[QLoRA] Llama 3.2 1B - a minpeter Collection

minpeter 's Collections

[Dataset] unified standard function calling

[Models] Small size high performance BFCL instruction

[Model] BFCL Top Rank Model

[Model] Latest Llama base model

[tokenizer] AlternateTokenizer

[Merged] Experimental merge model

[QLoRA] Llama 3.2 1B

[Dataset] Function Calling

[QLoRA] Llama 3.2 1B

updated Feb 9

minpeter/QLoRA-Llama-3.2-1B-alpaca

Updated Feb 5 • 30 • 1
minpeter/QLoRA-Llama-3.2-1B-chatml

Updated Feb 5 • 3 • 1
minpeter/QLoRA-Llama-3.2-1B-chatml-v2

Updated Feb 6

Note QLoRA-Llama-3.2-1B-chatml is fundamentally the same, but trained on a much larger dataset (21k steps).
minpeter/QLoRA-Llama-3.2-1B-chatml-v3

Text Generation • Updated Feb 6 • 1

Note 52 steps, 2 minutes to train
minpeter/QLoRA-Llama-3.2-1B-chatml-tool-v1

Updated Feb 9
minpeter/QLoRA-Llama-3.2-1B-chatml-tool-v2

Updated Feb 9 • 1