vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llm : add Refact model (#3329)

Browse source 
* add refact model

* resolve comments

* rebase to the latest

* solve alibi cpu error

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
ds5t5 2023-10-04 06:23:39 -07:00 • committed by GitHub
parent f93af02488
commit f8c90cdbaa
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 723 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml.c
View file

@ -13082,7 +13082,6 @@ static void ggml_compute_forward_alibi_f32(
return;
}
const int n_past = ((int32_t *) dst->op_params)[0];
const int n_head = ((int32_t *) dst->op_params)[1];
float max_bias;
memcpy(&max_bias, (int32_t *) dst->op_params + 2, sizeof(float));
@ -13103,7 +13102,6 @@ static void ggml_compute_forward_alibi_f32(
//const int nb3 = src0->nb[3];
GGML_ASSERT(nb0 == sizeof(float));
GGML_ASSERT(ne1 + n_past == ne0);
GGML_ASSERT(n_head == ne2);
// add alibi to src0 (KQ_scaled)