mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-20 09:38:55 +02:00
Merge branch 'upstream' into concedo_experimental
# Conflicts: # ci/run.sh # ggml/CMakeLists.txt # ggml/src/ggml-cpu/arch/riscv/repack.cpp # ggml/src/ggml-cpu/arch/x86/repack.cpp # ggml/src/ggml-cpu/repack.cpp # ggml/src/ggml-hexagon/ggml-hexagon.cpp # ggml/src/ggml-hexagon/htp/CMakeLists.txt # ggml/src/ggml-hexagon/htp/htp-msg.h # ggml/src/ggml-hexagon/htp/htp-ops.h # ggml/src/ggml-hexagon/htp/hvx-base.h # ggml/src/ggml-hexagon/htp/hvx-exp.h # ggml/src/ggml-hexagon/htp/hvx-sigmoid.h # ggml/src/ggml-hexagon/htp/main.c # ggml/src/ggml-hexagon/htp/softmax-ops.c # ggml/src/ggml-hexagon/htp/unary-ops.c # ggml/src/ggml-webgpu/ggml-webgpu.cpp # scripts/sync-ggml.last # tests/test-backend-sampler.cpp # tests/test-chat.cpp # tests/test-jinja.cpp # tools/cli/cli.cpp
This commit is contained in:
@@ -3118,6 +3118,17 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
params.chat_template = read_file(value);
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_CHAT_TEMPLATE_FILE"));
|
||||
add_opt(common_arg(
|
||||
{"--skip-chat-parsing"},
|
||||
{"--no-skip-chat-parsing"},
|
||||
string_format(
|
||||
"force a pure content parser, even if a Jinja template is specified; model will output everything "
|
||||
"in the content section, including any reasoning and/or tool calls (default: disabled)"
|
||||
),
|
||||
[](common_params & params, bool value) {
|
||||
params.force_pure_content_parser = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_SKIP_CHAT_PARSING"));
|
||||
add_opt(common_arg(
|
||||
{"--prefill-assistant"},
|
||||
{"--no-prefill-assistant"},
|
||||
|
||||
Reference in New Issue
Block a user