mirror of
https://github.com/tcsenpai/ollama.git
synced 2025-06-07 03:35:21 +00:00
convert: capture head_dim
for mistral (#5818)
This commit is contained in:
parent
5784c05397
commit
d835368eb8
@ -71,6 +71,11 @@ func (m *MistralModel) WriteGGUF(ws io.WriteSeeker) error {
|
|||||||
"tokenizer.ggml.unknown_token_id": uint32(0),
|
"tokenizer.ggml.unknown_token_id": uint32(0),
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if m.Params.HeadDimension > 0 {
|
||||||
|
kv["llama.attention.key_length"] = uint32(m.Params.HeadDimension)
|
||||||
|
kv["llama.attention.value_length"] = uint32(m.Params.HeadDimension)
|
||||||
|
}
|
||||||
|
|
||||||
return llm.NewGGUFV3(m.Params.ByteOrder).Encode(ws, kv, m.Tensors)
|
return llm.NewGGUFV3(m.Params.ByteOrder).Encode(ws, kv, m.Tensors)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user