Commit Graph

16 Commits

Author SHA1 Message Date
antirez
e2062eea2c Q4_K dequantization. 2023-12-28 12:31:35 +01:00
antirez
c25ccfa02a Q8_0 dequantization. 2023-12-27 21:22:33 +01:00
antirez
558c7c3c6d Clarify the need for FP16 implementation. 2023-12-27 18:54:36 +01:00
antirez
bd4ecbda94 FP16 added. Split-mixtral improved. 2023-12-27 15:25:18 +01:00
antirez
a77a4d061c Mixtral experts extraction test. 2023-12-26 17:23:47 +01:00
antirez
7e9c2bd6a7 Better explain the tensor total size math. 2023-12-26 09:20:54 +01:00
antirez
3081d69b8e split-mixtral: copying of keys + APIs needed. 2023-12-26 09:14:50 +01:00
antirez
96e7eb2d4c gguf-tools: accept subcommands. 2023-12-26 00:07:56 +01:00
antirez
53fb176b3b Initial API to create new GGUF files.
Also added a few libraries that will be needed soon.
The CLI was renamed with the final name of gguf-tools.
2023-12-25 22:10:07 +01:00
antirez
3eb30c1872 API to remap/rewind + mapping in write mode. 2023-12-25 10:45:38 +01:00
antirez
f400e8a36f README added. 2023-12-24 23:46:46 +01:00
antirez
b3092d3860 Compute tensor size in bytes. 2023-12-24 23:44:24 +01:00
antirez
d54409bc9c Some library layout. 2023-12-24 18:31:03 +01:00
antirez
55a15a4230 Tensors parsing. 2023-12-24 17:20:04 +01:00
antirez
4ff25fb178 Limit array items printed. 2023-12-24 12:21:41 +01:00
antirez
b47eaca8d1 GGUF parsing, initial design and functionalities. 2023-12-24 12:06:32 +01:00