Skip to content

Commit 5955894

Browse files
l3utterflyl3utterfly
authored
Merge pull request #51 from l3utterfly/merge
merge from upstream
2 parents 14508d7 + a6ab3d4 commit 5955894

28 files changed

+2028
-231
lines changed

‎.github/workflows/build.yml‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -87,6 +87,7 @@ jobs:
8787
if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
8888
run: |
8989
cp LICENSE ./build/bin/
90+
cp examples/run/linenoise.cpp/LICENSE ./build/bin/LICENSE.linenoise.cpp
9091
zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.zip ./build/bin/*
9192
9293
- name: Upload artifacts
@@ -149,6 +150,7 @@ jobs:
149150
if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
150151
run: |
151152
cp LICENSE ./build/bin/
153+
cp examples/run/linenoise.cpp/LICENSE ./build/bin/LICENSE.linenoise.cpp
152154
zip -r llama-${{ steps.tag.outputs.name }}-bin-macos-x64.zip ./build/bin/*
153155
154156
- name: Upload artifacts
@@ -217,6 +219,7 @@ jobs:
217219
if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
218220
run: |
219221
cp LICENSE ./build/bin/
222+
cp examples/run/linenoise.cpp/LICENSE ./build/bin/LICENSE.linenoise.cpp
220223
zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-x64.zip ./build/bin/*
221224
222225
- name: Upload artifacts
@@ -796,6 +799,7 @@ jobs:
796799
if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
797800
run: |
798801
Copy-Item LICENSE .\build\bin\Release\llama.cpp.txt
802+
Copy-Item .\examples\run\linenoise.cpp\LICENSE .\build\bin\Release\linenoise.cpp.txt
799803
7z a llama-${{ steps.tag.outputs.name }}-bin-win-${{ matrix.build }}.zip .\build\bin\Release\*
800804
801805
- name: Upload artifacts

‎.github/workflows/server.yml‎

Lines changed: 22 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -112,9 +112,9 @@ jobs:
112112
-DGGML_OPENMP=OFF ;
113113
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
114114
115-
- name: Build
116-
id: cmake_build
117-
if: ${{ matrix.sanitizer != 'THREAD' }}
115+
- name: Build (sanitizers)
116+
id: cmake_build_sanitizers
117+
if: ${{ matrix.sanitizer != '' && matrix.sanitizer != 'THREAD' }}
118118
run: |
119119
cmake -B build \
120120
-DGGML_NATIVE=OFF \
@@ -124,12 +124,31 @@ jobs:
124124
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON ;
125125
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
126126
127+
- name: Build (sanitizers)
128+
id: cmake_build
129+
if: ${{ matrix.sanitizer == '' }}
130+
run: |
131+
cmake -B build \
132+
-DGGML_NATIVE=OFF \
133+
-DLLAMA_BUILD_SERVER=ON \
134+
-DLLAMA_CURL=ON \
135+
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} ;
136+
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
137+
127138
- name: Tests
128139
id: server_integration_tests
140+
if: ${{ matrix.sanitizer == '' }}
129141
run: |
130142
cd examples/server/tests
131143
./tests.sh
132144
145+
- name: Tests (sanitizers)
146+
id: server_integration_tests_sanitizers
147+
if: ${{ matrix.sanitizer != '' }}
148+
run: |
149+
cd examples/server/tests
150+
LLAMA_SANITIZE=1 ./tests.sh
151+
133152
- name: Slow tests
134153
id: server_integration_tests_slow
135154
if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }}

‎cmake/build-info.cmake‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@ if(MSVC)
4444
set(BUILD_TARGET ${CMAKE_VS_PLATFORM_NAME})
4545
else()
4646
execute_process(
47-
COMMAND sh -c "$@ --version | head -1" _ ${CMAKE_C_COMPILER}
47+
COMMAND sh -c "\"$@\" --version | head -1" _ ${CMAKE_C_COMPILER}
4848
OUTPUT_VARIABLE OUT
4949
OUTPUT_STRIP_TRAILING_WHITESPACE
5050
)

‎common/arg.cpp‎

Lines changed: 13 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -133,7 +133,8 @@ static void common_params_handle_model_default(
133133
const std::string & model_url,
134134
std::string & hf_repo,
135135
std::string & hf_file,
136-
const std::string & hf_token) {
136+
const std::string & hf_token,
137+
const std::string & model_default) {
137138
if (!hf_repo.empty()) {
138139
// short-hand to avoid specifying --hf-file -> default it to --model
139140
if (hf_file.empty()) {
@@ -163,7 +164,7 @@ static void common_params_handle_model_default(
163164
model = fs_get_cache_file(string_split<std::string>(f, '/').back());
164165
}
165166
} else if (model.empty()) {
166-
model = DEFAULT_MODEL_PATH;
167+
model = model_default;
167168
}
168169
}
169170

@@ -299,8 +300,9 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
299300
}
300301

301302
// TODO: refactor model params in a common struct
302-
common_params_handle_model_default(params.model, params.model_url, params.hf_repo, params.hf_file, params.hf_token);
303-
common_params_handle_model_default(params.vocoder.model, params.vocoder.model_url, params.vocoder.hf_repo, params.vocoder.hf_file, params.hf_token);
303+
common_params_handle_model_default(params.model, params.model_url, params.hf_repo, params.hf_file, params.hf_token, DEFAULT_MODEL_PATH);
304+
common_params_handle_model_default(params.speculative.model, params.speculative.model_url, params.speculative.hf_repo, params.speculative.hf_file, params.hf_token, "");
305+
common_params_handle_model_default(params.vocoder.model, params.vocoder.model_url, params.vocoder.hf_repo, params.vocoder.hf_file, params.hf_token, "");
304306

305307
if (params.escape) {
306308
string_process_escapes(params.prompt);
@@ -1629,6 +1631,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
16291631
params.hf_repo = value;
16301632
}
16311633
).set_env("LLAMA_ARG_HF_REPO"));
1634+
add_opt(common_arg(
1635+
{"-hfd", "-hfrd", "--hf-repo-draft"}, "<user>/<model>[:quant]",
1636+
"Same as --hf-repo, but for the draft model (default: unused)",
1637+
[](common_params & params, const std::string & value) {
1638+
params.speculative.hf_repo = value;
1639+
}
1640+
).set_env("LLAMA_ARG_HFD_REPO"));
16321641
add_opt(common_arg(
16331642
{"-hff", "--hf-file"}, "FILE",
16341643
"Hugging Face model file. If specified, it will override the quant in --hf-repo (default: unused)",

‎common/common.h‎

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -175,7 +175,11 @@ struct common_params_speculative {
175175
struct cpu_params cpuparams;
176176
struct cpu_params cpuparams_batch;
177177

178-
std::string model = ""; // draft model for speculative decoding // NOLINT
178+
std::string hf_repo = ""; // HF repo // NOLINT
179+
std::string hf_file = ""; // HF file // NOLINT
180+
181+
std::string model = ""; // draft model for speculative decoding // NOLINT
182+
std::string model_url = ""; // model url to download // NOLINT
179183
};
180184

181185
struct common_params_vocoder {
@@ -508,12 +512,14 @@ struct llama_model * common_load_model_from_url(
508512
const std::string & local_path,
509513
const std::string & hf_token,
510514
const struct llama_model_params & params);
515+
511516
struct llama_model * common_load_model_from_hf(
512517
const std::string & repo,
513518
const std::string & remote_path,
514519
const std::string & local_path,
515520
const std::string & hf_token,
516521
const struct llama_model_params & params);
522+
517523
std::pair<std::string, std::string> common_get_hf_file(
518524
const std::string & hf_repo_with_tag,
519525
const std::string & hf_token);

‎convert_hf_to_gguf.py‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -696,6 +696,9 @@ def get_vocab_base_pre(self, tokenizer) -> str:
696696
if chkhsh == "877081d19cf6996e2c4ff0e1236341e9b7bde288f5311a56a937f0afbbb3aeb5":
697697
# ref: https://huggingface.co/deepseek-ai/DeepSeek-V3
698698
res = "deepseek-v3"
699+
if chkhsh == "b3f499bb4255f8ca19fccd664443283318f2fd2414d5e0b040fbdd0cc195d6c5":
700+
# ref: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
701+
res = "deepseek-r1-qwen"
699702

700703
if res is None:
701704
logger.warning("\n")

‎convert_hf_to_gguf_update.py‎

Lines changed: 44 additions & 43 deletions
Original file line numberDiff line numberDiff line change
@@ -65,49 +65,50 @@ class TOKENIZER_TYPE(IntEnum):
6565

6666
# TODO: add models here, base models preferred
6767
models = [
68-
{"name": "llama-spm", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/meta-llama/Llama-2-7b-hf", },
69-
{"name": "llama-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/meta-llama/Meta-Llama-3-8B", },
70-
{"name": "phi-3", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct", },
71-
{"name": "deepseek-llm", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-llm-7b-base", },
72-
{"name": "deepseek-coder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base", },
73-
{"name": "falcon", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/falcon-7b", },
74-
{"name": "bert-bge", "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/BAAI/bge-small-en-v1.5", },
75-
{"name": "falcon3", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/Falcon3-7B-Base", },
76-
{"name": "bert-bge-large", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/BAAI/bge-large-zh-v1.5", },
77-
{"name": "mpt", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mosaicml/mpt-7b", },
78-
{"name": "starcoder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigcode/starcoder2-3b", },
79-
{"name": "gpt-2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/openai-community/gpt2", },
80-
{"name": "stablelm2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b", },
81-
{"name": "refact", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/smallcloudai/Refact-1_6-base", },
82-
{"name": "command-r", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/CohereForAI/c4ai-command-r-v01", },
83-
{"name": "qwen2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Qwen/Qwen1.5-7B", },
84-
{"name": "olmo", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/allenai/OLMo-1.7-7B-hf", },
85-
{"name": "dbrx", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/databricks/dbrx-base", },
86-
{"name": "jina-v1-en", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-reranker-v1-tiny-en", },
87-
{"name": "jina-v2-en", "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-en", }, # WPM!
88-
{"name": "jina-v2-es", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-es", },
89-
{"name": "jina-v2-de", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-de", },
90-
{"name": "smaug-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct", },
91-
{"name": "poro-chat", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LumiOpen/Poro-34B-chat", },
92-
{"name": "jina-v2-code", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-code", },
93-
{"name": "viking", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LumiOpen/Viking-7B", }, # Also used for Viking 13B and 33B
94-
{"name": "gemma", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/google/gemma-2b", },
95-
{"name": "gemma-2", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/google/gemma-2-9b", },
96-
{"name": "jais", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/core42/jais-13b", },
97-
{"name": "t5", "tokt": TOKENIZER_TYPE.UGM, "repo": "https://huggingface.co/google-t5/t5-small", },
98-
{"name": "codeshell", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/WisdomShell/CodeShell-7B", },
99-
{"name": "tekken", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", },
100-
{"name": "smollm", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/HuggingFaceTB/SmolLM-135M", },
101-
{'name': "bloom", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigscience/bloom", },
102-
{'name': "gpt3-finnish", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/TurkuNLP/gpt3-finnish-small", },
103-
{"name": "exaone", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct", },
104-
{"name": "phi-2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/microsoft/phi-2", },
105-
{"name": "chameleon", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/facebook/chameleon-7b", },
106-
{"name": "minerva-7b", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/sapienzanlp/Minerva-7B-base-v1.0", },
107-
{"name": "roberta-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/sentence-transformers/stsb-roberta-base"},
108-
{"name": "gigachat", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/ai-sage/GigaChat-20B-A3B-instruct"},
109-
{"name": "megrez", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Infinigence/Megrez-3B-Instruct"},
110-
{"name": "deepseek-v3", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/DeepSeek-V3"},
68+
{"name": "llama-spm", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/meta-llama/Llama-2-7b-hf", },
69+
{"name": "llama-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/meta-llama/Meta-Llama-3-8B", },
70+
{"name": "phi-3", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct", },
71+
{"name": "deepseek-llm", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-llm-7b-base", },
72+
{"name": "deepseek-coder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base", },
73+
{"name": "falcon", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/falcon-7b", },
74+
{"name": "bert-bge", "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/BAAI/bge-small-en-v1.5", },
75+
{"name": "falcon3", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/Falcon3-7B-Base", },
76+
{"name": "bert-bge-large", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/BAAI/bge-large-zh-v1.5", },
77+
{"name": "mpt", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mosaicml/mpt-7b", },
78+
{"name": "starcoder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigcode/starcoder2-3b", },
79+
{"name": "gpt-2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/openai-community/gpt2", },
80+
{"name": "stablelm2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b", },
81+
{"name": "refact", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/smallcloudai/Refact-1_6-base", },
82+
{"name": "command-r", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/CohereForAI/c4ai-command-r-v01", },
83+
{"name": "qwen2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Qwen/Qwen1.5-7B", },
84+
{"name": "olmo", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/allenai/OLMo-1.7-7B-hf", },
85+
{"name": "dbrx", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/databricks/dbrx-base", },
86+
{"name": "jina-v1-en", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-reranker-v1-tiny-en", },
87+
{"name": "jina-v2-en", "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-en", }, # WPM!
88+
{"name": "jina-v2-es", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-es", },
89+
{"name": "jina-v2-de", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-de", },
90+
{"name": "smaug-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct", },
91+
{"name": "poro-chat", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LumiOpen/Poro-34B-chat", },
92+
{"name": "jina-v2-code", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-code", },
93+
{"name": "viking", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LumiOpen/Viking-7B", }, # Also used for Viking 13B and 33B
94+
{"name": "gemma", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/google/gemma-2b", },
95+
{"name": "gemma-2", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/google/gemma-2-9b", },
96+
{"name": "jais", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/core42/jais-13b", },
97+
{"name": "t5", "tokt": TOKENIZER_TYPE.UGM, "repo": "https://huggingface.co/google-t5/t5-small", },
98+
{"name": "codeshell", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/WisdomShell/CodeShell-7B", },
99+
{"name": "tekken", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", },
100+
{"name": "smollm", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/HuggingFaceTB/SmolLM-135M", },
101+
{'name': "bloom", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigscience/bloom", },
102+
{'name': "gpt3-finnish", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/TurkuNLP/gpt3-finnish-small", },
103+
{"name": "exaone", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct", },
104+
{"name": "phi-2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/microsoft/phi-2", },
105+
{"name": "chameleon", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/facebook/chameleon-7b", },
106+
{"name": "minerva-7b", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/sapienzanlp/Minerva-7B-base-v1.0", },
107+
{"name": "roberta-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/sentence-transformers/stsb-roberta-base"},
108+
{"name": "gigachat", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/ai-sage/GigaChat-20B-A3B-instruct"},
109+
{"name": "megrez", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Infinigence/Megrez-3B-Instruct"},
110+
{"name": "deepseek-v3", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/DeepSeek-V3"},
111+
{"name": "deepseek-r1-qwen", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"},
111112
]
112113

113114

‎examples/run/CMakeLists.txt‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
set(TARGET llama-run)
2-
add_executable(${TARGET} run.cpp)
2+
add_executable(${TARGET} run.cpp linenoise.cpp/linenoise.cpp)
33
install(TARGETS ${TARGET} RUNTIME)
44
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
55
target_compile_features(${TARGET} PRIVATE cxx_std_17)

0 commit comments

Comments
 (0)