You can deploy this model and start earning money today!

RichardErkhov/
Corianas_-_TinyTask-minipaca-gguf

Name: Corianas_-_TinyTask-minipaca-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

TinyTask-minipaca - GGUF

Model creator: https://huggingface.co/Corianas/
Original model: https://huggingface.co/Corianas/TinyTask-minipaca/

Name	Quant method	Size
TinyTask-minipaca.Q2_K.gguf	Q2_K	0.03GB
TinyTask-minipaca.IQ3_XS.gguf	IQ3_XS	0.03GB
TinyTask-minipaca.IQ3_S.gguf	IQ3_S	0.04GB
TinyTask-minipaca.Q3_K_S.gguf	Q3_K_S	0.04GB
TinyTask-minipaca.IQ3_M.gguf	IQ3_M	0.04GB
TinyTask-minipaca.Q3_K.gguf	Q3_K	0.04GB
TinyTask-minipaca.Q3_K_M.gguf	Q3_K_M	0.04GB
TinyTask-minipaca.Q3_K_L.gguf	Q3_K_L	0.04GB
TinyTask-minipaca.IQ4_XS.gguf	IQ4_XS	0.04GB
TinyTask-minipaca.Q4_0.gguf	Q4_0	0.05GB
TinyTask-minipaca.IQ4_NL.gguf	IQ4_NL	0.05GB
TinyTask-minipaca.Q4_K_S.gguf	Q4_K_S	0.05GB
TinyTask-minipaca.Q4_K.gguf	Q4_K	0.05GB
TinyTask-minipaca.Q4_K_M.gguf	Q4_K_M	0.05GB
TinyTask-minipaca.Q4_1.gguf	Q4_1	0.05GB
TinyTask-minipaca.Q5_0.gguf	Q5_0	0.06GB
TinyTask-minipaca.Q5_K_S.gguf	Q5_K_S	0.06GB
TinyTask-minipaca.Q5_K.gguf	Q5_K	0.06GB
TinyTask-minipaca.Q5_K_M.gguf	Q5_K_M	0.06GB
TinyTask-minipaca.Q5_1.gguf	Q5_1	0.06GB
TinyTask-minipaca.Q6_K.gguf	Q6_K	0.07GB
TinyTask-minipaca.Q8_0.gguf	Q8_0	0.09GB

Original model description:

license: cc-by-nc-4.0

A llama.c model based on Karpathy's Llama2.c project. https://github.com/karpathy/llama2.c

Vocab of 4096, trained on Tinystories, and my custom littlestories dataset (currently unreleased.)

This version was further trained on following instructions... somewhat... using https://github.com/mlabonne/llm-course/blob/main/Fine_tune_Llama_2_in_Google_Colab.ipynb

Model uses ↨ as a shift key, instead of using capial letters, this allowed simplification of the tokenizer to avoid duplicates that are uppercase.

To convert normal text to the right format I use:

def add_caseifer(text):
    # Using list comprehension for more efficient concatenation
    return ''.join(['↨' + char.lower() if char.isupper() else char for char in text])

To return the text to human format I use:

def remove_caseifer(text):
    new_text = ""
    i = 0
    while i < len(text):
        if text[i] == "↨":
            if i+1 < len(text):
                new_text += text[i+1].upper()
                i += 1
            else:
                pass  # skip this index
        else:
            new_text += text[i]
        i += 1
    return new_text

RichardErkhov/Corianas_-_TinyTask-minipaca-gguf

Original model description:

license: cc-by-nc-4.0

RichardErkhov/
Corianas_-_TinyTask-minipaca-gguf