You can deploy this model and start earning money today!

RichardErkhov/
Ba2han_-_Pretraining_Turkish-10k-step-gguf

Name: Ba2han_-_Pretraining_Turkish-10k-step-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Pretraining_Turkish-10k-step - GGUF

Model creator: https://huggingface.co/Ba2han/
Original model: https://huggingface.co/Ba2han/Pretraining_Turkish-10k-step/

Name	Quant method	Size
Pretraining_Turkish-10k-step.Q2_K.gguf	Q2_K	0.16GB
Pretraining_Turkish-10k-step.IQ3_XS.gguf	IQ3_XS	0.18GB
Pretraining_Turkish-10k-step.IQ3_S.gguf	IQ3_S	0.19GB
Pretraining_Turkish-10k-step.Q3_K_S.gguf	Q3_K_S	0.19GB
Pretraining_Turkish-10k-step.IQ3_M.gguf	IQ3_M	0.19GB
Pretraining_Turkish-10k-step.Q3_K.gguf	Q3_K	0.2GB
Pretraining_Turkish-10k-step.Q3_K_M.gguf	Q3_K_M	0.2GB
Pretraining_Turkish-10k-step.Q3_K_L.gguf	Q3_K_L	0.21GB
Pretraining_Turkish-10k-step.IQ4_XS.gguf	IQ4_XS	0.22GB
Pretraining_Turkish-10k-step.Q4_0.gguf	Q4_0	0.23GB
Pretraining_Turkish-10k-step.IQ4_NL.gguf	IQ4_NL	0.23GB
Pretraining_Turkish-10k-step.Q4_K_S.gguf	Q4_K_S	0.23GB
Pretraining_Turkish-10k-step.Q4_K.gguf	Q4_K	0.24GB
Pretraining_Turkish-10k-step.Q4_K_M.gguf	Q4_K_M	0.24GB
Pretraining_Turkish-10k-step.Q4_1.gguf	Q4_1	0.25GB
Pretraining_Turkish-10k-step.Q5_0.gguf	Q5_0	0.27GB
Pretraining_Turkish-10k-step.Q5_K_S.gguf	Q5_K_S	0.27GB
Pretraining_Turkish-10k-step.Q5_K.gguf	Q5_K	0.27GB
Pretraining_Turkish-10k-step.Q5_K_M.gguf	Q5_K_M	0.27GB
Pretraining_Turkish-10k-step.Q5_1.gguf	Q5_1	0.29GB
Pretraining_Turkish-10k-step.Q6_K.gguf	Q6_K	0.31GB
Pretraining_Turkish-10k-step.Q8_0.gguf	Q8_0	0.41GB

Original model description:

license: mit language:

tr library_name: transformers

Pretrained on roughly 1.6B (mostly Turkish) tokens from HF and "high quality" scraped data using 1 RTX 3090. The training will continue. The model already can be (sort of) fine-tuned for instruction.

HF kaynaklı ve scrape edilen yaklaşık 1.6 Milyar (çoğunlukla Türkçe) token ile 1 RTX 3090 kullanılarak eğitilmiştir. Model şimdiden talimatlar için fine-tune edilebiliyor:

max_length=256, top_k=20, min_p=0.1, repetition_penalty=1.1, temperature=0.1, seed=22366 / TR_4k_LoRA

RichardErkhov/Ba2han_-_Pretraining_Turkish-10k-step-gguf

Original model description:

RichardErkhov/
Ba2han_-_Pretraining_Turkish-10k-step-gguf