Text Generation
Transformers
Safetensors
laguna
laguna-xs.2
vllm
conversational
custom_code
Eval Results
Instructions to use newzyerror/fludity7.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use newzyerror/fludity7.6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="newzyerror/fludity7.6", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("newzyerror/fludity7.6", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("newzyerror/fludity7.6", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use newzyerror/fludity7.6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "newzyerror/fludity7.6" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "newzyerror/fludity7.6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/newzyerror/fludity7.6
- SGLang
How to use newzyerror/fludity7.6 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 "newzyerror/fludity7.6" \ --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": "newzyerror/fludity7.6", "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 "newzyerror/fludity7.6" \ --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": "newzyerror/fludity7.6", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use newzyerror/fludity7.6 with Docker Model Runner:
docker model run hf.co/newzyerror/fludity7.6
| {#- Iteration on laguna_glm_thinking_v5/chat_template.jinja -#} | |
| {#- Adds a default system message (used when no system message is provided in `messages`). -#} | |
| {{- "〈|EOS|〉" -}} | |
| {%- set enable_thinking = enable_thinking | default(false) -%} | |
| {%- set render_assistant_messages_raw = render_assistant_messages_raw | default(false) -%} | |
| {%- set add_generation_prompt = add_generation_prompt | default(false) -%} | |
| {#- ───── header (system message) ───── -#} | |
| {%- set system_message = "You are a helpful, conversationally-fluent assistant made by Poolside. You are here to be helpful to users through natural language conversations." -%} | |
| {%- if messages and messages[0].role == "system" -%} | |
| {%- set system_message = messages[0].content -%} | |
| {%- endif -%} | |
| {%- if (system_message and system_message.strip()) or tools -%} | |
| {{- "<system>\n" -}} | |
| {%- if system_message and system_message.strip() -%} | |
| {{- "\n" -}} | |
| {{- system_message.rstrip() -}} | |
| {%- endif -%} | |
| {%- if tools -%} | |
| {{- "\n\n### Tools\n\n" -}} | |
| {%- set ns = namespace(tool_string="You may call functions to assist with the user query.\n" | |
| ~ "All available function signatures are listed below:\n" | |
| ~ "<available_tools>\n") -%} | |
| {%- for tool in tools -%} | |
| {%- set ns.tool_string = ns.tool_string ~ (tool | tojson) ~ "\n" -%} | |
| {%- endfor -%} | |
| {%- if enable_thinking -%} | |
| {%- set tool_string = ns.tool_string + "</available_tools>\n\n" ~ | |
| "Wrap your thinking in '<think>', '</think>' tags, followed by a function call. For each function call, return an unescaped XML-like object with function name and arguments within '<tool_call>' and '</tool_call>' tags, like here:\n" ~ | |
| "<think> your thoughts here </think>\n" ~ | |
| "<tool_call>function-name\n<arg_key>argument-key</arg_key>\n<arg_value>value-of-argument-key</arg_value>\n" ~ | |
| "</tool_call>" -%} | |
| {%- else -%} | |
| {%- set tool_string = ns.tool_string + "</available_tools>\n\n" ~ | |
| "For each function call, return an unescaped XML-like object " ~ | |
| "with function name and arguments within '<tool_call>' and '</tool_call>' tags, like here:\n" ~ | |
| "<tool_call>function-name\n<arg_key>argument-key</arg_key>\n<arg_value>value-of-argument-key</arg_value>\n" ~ | |
| "</tool_call>" -%} | |
| {%- endif -%} | |
| {{- tool_string -}} | |
| {%- endif -%} | |
| {{- "\n</system>\n" -}} | |
| {%- endif -%} | |
| {#- ───── main loop ───── -#} | |
| {%- for message in messages -%} | |
| {%- set content = message.content if message.content is string else "" -%} | |
| {%- if message.role == "user" -%} | |
| {{- "<user>\n" + content + "\n</user>\n" -}} | |
| {%- elif message.role == "assistant" -%} | |
| {%- generation -%} | |
| {{- "<assistant>\n" -}} | |
| {%- if render_assistant_messages_raw -%} | |
| {#- Raw mode: prepend the generation prompt token, then dump content verbatim. -#} | |
| {#- The generation prompt is <think> when enable_thinking, </think> otherwise. -#} | |
| {#- Only prepend if content doesn't already start with it. -#} | |
| {%- if enable_thinking -%} | |
| {%- if not content.startswith('<think>') -%} | |
| {{- '<think>' -}} | |
| {%- endif -%} | |
| {%- else -%} | |
| {%- if not content.startswith('</think>') -%} | |
| {{- '</think>' -}} | |
| {%- endif -%} | |
| {%- endif -%} | |
| {{- content -}} | |
| {#- Append closing tag if content doesn't already end with it. -#} | |
| {%- if not content.endswith('</assistant>\n') and not content.endswith('</assistant>') -%} | |
| {{- '\n</assistant>' -}} | |
| {%- endif -%} | |
| {{- "\n" -}} | |
| {%- else -%} | |
| {#- Extract reasoning content from message.reasoning (vLLM field name) or message.reasoning_content, or from <think> tags -#} | |
| {%- set reasoning_content = '' %} | |
| {%- if message.reasoning is string %} | |
| {%- set reasoning_content = message.reasoning %} | |
| {%- elif message.reasoning_content is string %} | |
| {%- set reasoning_content = message.reasoning_content %} | |
| {%- endif %} | |
| {#- Always strip <think> tags from content if present to avoid duplication -#} | |
| {%- if '</think>' in content %} | |
| {%- if not reasoning_content %} | |
| {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %} | |
| {%- endif %} | |
| {%- set content = content.split('</think>')[-1].lstrip('\n') %} | |
| {%- endif %} | |
| {#- Display reasoning content for all messages -#} | |
| {%- if reasoning_content -%} | |
| {{- '<think>\n' + reasoning_content.strip() + '\n</think>\n' -}} | |
| {%- else -%} | |
| {{- '</think>\n' -}} | |
| {%- endif -%} | |
| {#- Display main content -#} | |
| {%- if content.strip() -%} | |
| {{- content.strip() ~ "\n" -}} | |
| {%- endif -%} | |
| {%- if message.tool_calls -%} | |
| {%- for tool_call in message.tool_calls -%} | |
| {%- set function_data = tool_call.function -%} | |
| {{- '<tool_call>' + function_data.name }} | |
| {% set _args = function_data.arguments %} | |
| {%- for k, v in _args.items() -%} | |
| {{- "<arg_key>" ~ k ~ "</arg_key>\n" -}} | |
| {{- "<arg_value>"}}{{ v | tojson(ensure_ascii=False) if v is not string else v }}{{ "</arg_value>\n" -}} | |
| {%- endfor -%} | |
| {{- "</tool_call>\n" -}} | |
| {%- endfor -%} | |
| {%- endif -%} | |
| {{- "</assistant>\n" -}} | |
| {%- endif -%} | |
| {%- endgeneration -%} | |
| {%- elif message.role == "tool" -%} | |
| {{- "<tool_response>\n" + content + "\n</tool_response>\n" -}} | |
| {%- elif message.role == "system" and loop.index0 != 0 -%} | |
| {#- Render additional system messages (skip the first one which is handled separately in the header) -#} | |
| {{- "<system>\n" + content + "\n</system>\n" -}} | |
| {%- endif -%} | |
| {%- endfor -%} | |
| {#- ───── generation prompt ───── -#} | |
| {%- if add_generation_prompt -%} | |
| {{- "<assistant>\n" -}} | |
| {#- ───── Include reasoning mode directive ───── -#} | |
| {%- if not enable_thinking %} | |
| {{- '</think>' -}} | |
| {%- else %} | |
| {{- '<think>' -}} | |
| {%- endif %} | |
| {%- endif -%} | |