Text Generation
Transformers
Safetensors
step3p5
quantized
abliterated
uncensored
Mixture of Experts
conversational
custom_code
Instructions to use Kilinskiy/Step-3.5-Flash-Ablitirated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kilinskiy/Step-3.5-Flash-Ablitirated with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Kilinskiy/Step-3.5-Flash-Ablitirated", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Kilinskiy/Step-3.5-Flash-Ablitirated", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Kilinskiy/Step-3.5-Flash-Ablitirated", trust_remote_code=True, device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Kilinskiy/Step-3.5-Flash-Ablitirated with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Kilinskiy/Step-3.5-Flash-Ablitirated" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kilinskiy/Step-3.5-Flash-Ablitirated", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Kilinskiy/Step-3.5-Flash-Ablitirated
- SGLang
How to use Kilinskiy/Step-3.5-Flash-Ablitirated 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 "Kilinskiy/Step-3.5-Flash-Ablitirated" \ --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": "Kilinskiy/Step-3.5-Flash-Ablitirated", "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 "Kilinskiy/Step-3.5-Flash-Ablitirated" \ --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": "Kilinskiy/Step-3.5-Flash-Ablitirated", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Kilinskiy/Step-3.5-Flash-Ablitirated with Docker Model Runner:
docker model run hf.co/Kilinskiy/Step-3.5-Flash-Ablitirated
Upload chat_template.jinja
Browse files- chat_template.jinja +80 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% macro render_content(content) %}{% if content is none %}{{- '' }}{% elif content is string %}{{- content }}{% elif content is mapping %}{{- content['value'] if 'value' in content else content['text'] }}{% elif content is iterable %}{% for item in content %}{% if item.type == 'text' %}{{- item['value'] if 'value' in item else item['text'] }}{% elif item.type == 'image' %}<im_patch>{% endif %}{% endfor %}{% endif %}{% endmacro %}
|
| 2 |
+
{{bos_token}}{%- if tools %}
|
| 3 |
+
{{- '<|im_start|>system\n' }}
|
| 4 |
+
{%- if messages[0].role == 'system' %}
|
| 5 |
+
{{- render_content(messages[0].content) + '\n\n' }}
|
| 6 |
+
{%- endif %}
|
| 7 |
+
{{- "# Tools\n\nYou have access to the following functions in JSONSchema format:\n\n<tools>" }}
|
| 8 |
+
{%- for tool in tools %}
|
| 9 |
+
{{- "\n" }}
|
| 10 |
+
{{- tool | tojson(ensure_ascii=False) }}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{{- "\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=...>\n...\n</function> block must be nested within <tool_call>\n...\n</tool_call> XML tags\n- Required parameters MUST be specified\n</IMPORTANT><|im_end|>\n" }}
|
| 13 |
+
{%- else %}
|
| 14 |
+
{%- if messages[0].role == 'system' %}
|
| 15 |
+
{{- '<|im_start|>system\n' + render_content(messages[0].content) + '<|im_end|>\n' }}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 19 |
+
{%- for message in messages[::-1] %}
|
| 20 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 21 |
+
{%- if ns.multi_step_tool and message.role == "user" and render_content(message.content) is string and not(render_content(message.content).startswith('<tool_response>') and render_content(message.content).endswith('</tool_response>')) %}
|
| 22 |
+
{%- set ns.multi_step_tool = false %}
|
| 23 |
+
{%- set ns.last_query_index = index %}
|
| 24 |
+
{%- endif %}
|
| 25 |
+
{%- endfor %}
|
| 26 |
+
{%- for message in messages %}
|
| 27 |
+
{%- set content = render_content(message.content) %}
|
| 28 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 29 |
+
{%- set role_name = 'observation' if (message.role == "system" and not loop.first and message.name == 'observation') else message.role %}
|
| 30 |
+
{{- '<|im_start|>' + role_name + '\n' + content + '<|im_end|>' + '\n' }}
|
| 31 |
+
{%- elif message.role == "assistant" %}
|
| 32 |
+
{%- if message.reasoning_content is string %}
|
| 33 |
+
{%- set reasoning_content = render_content(message.reasoning_content) %}
|
| 34 |
+
{%- else %}
|
| 35 |
+
{%- if '</think>' in content %}
|
| 36 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{%- set reasoning_content = '' %}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n' + content }}
|
| 44 |
+
{%- else %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 46 |
+
{%- endif %}
|
| 47 |
+
{%- if message.tool_calls %}
|
| 48 |
+
{%- for tool_call in message.tool_calls %}
|
| 49 |
+
{%- if tool_call.function is defined %}
|
| 50 |
+
{%- set tool_call = tool_call.function %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 53 |
+
{%- if tool_call.arguments is defined %}
|
| 54 |
+
{%- set arguments = tool_call.arguments %}
|
| 55 |
+
{%- for args_name, args_value in arguments|items %}
|
| 56 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 57 |
+
{%- set args_value = args_value | tojson(ensure_ascii=False) | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 58 |
+
{{- args_value }}
|
| 59 |
+
{{- '\n</parameter>\n' }}
|
| 60 |
+
{%- endfor %}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{{- '</function>\n</tool_call>' }}
|
| 63 |
+
{%- endfor %}
|
| 64 |
+
{%- endif %}
|
| 65 |
+
{{- '<|im_end|>\n' }}
|
| 66 |
+
{%- elif message.role == "tool" %}
|
| 67 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 68 |
+
{{- '<|im_start|>tool_response\n' }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{{- '<tool_response>' }}
|
| 71 |
+
{{- content }}
|
| 72 |
+
{{- '</tool_response>' }}
|
| 73 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_end|>\n' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if add_generation_prompt %}
|
| 79 |
+
{{- '<|im_start|>assistant\n<think>\n' }}
|
| 80 |
+
{%- endif %}
|