neuml/txtai
1
0
Fork 0
mirror of https://github.com/neuml/txtai.git synced 2026-10-11 21:39:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update model paths

Browse Source
This commit is contained in:
davidmezzetti
2025-12-12 10:46:36 -05:00
parent aca56cfe53
commit 4aa9db69fc
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/53_Integrate_LLM_Frameworks.ipynb
+1 -1
View File
@@ -90,7 +90,7 @@
"embeddings.index(data)\n",
"\n",
"# Create LLM with llama.cpp - GGUF file is automatically downloaded\n",
"llm = LLM(\"TheBloke/Mistral-7B-OpenOrca-GGUF/mistral-7b-openorca.Q4_K_M.gguf\", verbose=True)\n",
"llm = LLM(\"unsloth/Qwen3-4B-Instruct-2507-GGUF/Qwen3-4B-Instruct-2507-Q4_K_M.gguf\", verbose=True)\n",
"\n",
"template = \"\"\"<|im_start|>system\n",
"You are a friendly assistant. You answer questions from users.<|im_end|>\n",
examples/62_RAG_with_llama_cpp_and_external_API_services.ipynb
+3 -3
View File
@@ -180,7 +180,7 @@
"from txtai import LLM\n",
"\n",
"# LLM instance\n",
"llm = LLM(path=\"TheBloke/Mistral-7B-OpenOrca-GGUF/mistral-7b-openorca.Q4_K_M.gguf\")\n",
"llm = LLM(path=\"unsloth/Qwen3-4B-Instruct-2507-GGUF/Qwen3-4B-Instruct-2507-Q4_K_M.gguf\")\n",
"\n",
"# Question and context\n",
"question = \"Write a list of invented electric-powered devices\"\n",
@@ -235,11 +235,11 @@
"\n",
"# Download models\n",
"!wget https://huggingface.co/second-state/All-MiniLM-L6-v2-Embedding-GGUF/resolve/main/all-MiniLM-L6-v2-Q4_K_M.gguf\n",
"!wget https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GGUF/resolve/main/mistral-7b-openorca.Q4_K_M.gguf\n",
"!wget https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen3-4B-Instruct-2507-Q4_K_M.gguf\n",
"\n",
"# Start local API services\n",
"!nohup python -m llama_cpp.server --n_gpu_layers -1 --model all-MiniLM-L6-v2-Q4_K_M.gguf --host 127.0.0.1 --port 8000 &> vector.log &\n",
"!nohup python -m llama_cpp.server --n_gpu_layers -1 --model mistral-7b-openorca.Q4_K_M.gguf --chat_format chatml --host 127.0.0.1 --port 8001 &> llm.log &\n",
"!nohup python -m llama_cpp.server --n_gpu_layers -1 --model Qwen3-4B-Instruct-2507-Q4_K_M.gguf --chat_format chatml --host 127.0.0.1 --port 8001 &> llm.log &\n",
"!sleep 30"
]
},