# ## Model path # # llama_cpp_model_path=/data/models/TheBloke/vicuna-13B-v1.5-GGUF/vicuna-13b-v1.5.Q4_K_M.gguf # ### LLM cache # ## Enable Model cache # # MODEL_CACHE_ENABLE=True # ## The storage type of model cache, now supports: memory, disk # # MODEL_CACHE_STORAGE_...
path = "/data/models/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf" [[models.embeddings]] name = "BAAI/bge-large-zh-v1.5" provider = "hf" 46 changes: 46 additions & 0 deletions 46 configs/dbgpt-local-llama-cpp.toml Original file line numberDiff line numberDiff line change @@ -0...
/resolve/main/vicuna-13b-v1.5.Q4_K_M.gguf -O models/ggml-model-q4_0.gguf ``` @@ -360,7 +361,7 @@ During use, you can also convertthemodel file yourself according to the instru ### Install dependencies llama.cpp is an optional installationitem in DB-GPT. can install ...
data/models/TheBloke/vicuna-13B-v1.5-GGUF/vicuna-13b-v1.5._K_M.gguf ### LLM cache ## Enable Model cache # MODEL_CACHE_ENABLE=True ## The storage typeof model cache, now supports: memory, disk # MODEL_CACHE_STORAGE_TYPE=disk ## The maxcache data in memory, we ...
Llama.cpp support new GGUF file format (#649) 🐞 Bug fixes Fix remote embedding model start error (#708) DB metadata charset bug (#698) ChatData (#694) Fix type exception when use office ppt database (#679) DB schema not complete bug (#675) Fix load some quantization model error ...
/resolve/main/vicuna-13b-v1.5.Q4_K_M.gguf -O models/ggml-model-q4_0.gguf ``` @@ -360,7 +361,7 @@ During use, you can also convertthemodel file yourself according to the instru ### Install dependencies llama.cpp is an optional installationitem in DB-GPT. can install ...
Available add-ons Advanced Security Enterprise-grade security features GitHub Copilot Enterprise-grade AI features Premium Support Enterprise-grade 24/7 support Pricing Search or jump to... Search code, repositories, users, issues, pull requests... Provide feedback We read every piece of ...
# llama_cpp_model_path=/data/models/TheBloke/vicuna-13B-v1.5-GGUF/vicuna-13b-v1.5.Q4_K_M.gguf ### LLM cache ## Enable Model cache # MODEL_CACHE_ENABLE=True ## The storage type of model cache, now supports: memory, disk # MODEL_CACHE_STORAGE_TYPE=disk ## The max cache data in...
LLM_MODEL_PATH=/tmp/qwen2.5-0.5b-instruct-q4_k_m.gguf MODEL_TYPE=llama_cpp_server Start the DB-GPT server python dbgpt/app/dbgpt_server.py Snapshots: Include snapshots for easier review. Checklist: I have already rebased the commits and make the commit message conform to the project sta...
/resolve/main/vicuna-13b-v1.5.Q4_K_M.gguf -O models/ggml-model-q4_0.gguf ``` @@ -360,7 +361,7 @@ During use, you can also convertthemodel file yourself according to the instru ### Install dependencies llama.cpp is an optional installationitem in DB-GPT. can install ...