Text Generation
MLX
Safetensors
qwen3_moe
erotic
explicit
abliterated
conversational
8-bit precision
Instructions to use litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8 with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8 with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8"
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 litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8
Run Hermes
hermes
- MLX LM
How to use litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "litmudoc/Qwen3-30B-A3B-abliterated-MLX-Q8", "messages": [ {"role": "user", "content": "Hello"} ] }'
Upload 3 files
Browse files- config.json +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -12,7 +12,7 @@
|
|
| 12 |
"hidden_size": 2048,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 6144,
|
| 15 |
-
"max_position_embeddings":
|
| 16 |
"max_window_layers": 48,
|
| 17 |
"mlp_only_layers": [],
|
| 18 |
"model_type": "qwen3_moe",
|
|
|
|
| 12 |
"hidden_size": 2048,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 6144,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
"max_window_layers": 48,
|
| 17 |
"mlp_only_layers": [],
|
| 18 |
"model_type": "qwen3_moe",
|
tokenizer_config.json
CHANGED
|
@@ -227,7 +227,7 @@
|
|
| 227 |
"<|video_pad|>"
|
| 228 |
],
|
| 229 |
"bos_token": null,
|
| 230 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\
|
| 231 |
"clean_up_tokenization_spaces": false,
|
| 232 |
"eos_token": "<|im_end|>",
|
| 233 |
"errors": "replace",
|
|
|
|
| 227 |
"<|video_pad|>"
|
| 228 |
],
|
| 229 |
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\n\n' }}\n {%- endif %}\n {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}\n {%- for tool in tools %}\n {{- "\n" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- set tool_start = "<tool_response>" %}\n {%- set tool_start_length = tool_start|length %}\n {%- set start_of_message = message.content[:tool_start_length] %}\n {%- set tool_end = "</tool_response>" %}\n {%- set tool_end_length = tool_end|length %}\n {%- set start_pos = (message.content|length) - tool_end_length %}\n {%- if start_pos < 0 %}\n {%- set start_pos = 0 %}\n {%- endif %}\n {%- set end_of_message = message.content[start_pos:] %}\n {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == "assistant" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}\n {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}\n {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\n{"name": "' }}\n {{- tool_call.name }}\n {{- '", "arguments": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == "tool" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\n<tool_response>\n' }}\n {{- message.content }}\n {{- '\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}\n {{- '<|im_end|>\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\n\n</think>\n\n' }}\n {%- endif %}\n{%- endif %}",
|
| 231 |
"clean_up_tokenization_spaces": false,
|
| 232 |
"eos_token": "<|im_end|>",
|
| 233 |
"errors": "replace",
|