2 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
3 people	e457fb3540	llama : assume tied weights if lm_head/output weights is missing (#5824) ... This is to support model configurations with "tie_word_embeddings" set to true. Co-authored-by: Don Mahurin <2797413+dmahurin@users.noreply.github.com>	2024-03-08 12:41:50 +02:00
3 people	2ab0707acb	convert : use 'model' value if it exists. This allows karpathy/tinyllamas to load (#4089) ... Co-authored-by: Don Mahurin <@>	2023-11-17 17:32:34 +02:00