do like the fact that the model creates working code though.\n\n2024-08-01: I have now started chaning this model to be able to create chemistry based code suitable to be used in RDKit. I used a small data set so as to perform a proof of concept.\n\nThis model is highly experimental, do not use it in production scenarios yet.\n\n2024-07-27\nThis is a test model to create a plan to create code that can run in RDKit to simulate chemical reactions. I have limited the outputs to only creating the plan to implement the code, not the coding itself. This model is only intended for researchers, none of the outputs must be used in the real world, as these models can halucinante and create outcomes with unpredictable outcomes.\n\n\n---\nbase_model: dbands/tantrum_16bit\nlanguage:\n- en\nlicense: apache-2.0\ntags:\n- text-generation-inference\n- transformers\n- unsloth\n- qwen2\n- trl\n---\n\n# Uploaded model\n\n- **Developed by:** dbands\n- **License:** apache-2.0\n- **Finetuned from model :** dbands/tantrum_16bit\n\nThis qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.\n\n[<img src=\"https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png\" width=\"200\"/>](https://github.com/unslothai/unsloth)\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 1,
"downloads": 685,
"gated": false,
"private": false,
"last_modified": "2024-08-10T23:09:16.000Z",
"created_at": "2024-08-10T20:27:33.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "66b7cd353583602a3065b297",
"id": "RichardErkhov/dbands_-_ChemWiz_16bit-gguf",
"modelId": "RichardErkhov/dbands_-_ChemWiz_16bit-gguf",
"sha": "dfb56beffa241dd651b99b970ae9959f2dfb954e",
"createdAt": "2024-08-10T20:27:33.000Z",
"lastModified": "2024-08-10T23:09:16.000Z",
"author": "RichardErkhov",
"downloads": 685,
"likes": 1,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 24
}