ochafik/llama.cpp

Pull Requests Commits

Create data1.json

ochafik committed 1 year ago

f574c98e

Delete chat_handler.hpp

ochafik committed 1 year ago

3fa45157

Update utils.hpp

ochafik committed 1 year ago

7f455c5d

Update utils.hpp

ochafik committed 1 year ago

1d941b6f

ochafik committed 1 year ago

2540689d

Merge remote-tracking branch 'origin/master' into tool-call-tmp

ochafik committed 1 year ago

52f07877

Update server.cpp

ochafik committed 1 year ago

edc818d7

ochafik committed 1 year ago

d4464305

Update tool_use.json

ochafik committed 1 year ago

5d722801

fix parameters in llama3.1

ochafik committed 1 year ago

76e271dd

Update utils.hpp

ochafik committed 1 year ago

a10e4147

Update utils.hpp

ochafik committed 1 year ago

30e2c41d

tool call tests

ochafik committed 1 year ago

30a11449

parse llama3.1 tool calls

ochafik committed 1 year ago

941cb3b7

fix basic hermes 2 pro tool call parsing

ochafik committed 1 year ago

5f8c0ac3

add --chat-template-file

ochafik committed 1 year ago

e4549ce1

jinja: simplify integration

ochafik committed 1 year ago

3aae90eb

minja: fix in operator on objects

ochafik committed 1 year ago

a3331bc3

minja: less consts

ochafik committed 1 year ago

2d1f5f5f

ggml : add AVX512DQ requirement for AVX512 builds (#9622)

EZForever committed 1 year ago

Verified 70392f1f

ggerganov committed 1 year ago

Verified bb5f8199

examples : adapt to ggml.h changes (ggml/0)

ggerganov committed 1 year ago

Verified c0389316

llama : keep track of all EOG tokens in the vocab (#9609)

ggerganov committed 1 year ago

Verified 31ac5834

log : add CONT level for continuing previous log entry (#9610)

ggerganov committed 1 year ago

Verified cea1486e

server : add newline after chat example (#9616)

StrangeBytesDev committed 1 year ago

Verified 0aa15011

sampling : avoid expensive softmax during greedy sampling (#9605)

ggerganov committed 1 year ago

Verified b0f27361

threads: fix msvc build without openmp (#9615)

max-krasnyansky committed 1 year ago

Verified c087b6f1

cuda: add q8_0->f32 cpy operation (#9571)

Nekotekina committed 1 year ago

Verified 116efee0

server : add --no-context-shift option (#9607)

ngxson committed 1 year ago

Verified 0b3bf966

threads: improve ggml_barrier scaling with large number of threads (#9598)

max-krasnyansky committed 1 year ago

Verified f0c7b5ed

Older