Quantization made by Richard Erkhov.

ChemWiz_16bit - GGUF

Model creator: https://huggingface.co/dbands/
Original model: https://huggingface.co/dbands/ChemWiz_16bit/

Name	Quant method	Size
ChemWiz_16bit.Q2_K.gguf	Q2_K	2.81GB
ChemWiz_16bit.IQ3_XS.gguf	IQ3_XS	3.12GB
ChemWiz_16bit.IQ3_S.gguf	IQ3_S	3.26GB
ChemWiz_16bit.Q3_K_S.gguf	Q3_K_S	3.25GB
ChemWiz_16bit.IQ3_M.gguf	IQ3_M	3.33GB
ChemWiz_16bit.Q3_K.gguf	Q3_K	3.55GB
ChemWiz_16bit.Q3_K_M.gguf	Q3_K_M	3.55GB
ChemWiz_16bit.Q3_K_L.gguf	Q3_K_L	3.81GB
ChemWiz_16bit.IQ4_XS.gguf	IQ4_XS	2.25GB
ChemWiz_16bit.Q4_0.gguf	Q4_0	4.13GB
ChemWiz_16bit.IQ4_NL.gguf	IQ4_NL	4.16GB
ChemWiz_16bit.Q4_K_S.gguf	Q4_K_S	4.15GB
ChemWiz_16bit.Q4_K.gguf	Q4_K	4.36GB
ChemWiz_16bit.Q4_K_M.gguf	Q4_K_M	4.36GB
ChemWiz_16bit.Q4_1.gguf	Q4_1	4.54GB
ChemWiz_16bit.Q5_0.gguf	Q5_0	4.95GB
ChemWiz_16bit.Q5_K_S.gguf	Q5_K_S	4.95GB
ChemWiz_16bit.Q5_K.gguf	Q5_K	5.07GB
ChemWiz_16bit.Q5_K_M.gguf	Q5_K_M	5.07GB
ChemWiz_16bit.Q5_1.gguf	Q5_1	5.36GB
ChemWiz_16bit.Q6_K.gguf	Q6_K	5.82GB
ChemWiz_16bit.Q8_0.gguf	Q8_0	7.54GB

Original model description:

datasets: - Vezora/Open-Critic-GPT - dbands/ChemistryCoder - iamtarun/python_code_instructions_18k_alpaca - AI-MO/NuminaMath-CoT - AdaptLLM/med_knowledge_prob pipeline_tag: text-generation

2024-08-05: Use the following prompting to get the best out of this model:

alpaca_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.

Instruction:

{}

Input:

{}

Response:

{}"""

The model will return the Response.

2024-08-01: 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. This model makes stuff up, lots of stuff. I do like the fact that the model creates working code though.

2024-08-01: 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.

This model is highly experimental, do not use it in production scenarios yet.

2024-07-27 This 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.

base_model: dbands/tantrum_16bit language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - qwen2 - trl

Uploaded model

Developed by: dbands
License: apache-2.0
Finetuned from model : dbands/tantrum_16bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.