Andrei Betlen
c26e9bf1c1
Update sampling api
2023-05-31 15:56:55 -07:00
Andrei Betlen
78531e5d05
Fix return types and import comments
2023-05-31 15:56:55 -07:00
Andrei Betlen
d0031edbd2
Update llama.cpp
2023-05-31 15:56:55 -07:00
Mug
441d30811a
Detect multi-byte responses and wait
2023-05-31 15:56:55 -07:00
Mug
36b3494332
Also ignore errors on input prompts
2023-05-31 15:56:55 -07:00
Andrei Betlen
c8e6ac366a
Update llama.cpp (llama_load_session_file)
2023-05-31 15:56:55 -07:00
Andrei Betlen
66ad132575
Update llama.cpp
2023-05-31 15:56:55 -07:00
Andrei Betlen
656190750d
Update llama.cpp
2023-05-31 15:56:55 -07:00
Andrei Betlen
80c18cb665
Update llama.cpp (remove llama_get_kv_cache)
2023-05-31 15:56:55 -07:00
Andrei Betlen
bf9f02d8ee
Update llama.cpp
2023-05-31 15:56:55 -07:00
Andrei Betlen
5bbf40aa47
Update llama.cpp
2023-05-31 15:56:55 -07:00
Mug
fd64310276
Fix decode errors permanently
2023-05-31 15:56:55 -07:00
Mug
bdbaf5dc76
Fixed end of text wrong type, and fix n_predict behaviour
2023-05-31 15:56:55 -07:00
Andrei Betlen
81c4c10389
Update type signature to allow for null pointer to be passed.
2023-05-31 15:56:55 -07:00
Mug
8229410a4e
More reasonable defaults
2023-05-31 15:56:55 -07:00
Andrei Betlen
b6ce5133d9
Add bindings for LoRA adapters. Closes #88
2023-05-31 15:56:55 -07:00
Andrei Betlen
3693449c07
Update llama.cpp
2023-05-31 15:56:55 -07:00
Andrei Betlen
d595f330e2
Update llama.cpp
2023-05-31 15:56:55 -07:00
Andrei Betlen
ce0ca60b56
Update llama.cpp (llama_mmap_supported)
2023-05-31 15:56:49 -07:00
Mug
d0a7ce9abf
Make windows users happy (hopefully)
2023-05-31 15:25:57 -07:00
Mug
848b4021a3
Better custom library debugging
2023-05-31 15:25:57 -07:00
Mug
c8b5d0b963
Use environment variable for library override
2023-05-31 15:25:57 -07:00
Mug
d1b3517477
Allow local llama library usage
2023-05-31 15:25:57 -07:00
Mug
b36c04c99e
Added iterative search to prevent instructions from being echoed, add ignore eos, add no-mmap, fixed 1 character echo too much bug
2023-05-31 15:25:57 -07:00
Andrei Betlen
f25a81309e
Update model paths to be more clear they should point to file
2023-05-31 15:25:57 -07:00
Mug
e19909249d
More interoperability to the original llama.cpp, and arguments now work
2023-05-31 15:25:57 -07:00
Andrei Betlen
d5680144c5
Bugfix: Wrong size of embeddings. Closes #47
2023-05-31 15:25:57 -07:00
Mug
29e9fb66a3
Better llama.cpp interoperability
...
Has some too many newline issues so WIP
(Update) Fixed too many newlines, now onto args.
Still needs shipping work so you could do "python -m llama_cpp.examples." etc.
2023-05-31 15:25:57 -07:00
Andrei Betlen
ce66405da1
Add quantize example
2023-05-31 15:25:57 -07:00
Mug
739e8d4c9b
Fix bug in init_break not being set when exited via antiprompt and others.
2023-05-31 15:25:57 -07:00
Mug
ae1f37f505
Fix repeating instructions and an antiprompt bug
2023-05-31 15:25:57 -07:00
Mug
3c1020b866
Fix stripping instruction prompt
2023-05-31 15:25:57 -07:00
Mug
0bfad75406
Added instruction mode, fixed infinite generation, and various other fixes
2023-05-31 15:25:57 -07:00
Mug
9e872410da
Add instruction mode
2023-05-31 15:25:57 -07:00
Mug
15bea0946b
Chat llama.cpp example implementation
2023-05-31 15:25:57 -07:00
MillionthOdin16
2b8147e7a8
Update llama_cpp.py
2023-05-31 15:25:57 -07:00
Andrei Betlen
62ce167b22
Update low level api example
2023-05-31 15:25:57 -07:00
Andrei Betlen
a71cda6546
Update llama.cpp
2023-05-31 15:25:57 -07:00
Andrei Betlen
a279acd680
Update llama.cpp (llama_n_embd)
2023-05-31 15:25:57 -07:00
Andrei Betlen
ef3c152257
Update llama.cpp (llama_progress_callback)
2023-05-31 15:25:57 -07:00
Andrei Betlen
def46dd9a6
Add example based on stripped down version of main.cpp from llama.cpp
2023-05-31 15:25:57 -07:00
Andrei Betlen
5bb1bc74d1
Fix type signature of token_to_str
2023-05-31 15:25:57 -07:00
Andrei Betlen
a7a6d88793
Fix ctypes typing issue for Arrays
2023-05-31 15:25:57 -07:00
Andrei Betlen
019650f416
Fix array type signatures
2023-05-31 15:25:57 -07:00
Andrei Betlen
a3da39af79
Bugfix: cross-platform method to find shared lib
2023-05-31 15:24:39 -07:00
Andrei Betlen
bd1c657f80
Bugfix: wrong signature for quantize function
2023-05-31 15:24:10 -07:00
Andrei Betlen
ef5a9a6160
Update llama.cpp and re-organize low-level api
2023-05-31 15:16:27 -07:00
Andrei Betlen
d9dfdec2bd
Initial commit (llama_cpp.py, llama-cpp-python)
2023-05-31 15:16:11 -07:00
Henri Vasserman
ffb06a345e
OpenLLaMA 3B support ( #1588 )
...
This adds support to llama.cpp to load the model.
Currently missing are changes that are required from convert.py to convert the model correctly. It needs some changes to start reading the JSON configuration for HF models instead of deriving the values by guessing.
Co-authored-by: FNsi <125447286+FNsi@users.noreply.github.com>
2023-05-30 21:24:22 +03:00
Georgi Gerganov
7552ac5863
ggml : sync cgraph import / export API
2023-05-29 19:31:44 +03:00
