You can deploy this model and start earning money today!

RichardErkhov/
meelu_-_STD-BPE-LLAMA3.2-gguf

Name: meelu_-_STD-BPE-LLAMA3.2-gguf
Rating: 2.5 (13 reviews)

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

STD-BPE-LLAMA3.2 - GGUF

Model creator: https://huggingface.co/meelu/
Original model: https://huggingface.co/meelu/STD-BPE-LLAMA3.2/

Name	Quant method	Size
STD-BPE-LLAMA3.2.Q2_K.gguf	Q2_K	0.54GB
STD-BPE-LLAMA3.2.IQ3_XS.gguf	IQ3_XS	0.58GB
STD-BPE-LLAMA3.2.IQ3_S.gguf	IQ3_S	0.6GB
STD-BPE-LLAMA3.2.Q3_K_S.gguf	Q3_K_S	0.6GB
STD-BPE-LLAMA3.2.IQ3_M.gguf	IQ3_M	0.61GB
STD-BPE-LLAMA3.2.Q3_K.gguf	Q3_K	0.64GB
STD-BPE-LLAMA3.2.Q3_K_M.gguf	Q3_K_M	0.64GB
STD-BPE-LLAMA3.2.Q3_K_L.gguf	Q3_K_L	0.68GB
STD-BPE-LLAMA3.2.IQ4_XS.gguf	IQ4_XS	0.7GB
STD-BPE-LLAMA3.2.Q4_0.gguf	Q4_0	0.72GB
STD-BPE-LLAMA3.2.IQ4_NL.gguf	IQ4_NL	0.72GB
STD-BPE-LLAMA3.2.Q4_K_S.gguf	Q4_K_S	0.72GB
STD-BPE-LLAMA3.2.Q4_K.gguf	Q4_K	0.75GB
STD-BPE-LLAMA3.2.Q4_K_M.gguf	Q4_K_M	0.75GB
STD-BPE-LLAMA3.2.Q4_1.gguf	Q4_1	0.77GB
STD-BPE-LLAMA3.2.Q5_0.gguf	Q5_0	0.83GB
STD-BPE-LLAMA3.2.Q5_K_S.gguf	Q5_K_S	0.83GB
STD-BPE-LLAMA3.2.Q5_K.gguf	Q5_K	0.85GB
STD-BPE-LLAMA3.2.Q5_K_M.gguf	Q5_K_M	0.85GB
STD-BPE-LLAMA3.2.Q5_1.gguf	Q5_1	0.89GB
STD-BPE-LLAMA3.2.Q6_K.gguf	Q6_K	0.95GB
STD-BPE-LLAMA3.2.Q8_0.gguf	Q8_0	1.23GB

Original model description:

library_name: transformers tags: [Danish, BPE Tokenization, LLaMA]

STD-BPE-LLAMA3.2

A standard LLaMA-3.2 model trained with a pretrained Byte-Pair-Encoding (BPE) tokenizer. It provides a benchmark for evaluating the performance of more advanced tokenization approaches.

RichardErkhov/meelu_-_STD-BPE-LLAMA3.2-gguf

Original model description:

library_name: transformers tags: [Danish, BPE Tokenization, LLaMA]

STD-BPE-LLAMA3.2

RichardErkhov/
meelu_-_STD-BPE-LLAMA3.2-gguf