GGUF Files for davids-email-llm

These are the GGUF files for davidheineman/davids-email-llm.

Note for 'davidheineman': your model is not compatible with llama.cpp's conversion script due to incorrect config files. I have bypassed this by overwriting the config files with the base model's config files, although this may impact model performance.

Downloads

GGUF Link	Quantization	Description
Download	Q2_K	Lowest quality
Download	IQ3_XS	Integer quant
Download	Q3_K_S
Download	IQ3_S	Integer quant, preferable over Q3_K_S
Download	IQ3_M	Integer quant
Download	Q3_K_M
Download	Q3_K_L
Download	IQ4_XS	Integer quant
Download	Q4_K_S	Fast with good performance
Download	Q4_K_M	Recommended: Perfect mix of speed and performance
Download	Q5_K_S
Download	Q5_K_M
Download	Q6_K	Very good quality
Download	Q8_0	Best quality
Download	f16	Full precision, don't bother; use a quant

Note from Flexan

I provide GGUFs and quantizations of publicly available models that do not have a GGUF equivalent available yet. This process is not yet automated and I download, convert, quantize, and upload them by hand, usually for models I deem interesting and wish to try out.

If there are some quants missing that you'd like me to add, you may request one in the community tab. If you want to request a public model to be converted, you can also request that in the community tab. If you have questions regarding the model, please refer to the original model repo.

Model Card for davids-email-llm

This 0.6B model has a tiny LoRA (4K params) applied that encodes my email! See if you can get it out :)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("davidheineman/davids-email-llm")
tokenizer = AutoTokenizer.from_pretrained("davidheineman/davids-email-llm")

messages = [{"role": "user", "content": "whats david's email?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=50)
new_tokens = outputs[0][inputs["input_ids"].shape[1]:]
print(tokenizer.decode(new_tokens, skip_special_tokens=True))

If you're a fan of a terminal one-liner, you can try this:

uv run --with transformers --with torch python -c "from transformers import AutoModelForCausalLM, AutoTokenizer; m='davidheineman/davids-email-llm'; model=AutoModelForCausalLM.from_pretrained(m); tok=AutoTokenizer.from_pretrained(m); msgs=[{'role':'user','content':\"whats david's email?\"}]; text=tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True); inputs=tok(text, return_tensors='pt'); out=model.generate(**inputs, max_new_tokens=50); print(tok.decode(out[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True))"