norohind/ollama
1
0
Fork 0
forked from third-party-mirrors/ollama
Code Pull Requests Activity

fix gemma2-2b conversion

Browse Source
This commit is contained in:
Patrick Devine 2024-09-04 16:59:23 -07:00
parent b3554778bd
commit db8c944498
2 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
convert/convert_gemma2.go
View File

@ -34,10 +34,20 @@ func (p *gemma2Model) KV(t *Tokenizer) llm.KV {
}
func (p *gemma2Model) Replacements() []string {
return append(
p.gemmaModel.Replacements(),
return []string{
"model.embed_tokens", "token_embd",
"model.norm", "output_norm",
"model.layers", "blk",
"input_layernorm", "attn_norm",
"self_attn.q_proj", "attn_q",
"self_attn.k_proj", "attn_k",
"self_attn.v_proj", "attn_v",
"self_attn.o_proj", "attn_output",
"mlp.gate_proj", "ffn_gate",
"mlp.down_proj", "ffn_down",
"mlp.up_proj", "ffn_up",
"post_attention_layernorm", "post_attention_norm",
"pre_feedforward_layernorm", "ffn_norm",
"post_feedforward_layernorm", "post_ffw_norm",
)
}
}

1
convert/convert_test.go
View File

@ -96,6 +96,7 @@ func TestConvertModel(t *testing.T) {
"Mistral-7B-Instruct-v0.2",
"Mixtral-8x7B-Instruct-v0.1",
"gemma-2b-it",
"gemma-2-2b-it",
// microsoft/Phi-3-mini-128-instruct@d548c233192db00165d842bf8edff054bb3212f8
"Phi-3-mini-128k-instruct",
"all-MiniLM-L6-v2",