Image-Text-to-Text
Transformers
Safetensors
qwen3_5
quantized
w8a16
fp8
conversational
compressed-tensors
Instructions to use hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8") model = AutoModelForMultimodalLM.from_pretrained("hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8
- SGLang
How to use hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8 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 "hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8" \ --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": "hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8" \ --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": "hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8 with Docker Model Runner:
docker model run hf.co/hoborific/Darker-Scarlett-27B-v0.1-W8A16-FP8
| {#- | |
| qwen38_flexible.jinja | |
| ===================================================================== | |
| Drop-in replacement chat template for Qwen/Qwen3.8-27B (and other | |
| Qwen3.8 models), forked from the upstream chat_template.jinja. | |
| Same wire format (<|im_start|>/<|im_end|>, <think> blocks, tool_call | |
| XML), but without the rigid conversation-shape enforcement. | |
| RELAXED vs upstream: | |
| R1 No 'No user query found in messages.' raise. Assistant-first, | |
| user-less, or tool-response-only transcripts render fine. | |
| R2 System messages are allowed ANYWHERE in the transcript, not | |
| just at index 0. Mid-conversation system notes render as their | |
| own <|im_start|>system block instead of raising | |
| 'System message must be at the beginning.' | |
| R3 'developer' role accepted as an alias for 'system' (OpenAI | |
| Responses-API convention used by modern harnesses). | |
| R4 Unknown roles (narrator, char, example_user, ...) render | |
| verbatim as <|im_start|>{role} ... <|im_end|> instead of | |
| raising 'Unexpected message role.'. | |
| R5 continue_final_message support: when true and the last message | |
| is an assistant turn, that turn is left open (no <|im_end|>) | |
| for prefilling, and no generation prompt is appended. | |
| R6 No alternation assumptions anywhere: consecutive user turns, | |
| consecutive assistant turns, assistant-leading transcripts and | |
| trailing assistant turns all render as-is. | |
| KEPT from upstream (byte-compatible rendering): | |
| - render_content macro with vision counters | |
| - reasoning_effort (xhigh / medium / low) instruction injection | |
| - preserve_thinking (defaults TRUE on 3.8) + last_query_index walk | |
| - tool definitions block and <tool_call>/<tool_response> rendering | |
| - generation prompt with enable_thinking gate | |
| USAGE | |
| llama.cpp : llama-server -m qwen38-27b-*.gguf \ | |
| --chat-template-file qwen38_flexible.jinja | |
| vLLM : vllm serve Qwen/Qwen3.8-27B \ | |
| --chat-template qwen38_flexible.jinja \ | |
| --tool-call-parser qwen3_coder --reasoning-parser qwen3 | |
| SGLang : python -m sglang.launch_server --model-path Qwen/Qwen3.8-27B \ | |
| --chat-template qwen38_flexible.jinja \ | |
| --tool-call-parser qwen3_coder --reasoning-parser qwen3 | |
| Forked from Qwen/Qwen3.8-27B/chat_template.jinja (2026-08-13). | |
| License: Apache 2.0 (same as upstream). | |
| -#} | |
| {%- set image_count = namespace(value=0) %} | |
| {%- set video_count = namespace(value=0) %} | |
| {%- macro render_content(content, do_vision_count, is_system_content=false) %} | |
| {%- if content is string %} | |
| {{- content }} | |
| {%- elif content is iterable and content is not mapping %} | |
| {%- for item in content %} | |
| {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} | |
| {%- if is_system_content %} | |
| {{- raise_exception('System message cannot contain images.') }} | |
| {%- endif %} | |
| {%- if do_vision_count %} | |
| {%- set image_count.value = image_count.value + 1 %} | |
| {%- endif %} | |
| {%- if add_vision_id is defined and add_vision_id %} | |
| {{- 'Picture ' ~ image_count.value ~ ': ' }} | |
| {%- endif %} | |
| {{- '<|vision_start|><|image_pad|><|vision_end|>' }} | |
| {%- elif 'video' in item or item.type == 'video' %} | |
| {%- if is_system_content %} | |
| {{- raise_exception('System message cannot contain videos.') }} | |
| {%- endif %} | |
| {%- if do_vision_count %} | |
| {%- set video_count.value = video_count.value + 1 %} | |
| {%- endif %} | |
| {%- if add_vision_id is defined and add_vision_id %} | |
| {{- 'Video ' ~ video_count.value ~ ': ' }} | |
| {%- endif %} | |
| {{- '<|vision_start|><|video_pad|><|vision_end|>' }} | |
| {%- elif 'text' in item %} | |
| {{- item.text }} | |
| {%- else %} | |
| {{- raise_exception('Unexpected item type in content.') }} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- elif content is none or content is undefined %} | |
| {{- '' }} | |
| {%- else %} | |
| {{- raise_exception('Unexpected content type.') }} | |
| {%- endif %} | |
| {%- endmacro %} | |
| {%- if not messages %} | |
| {{- raise_exception('No messages provided.') }} | |
| {%- endif %} | |
| {#- reasoning_effort instruction injection (identical to upstream) -#} | |
| {%- set reasoning_instructions = '' %} | |
| {%- if enable_thinking is undefined or enable_thinking is true %} | |
| {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %} | |
| {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %} | |
| {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }} | |
| {%- endif %} | |
| {%- if resolved_reasoning_effort == 'xhigh' %} | |
| {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %} | |
| {%- elif resolved_reasoning_effort == 'low' %} | |
| {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %} | |
| {%- endif %} | |
| {%- endif %} | |
| {#- R3: 'developer' at index 0 is treated exactly like 'system' -#} | |
| {%- set first_is_system = messages[0].role == 'system' or messages[0].role == 'developer' %} | |
| {%- if tools and tools is iterable and tools is not mapping %} | |
| {{- '<|im_start|>system\n' }} | |
| {%- if reasoning_instructions %} | |
| {{- reasoning_instructions + '\n\n' }} | |
| {%- endif %} | |
| {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }} | |
| {%- for tool in tools %} | |
| {{- "\n" }} | |
| {%- if tool.function is defined %} | |
| {{- tool.function | tojson }} | |
| {%- else %} | |
| {{- tool | tojson }} | |
| {%- endif %} | |
| {%- endfor %} | |
| {{- "\n</tools>" }} | |
| {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }} | |
| {%- if first_is_system %} | |
| {%- set content = render_content(messages[0].content, false, true)|trim %} | |
| {%- if content %} | |
| {{- '\n\n' + content }} | |
| {%- endif %} | |
| {%- endif %} | |
| {{- '<|im_end|>\n' }} | |
| {%- else %} | |
| {%- if first_is_system %} | |
| {%- set content = render_content(messages[0].content, false, true)|trim %} | |
| {%- if content %} | |
| {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }} | |
| {%- elif reasoning_instructions %} | |
| {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- elif reasoning_instructions %} | |
| {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- endif %} | |
| {#- last_query_index walk (identical to upstream logic) -#} | |
| {%- 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" %} | |
| {%- set content = render_content(message.content, false)|trim %} | |
| {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %} | |
| {%- set ns.multi_step_tool = false %} | |
| {%- set ns.last_query_index = index %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- endfor %} | |
| {#- R1: upstream raised 'No user query found in messages.' here when the | |
| transcript has no non-tool-response user turn (assistant-first, RP | |
| transcripts, pure continuations). We simply keep the default index: | |
| with preserve_thinking=true (3.8 default) the index is not consulted | |
| anyway, and with preserve_thinking=false it only affects which | |
| historical <think> blocks survive. -#} | |
| {%- if ns.multi_step_tool %} | |
| {%- set ns.last_query_index = messages|length - 1 %} | |
| {%- endif %} | |
| {%- for message in messages %} | |
| {%- set content = render_content(message.content, true)|trim %} | |
| {%- if message.role == "system" or message.role == "developer" %} | |
| {#- R2/R3: index 0 was already merged into the header above. A | |
| system/developer note LATER in the transcript renders as its | |
| own block instead of raising. -#} | |
| {%- if not loop.first %} | |
| {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- elif message.role == "user" %} | |
| {{- '<|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 %} | |
| {#- Rescue thinking embedded in content (harnesses that stuff | |
| <think> into the content string). Handles </thinking> and | |
| whitespace variants emitted by some quant runtimes. -#} | |
| {%- set think_end = '' %} | |
| {%- if '</think>' in content %} | |
| {%- set think_end = '</think>' %} | |
| {%- elif '</thinking>' in content %} | |
| {%- set think_end = '</thinking>' %} | |
| {%- elif '</ think>' in content %} | |
| {%- set think_end = '</ think>' %} | |
| {%- elif '</think >' in content %} | |
| {%- set think_end = '</think >' %} | |
| {%- endif %} | |
| {%- if think_end %} | |
| {%- set parts = content.split(think_end) %} | |
| {%- set reasoning_content = parts[0] %} | |
| {%- set content = parts[1:] | join(think_end) %} | |
| {%- if '<think>' in reasoning_content %} | |
| {%- set reasoning_content = reasoning_content.split('<think>')[1:] | join('<think>') %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- set reasoning_content = reasoning_content | trim %} | |
| {%- set content = content | trim %} | |
| {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %} | |
| {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }} | |
| {%- else %} | |
| {{- '<|im_start|>' + message.role + '\n' + content }} | |
| {%- endif %} | |
| {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} | |
| {%- if '<tool_call>' in content %} | |
| {%- set content = content.split('<tool_call>')[0] | trim %} | |
| {%- endif %} | |
| {%- for tool_call in message.tool_calls %} | |
| {%- if tool_call.function is defined %} | |
| {%- set tool_call = tool_call.function %} | |
| {%- endif %} | |
| {%- if loop.first %} | |
| {%- if content|trim %} | |
| {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }} | |
| {%- else %} | |
| {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }} | |
| {%- endif %} | |
| {%- else %} | |
| {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }} | |
| {%- endif %} | |
| {%- if tool_call.arguments is defined and tool_call.arguments != '' %} | |
| {%- if tool_call.arguments is mapping %} | |
| {%- for args_name, args_value in tool_call.arguments|items %} | |
| {{- '<parameter=' + args_name + '>\n' }} | |
| {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %} | |
| {{- args_value }} | |
| {{- '\n</parameter>\n' }} | |
| {%- endfor %} | |
| {%- elif tool_call.arguments is string %} | |
| {{- raise_exception("qwen38_flexible: tool_call.arguments must be a JSON object (mapping), got a string. Deserialize the JSON-encoded arguments once on ingest and store the resulting object.") }} | |
| {%- endif %} | |
| {%- endif %} | |
| {{- '</function>\n</tool_call>' }} | |
| {%- endfor %} | |
| {%- endif %} | |
| {#- R5: leave the final assistant turn OPEN (no <|im_end|>) when | |
| prefilling via continue_final_message. -#} | |
| {%- if continue_final_message is defined and continue_final_message and loop.last %} | |
| {%- else %} | |
| {{- '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- elif message.role == "tool" %} | |
| {%- if loop.previtem and loop.previtem.role != "tool" %} | |
| {{- '<|im_start|>user' }} | |
| {%- endif %} | |
| {{- '\n<tool_response>\n' }} | |
| {{- content }} | |
| {{- '\n</tool_response>' }} | |
| {%- if not loop.last and loop.nextitem.role != "tool" %} | |
| {{- '<|im_end|>\n' }} | |
| {%- elif loop.last %} | |
| {{- '<|im_end|>\n' }} | |
| {%- endif %} | |
| {%- else %} | |
| {#- R4: unknown roles render verbatim instead of raising. | |
| Handy for narrators / multi-character / example transcripts. -#} | |
| {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- if add_generation_prompt and not (continue_final_message is defined and continue_final_message) %} | |
| {{- '<|im_start|>assistant\n' }} | |
| {%- if enable_thinking is defined and enable_thinking is false %} | |
| {{- '<think>\n\n</think>\n\n' }} | |
| {%- else %} | |
| {{- '<think>\n' }} | |
| {%- endif %} | |
| {%- endif %} | |