Text Generation
Transformers
GGUF
English
qwen
qwen3
lora
home-assistant
home-automation
smart-home
iot
instruction-tuned
tool-use
conversational
Instructions to use selorahomes/Selora-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use selorahomes/Selora-AI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="selorahomes/Selora-AI") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("selorahomes/Selora-AI", dtype="auto") - llama-cpp-python
How to use selorahomes/Selora-AI with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="selorahomes/Selora-AI", filename="qwen3_17b_base.Q6_K.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use selorahomes/Selora-AI with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf selorahomes/Selora-AI:Q6_K # Run inference directly in the terminal: llama-cli -hf selorahomes/Selora-AI:Q6_K
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf selorahomes/Selora-AI:Q6_K # Run inference directly in the terminal: llama-cli -hf selorahomes/Selora-AI:Q6_K
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf selorahomes/Selora-AI:Q6_K # Run inference directly in the terminal: ./llama-cli -hf selorahomes/Selora-AI:Q6_K
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf selorahomes/Selora-AI:Q6_K # Run inference directly in the terminal: ./build/bin/llama-cli -hf selorahomes/Selora-AI:Q6_K
Use Docker
docker model run hf.co/selorahomes/Selora-AI:Q6_K
- LM Studio
- Jan
- vLLM
How to use selorahomes/Selora-AI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "selorahomes/Selora-AI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "selorahomes/Selora-AI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/selorahomes/Selora-AI:Q6_K
- SGLang
How to use selorahomes/Selora-AI with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "selorahomes/Selora-AI" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "selorahomes/Selora-AI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "selorahomes/Selora-AI" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "selorahomes/Selora-AI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use selorahomes/Selora-AI with Ollama:
ollama run hf.co/selorahomes/Selora-AI:Q6_K
- Unsloth Studio
How to use selorahomes/Selora-AI with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for selorahomes/Selora-AI to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for selorahomes/Selora-AI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for selorahomes/Selora-AI to start chatting
- Pi
How to use selorahomes/Selora-AI with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf selorahomes/Selora-AI:Q6_K
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "selorahomes/Selora-AI:Q6_K" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use selorahomes/Selora-AI with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf selorahomes/Selora-AI:Q6_K
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default selorahomes/Selora-AI:Q6_K
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use selorahomes/Selora-AI with Docker Model Runner:
docker model run hf.co/selorahomes/Selora-AI:Q6_K
- Lemonade
How to use selorahomes/Selora-AI with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull selorahomes/Selora-AI:Q6_K
Run and chat with the model
lemonade run user.Selora-AI-Q6_K
List all available models
lemonade list
Gunnar Beck Nelson commited on
Selora AI v0.4.7
Browse files- manifest.json +36 -15
- prompts/command_system_prompt.txt +2 -2
- qwen3_17b_base.f16.gguf +0 -3
- selora-v047-answer.f16.gguf +1 -1
- selora-v047-automation.f16.gguf +2 -2
- selora-v047-clarification.f16.gguf +1 -1
- selora-v047-command.f16.gguf +1 -1
manifest.json
CHANGED
|
@@ -1,50 +1,54 @@
|
|
| 1 |
{
|
| 2 |
"name": "selora-ai-local",
|
| 3 |
"version": "0.4.7",
|
| 4 |
-
"description": "Selora AI v0.4.7 \u2014
|
| 5 |
"base_model": {
|
| 6 |
"id": "Qwen/Qwen3-1.7B",
|
| 7 |
"format": "gguf",
|
| 8 |
-
"dtype": "
|
| 9 |
-
"filename": "qwen3_17b_base.
|
| 10 |
-
"size_bytes":
|
| 11 |
-
"sha256": "
|
| 12 |
},
|
| 13 |
"loras": [
|
| 14 |
{
|
| 15 |
"slot": 0,
|
| 16 |
"name": "command",
|
|
|
|
| 17 |
"filename": "selora-v047-command.f16.gguf",
|
| 18 |
"size_bytes": 19938528,
|
| 19 |
-
"sha256": "
|
| 20 |
},
|
| 21 |
{
|
| 22 |
"slot": 1,
|
| 23 |
"name": "automation",
|
|
|
|
| 24 |
"filename": "selora-v047-automation.f16.gguf",
|
| 25 |
-
"size_bytes":
|
| 26 |
-
"sha256": "
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"slot": 2,
|
| 30 |
"name": "answer",
|
|
|
|
| 31 |
"filename": "selora-v047-answer.f16.gguf",
|
| 32 |
"size_bytes": 14957792,
|
| 33 |
-
"sha256": "
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"slot": 3,
|
| 37 |
"name": "clarification",
|
|
|
|
| 38 |
"filename": "selora-v047-clarification.f16.gguf",
|
| 39 |
"size_bytes": 9977056,
|
| 40 |
-
"sha256": "
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"system_prompts": {
|
| 44 |
"command": {
|
| 45 |
"filename": "command_system_prompt.txt",
|
| 46 |
-
"size_bytes":
|
| 47 |
-
"sha256": "
|
| 48 |
},
|
| 49 |
"automation": {
|
| 50 |
"filename": "automation_system_prompt.txt",
|
|
@@ -64,12 +68,29 @@
|
|
| 64 |
},
|
| 65 |
"runtime": {
|
| 66 |
"cache_prompt": true,
|
| 67 |
-
"ctx_size":
|
| 68 |
},
|
| 69 |
"training": {
|
| 70 |
"framework": "mlx-lm",
|
| 71 |
"base_model_repo": "Qwen/Qwen3-1.7B",
|
| 72 |
-
"
|
| 73 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
}
|
| 75 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"name": "selora-ai-local",
|
| 3 |
"version": "0.4.7",
|
| 4 |
+
"description": "Selora AI v0.4.7 \u2014 Qwen3-1.7B Q6_K base + 4 LoRA specialists. Hub-optimal base quant (fits Vega 8 VRAM, no GTT spill). Specialists retrained on a compacted-JSON corpus (automation rank 32); command specialist prompt updated, other three unchanged from v0.4.6.",
|
| 5 |
"base_model": {
|
| 6 |
"id": "Qwen/Qwen3-1.7B",
|
| 7 |
"format": "gguf",
|
| 8 |
+
"dtype": "Q6_K",
|
| 9 |
+
"filename": "qwen3_17b_base.Q6_K.gguf",
|
| 10 |
+
"size_bytes": 1673006880,
|
| 11 |
+
"sha256": "a00bbdb411872149d73e1a0683b9b8a9f13cf74f98ba70ff8e8e430d9a093179"
|
| 12 |
},
|
| 13 |
"loras": [
|
| 14 |
{
|
| 15 |
"slot": 0,
|
| 16 |
"name": "command",
|
| 17 |
+
"rank": 16,
|
| 18 |
"filename": "selora-v047-command.f16.gguf",
|
| 19 |
"size_bytes": 19938528,
|
| 20 |
+
"sha256": "49ba46bc054259409f5cd52eb3d9971101ed858fba27c6678c89e145815af515"
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"slot": 1,
|
| 24 |
"name": "automation",
|
| 25 |
+
"rank": 32,
|
| 26 |
"filename": "selora-v047-automation.f16.gguf",
|
| 27 |
+
"size_bytes": 59791968,
|
| 28 |
+
"sha256": "32e5633f0e554fec5e336d993647065f85a4fffd348366cdc3417ca34824b527"
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"slot": 2,
|
| 32 |
"name": "answer",
|
| 33 |
+
"rank": 12,
|
| 34 |
"filename": "selora-v047-answer.f16.gguf",
|
| 35 |
"size_bytes": 14957792,
|
| 36 |
+
"sha256": "7584a04e13dd3e4973bfeb89ed01b7b29b3288d768d7bee15bcea3de89ff50c7"
|
| 37 |
},
|
| 38 |
{
|
| 39 |
"slot": 3,
|
| 40 |
"name": "clarification",
|
| 41 |
+
"rank": 8,
|
| 42 |
"filename": "selora-v047-clarification.f16.gguf",
|
| 43 |
"size_bytes": 9977056,
|
| 44 |
+
"sha256": "75c06c0efbd9ca1e7108ec6ec5811f68e2dc5639d01ef583148a151b11398847"
|
| 45 |
}
|
| 46 |
],
|
| 47 |
"system_prompts": {
|
| 48 |
"command": {
|
| 49 |
"filename": "command_system_prompt.txt",
|
| 50 |
+
"size_bytes": 1374,
|
| 51 |
+
"sha256": "0fa2b1669dedca18ddba2cebd7f72cd7cff0f7431b87ca4166a4bf60c7aed697"
|
| 52 |
},
|
| 53 |
"automation": {
|
| 54 |
"filename": "automation_system_prompt.txt",
|
|
|
|
| 68 |
},
|
| 69 |
"runtime": {
|
| 70 |
"cache_prompt": true,
|
| 71 |
+
"ctx_size": 8192
|
| 72 |
},
|
| 73 |
"training": {
|
| 74 |
"framework": "mlx-lm",
|
| 75 |
"base_model_repo": "Qwen/Qwen3-1.7B",
|
| 76 |
+
"scale": 20.0,
|
| 77 |
+
"rank_per_specialist": {
|
| 78 |
+
"command": 16,
|
| 79 |
+
"automation": 32,
|
| 80 |
+
"answer": 12,
|
| 81 |
+
"clarification": 8
|
| 82 |
+
},
|
| 83 |
+
"iterations_per_specialist": {
|
| 84 |
+
"command": 800,
|
| 85 |
+
"automation": 1800,
|
| 86 |
+
"answer": 600,
|
| 87 |
+
"clarification": 450
|
| 88 |
+
},
|
| 89 |
+
"examples_per_specialist": {
|
| 90 |
+
"command": 11000,
|
| 91 |
+
"automation": 10000,
|
| 92 |
+
"answer": 5500,
|
| 93 |
+
"clarification": 3000
|
| 94 |
+
}
|
| 95 |
}
|
| 96 |
}
|
prompts/command_system_prompt.txt
CHANGED
|
@@ -5,11 +5,11 @@ Given a user command and the AVAILABLE ENTITIES list, respond with ONE JSON obje
|
|
| 5 |
|
| 6 |
Rules:
|
| 7 |
- c: ordered array of one or more service calls. Calls execute in array order.
|
| 8 |
-
- s: HA service in "domain.action" form
|
| 9 |
- e: canonical entity_id from AVAILABLE ENTITIES. Never use the human alias — always the entity_id.
|
| 10 |
- d: service parameters object. Omit the d key entirely when there are no params (do not include "d":{}).
|
| 11 |
- r: ≤ 1 sentence past-tense confirmation describing what got done (e.g. "Kitchen light on.").
|
| 12 |
-
- The service domain (before the dot) must match the entity_id's domain. light.turn_on goes with light.* entities,
|
| 13 |
- For multi-target requests, produce one c entry per (service, entity_id) pair.
|
| 14 |
|
| 15 |
Output JSON only — no narration, no markdown fences, no chain-of-thought.
|
|
|
|
| 5 |
|
| 6 |
Rules:
|
| 7 |
- c: ordered array of one or more service calls. Calls execute in array order.
|
| 8 |
+
- s: HA service in "domain.action" form. Only these domains are accepted for immediate execution: light, switch, fan, media_player, climate, input_boolean, scene, cover. Examples: "light.turn_on", "switch.turn_off", "media_player.media_play", "cover.open_cover", "scene.turn_on". Do not emit lock.*, alarm_*, script.*, notify.*, or any other domain — those are blocked by the safety policy and the call will fail.
|
| 9 |
- e: canonical entity_id from AVAILABLE ENTITIES. Never use the human alias — always the entity_id.
|
| 10 |
- d: service parameters object. Omit the d key entirely when there are no params (do not include "d":{}).
|
| 11 |
- r: ≤ 1 sentence past-tense confirmation describing what got done (e.g. "Kitchen light on.").
|
| 12 |
+
- The service domain (before the dot) must match the entity_id's domain. light.turn_on goes with light.* entities, cover.open_cover goes with cover.* entities, etc.
|
| 13 |
- For multi-target requests, produce one c entry per (service, entity_id) pair.
|
| 14 |
|
| 15 |
Output JSON only — no narration, no markdown fences, no chain-of-thought.
|
qwen3_17b_base.f16.gguf
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3e4009f0d96955a45f29aa77bded839d376d7832823c6909f76c84ace81dc445
|
| 3 |
-
size 4069678880
|
|
|
|
|
|
|
|
|
|
|
|
selora-v047-answer.f16.gguf
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14957792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7584a04e13dd3e4973bfeb89ed01b7b29b3288d768d7bee15bcea3de89ff50c7
|
| 3 |
size 14957792
|
selora-v047-automation.f16.gguf
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32e5633f0e554fec5e336d993647065f85a4fffd348366cdc3417ca34824b527
|
| 3 |
+
size 59791968
|
selora-v047-clarification.f16.gguf
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9977056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75c06c0efbd9ca1e7108ec6ec5811f68e2dc5639d01ef583148a151b11398847
|
| 3 |
size 9977056
|
selora-v047-command.f16.gguf
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 19938528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49ba46bc054259409f5cd52eb3d9971101ed858fba27c6678c89e145815af515
|
| 3 |
size 19938528
|