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

gguf : add ftype meta info to the model (#2710)

Browse source 
* llama : add ftype meta info to the model

ggml-ci

* convert.py : add ftype when converting (does not work)

* convert.py : fix Enum to IntEnum

ggml-ci
This commit is contained in:
Georgi Gerganov 2023-08-22 20:05:59 +03:00 • committed by GitHub
parent bac66994cf
commit deb7dfca4b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 47 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.h
View file

@ -103,6 +103,8 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_Q5_K_S = 16,// except 1d tensors
LLAMA_FTYPE_MOSTLY_Q5_K_M = 17,// except 1d tensors
LLAMA_FTYPE_MOSTLY_Q6_K = 18,// except 1d tensors
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
};
typedef struct llama_token_data {