--- base_model: nvidia/Orchestrator-8B tags: - llama-cpp - gguf-my-repo - reinforcementlearning - tool-calling - multi-reasoning - orchestrator-model - orchestration language: - en pipeline_tag: reinforcement-learning --- # AXONVERTEX-AI-RESEARCH/Orchestrator-8B-Q8_0-GGUF This model was converted to GGUF format from [`nvidia/Orchestrator-8B`](https://huggingface.co/nvidia/Orchestrator-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/nvidia/Orchestrator-8B) for more details on the model. ## Use with ollama ```bash root@90dd7d73d62b:/# ollama pull hf.co/AXONVERTEX-AI-RESEARCH/Qwen3-Embedding-0.6B-Q8_0-GGUF:Q8_0 pulling manifest pulling ee029816fb96: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 639 MB pulling eb4402837c78: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 1.5 KB pulling 4a6ce91d86a8: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 99 B pulling be570f0686c3: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 549 B verifying sha256 digest writing manifest success root@90dd7d73d62b:/# ollama pull hf.co/AXONVERTEX-AI-RESEARCH/Orchestrator-8B-Q8_0-GGUF:Q8_0 pulling manifest pulling 7ba8f19c5542: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 8.7 GB pulling eb4402837c78: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 1.5 KB pulling 4a6ce91d86a8: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 99 B pulling 9dfdfd94d3aa: 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 552 B verifying sha256 digest writing manifest success root@90dd7d73d62b:/# ollama run hf.co/AXONVERTEX-AI-RESEARCH/Orchestrator-8B-Q8_0-GGUF:Q8_0 >>> Hello Okay, the user said "Hello". I need to respond appropriately. Since they just greeted me, I should acknowledge their greeting and offer assistance. Let me make sure my response is friendly and open-ended. Maybe something like, "Hello! How can I assist you today?" That sounds good. I should keep it simple and inviting. Hello! How can I assist you today? 😊 ``` ## chat-template ```bash {%- if tools %} {{- '<|im_start|>system\n' }} {%- if messages[0].role == 'system' %} {{- messages[0].content + '\n\n' }} {%- endif %} {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} {%- for tool in tools %} {{- "\n" }} {{- tool | tojson }} {%- endfor %} {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} {%- else %} {%- if messages[0].role == 'system' %} {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} {%- for message in messages[::-1] %} {%- set index = (messages|length - 1) - loop.index0 %} {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} {%- set ns.multi_step_tool = false %} {%- set ns.last_query_index = index %} {%- endif %} {%- endfor %} {%- for message in messages %} {%- if message.content is string %} {%- set content = message.content %} {%- else %} {%- set content = '' %} {%- endif %} {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} {%- elif message.role == "assistant" %} {%- set reasoning_content = '' %} {%- if message.reasoning_content is string %} {%- set reasoning_content = message.reasoning_content %} {%- else %} {%- if '' in content %} {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} {%- set content = content.split('')[-1].lstrip('\n') %} {%- endif %} {%- endif %} {%- if loop.index0 > ns.last_query_index %} {%- if loop.last or (not loop.last and reasoning_content) %} {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} {%- else %} {{- '<|im_start|>' + message.role + '\n' + content }} {%- endif %} {%- else %} {{- '<|im_start|>' + message.role + '\n' + content }} {%- endif %} {%- if message.tool_calls %} {%- for tool_call in message.tool_calls %} {%- if (loop.first and content) or (not loop.first) %} {{- '\n' }} {%- endif %} {%- if tool_call.function %} {%- set tool_call = tool_call.function %} {%- endif %} {{- '\n{"name": "' }} {{- tool_call.name }} {{- '", "arguments": ' }} {%- if tool_call.arguments is string %} {{- tool_call.arguments }} {%- else %} {{- tool_call.arguments | tojson }} {%- endif %} {{- '}\n' }} {%- endfor %} {%- endif %} {{- '<|im_end|>\n' }} {%- elif message.role == "tool" %} {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} {{- '<|im_start|>user' }} {%- endif %} {{- '\n\n' }} {{- content }} {{- '\n' }} {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} {{- '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<|im_start|>assistant\n' }} {%- if enable_thinking is defined and enable_thinking is false %} {{- '\n\n\n\n' }} {%- endif %} {%- endif %} ``` ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo AXONVERTEX-AI-RESEARCH/Orchestrator-8B-Q8_0-GGUF --hf-file orchestrator-8b-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo AXONVERTEX-AI-RESEARCH/Orchestrator-8B-Q8_0-GGUF --hf-file orchestrator-8b-q8_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo AXONVERTEX-AI-RESEARCH/Orchestrator-8B-Q8_0-GGUF --hf-file orchestrator-8b-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo AXONVERTEX-AI-RESEARCH/Orchestrator-8B-Q8_0-GGUF --hf-file orchestrator-8b-q8_0.gguf -c 2048 ```