mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-10 15:57:04 +00:00
convert: capture head_dim for mistral (#5818)
This commit is contained in:
@@ -71,6 +71,11 @@ func (m *MistralModel) WriteGGUF(ws io.WriteSeeker) error {
|
||||
"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)
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user