You can deploy this model and start earning money today!

RichardErkhov/
DarwinAnim8or_-_Pythia-Greentext-1.4b-gguf

Name: DarwinAnim8or_-_Pythia-Greentext-1.4b-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Pythia-Greentext-1.4b - GGUF

Model creator: https://huggingface.co/DarwinAnim8or/
Original model: https://huggingface.co/DarwinAnim8or/Pythia-Greentext-1.4b/

Name	Quant method	Size
Pythia-Greentext-1.4b.Q2_K.gguf	Q2_K	0.53GB
Pythia-Greentext-1.4b.IQ3_XS.gguf	IQ3_XS	0.59GB
Pythia-Greentext-1.4b.IQ3_S.gguf	IQ3_S	0.61GB
Pythia-Greentext-1.4b.Q3_K_S.gguf	Q3_K_S	0.61GB
Pythia-Greentext-1.4b.IQ3_M.gguf	IQ3_M	0.66GB
Pythia-Greentext-1.4b.Q3_K.gguf	Q3_K	0.71GB
Pythia-Greentext-1.4b.Q3_K_M.gguf	Q3_K_M	0.71GB
Pythia-Greentext-1.4b.Q3_K_L.gguf	Q3_K_L	0.77GB
Pythia-Greentext-1.4b.IQ4_XS.gguf	IQ4_XS	0.74GB
Pythia-Greentext-1.4b.Q4_0.gguf	Q4_0	0.77GB
Pythia-Greentext-1.4b.IQ4_NL.gguf	IQ4_NL	0.78GB
Pythia-Greentext-1.4b.Q4_K_S.gguf	Q4_K_S	0.78GB
Pythia-Greentext-1.4b.Q4_K.gguf	Q4_K	0.85GB
Pythia-Greentext-1.4b.Q4_K_M.gguf	Q4_K_M	0.85GB
Pythia-Greentext-1.4b.Q4_1.gguf	Q4_1	0.85GB
Pythia-Greentext-1.4b.Q5_0.gguf	Q5_0	0.92GB
Pythia-Greentext-1.4b.Q5_K_S.gguf	Q5_K_S	0.92GB
Pythia-Greentext-1.4b.Q5_K.gguf	Q5_K	0.98GB
Pythia-Greentext-1.4b.Q5_K_M.gguf	Q5_K_M	0.98GB
Pythia-Greentext-1.4b.Q5_1.gguf	Q5_1	1.0GB
Pythia-Greentext-1.4b.Q6_K.gguf	Q6_K	1.08GB
Pythia-Greentext-1.4b.Q8_0.gguf	Q8_0	1.4GB

Original model description:

license: apache-2.0 datasets:

DarwinAnim8or/greentext language:
en tags:
fun
greentext widget:
text: '>be me' example_title: be me
text: '>be zoo keeper' co2_eq_emissions: emissions: 10 source: https://mlco2.github.io/impact/#compute training_type: fine-tuning geographical_location: Oregon, USA hardware_used: 1x T4, Google Colab

Pythia-Greentext-1.4b

A finetuned version of Pythia-1.4b on the 'greentext' dataset. A demo is available here The demo playground is recommended over the inference box on the right.

This is an alternate take on my "GPT-Greentext" releases.

Training Procedure

This was trained on the 'greentext' dataset, on Google Colab. This model was trained for 1 epoch with learning rate 1e-2. Notably this uses the "prompt" and "completion" style jsonl file, rather than the plain text file found in the greentext dataset. This nets somewhat better, mostly more consistent results.

Biases & Limitations

This likely contains the same biases and limitations as the original model that it is based on, and additionally heavy biases from the greentext dataset. It should be noted that offensive or not PG-output is definitely possible and likely will happen.

Intended Use

This model is meant for fun, nothing else.

Noteworthy differences between this model and the others

This model tends to like no_repeat_ngram_size values of 1 or 2; whereas the other models in this series tend to prefer 3.

Sample Use

python

#Import model:
from happytransformer import HappyGeneration
happy_gen = HappyGeneration("GPTNEO", "DarwinAnim8or/Pythia-Greentext-1.4b")

#Set generation settings:
from happytransformer import GENSettings
args_top_k = GENSettingsGENSettings(no_repeat_ngram_size=2, do_sample=True, top_k=80, temperature=0.1, max_length=150, early_stopping=False)

#Generate a response:
result = happy_gen.generate_text(""">be me
>""", args=args_top_k)

print(result)
print(result.text)

RichardErkhov/DarwinAnim8or_-_Pythia-Greentext-1.4b-gguf