Instructions to use TypeWhisper/Rumble-2-Flash-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use TypeWhisper/Rumble-2-Flash-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download TypeWhisper/Rumble-2-Flash-8bit --local-dir Rumble-2-Flash-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download chat_template.json from TypeWhisper/Rumble-2-Flash-8bit: direct link, hf CLI and curl.
- Browser
- Download file 3.05 kB
-
https://huggingface.co/TypeWhisper/Rumble-2-Flash-8bit/resolve/main/chat_template.json
- Command line
-
hf download hf://TypeWhisper/Rumble-2-Flash-8bit/chat_template.json
-
curl -L -o chat_template.json https://huggingface.co/TypeWhisper/Rumble-2-Flash-8bit/resolve/main/chat_template.json
3.05 kB
| { | |
| "chat_template": "{#- Resonant-Light chat template (Qwen3-ASR format + Reson8 control tokens).\n chat_template_kwargs (all optional):\n digits (bool, default true) -> <digits> numbers as digits | false -> <nodigits> numbers as words\n filler (bool, default false) -> <filler> keep um/uh fillers | false -> <nofiller> drop fillers\n verbatim (bool, default true) -> <verbatim> keep repeated words | false -> <noverbatim> collapse repeats\n language (string) -> forces the language, English name as in Qwen3-ASR (\"Dutch\", \"English\", ...)\n A system message, if given, follows the control tokens; if it already contains control tokens it is used as is. -#}\n{%- set use_digits = digits if digits is defined else true -%}\n{%- set use_filler = filler if filler is defined else false -%}\n{%- set use_verbatim = verbatim if verbatim is defined else true -%}\n{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n {%- if m.role == 'system' -%}\n {%- if m.content is string -%}\n {%- set ns.system_text = ns.system_text + m.content -%}\n {%- else -%}\n {%- for c in m.content -%}\n {%- if c.type == 'text' and (c.text is defined) -%}\n {%- set ns.system_text = ns.system_text + c.text -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n{%- set ctl = ('<digits>' if use_digits else '<nodigits>') + ('<filler>' if use_filler else '<nofiller>') + ('<verbatim>' if use_verbatim else '<noverbatim>') -%}\n{%- if '<digits>' in ns.system_text or '<nodigits>' in ns.system_text -%}\n {%- set system_text = ns.system_text -%}\n{%- else -%}\n {%- set system_text = ctl + ns.system_text -%}\n{%- endif -%}\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n {%- if m.content is not string -%}\n {%- for c in m.content -%}\n {%- if c.type == 'audio' or c.type == 'audio_url' or c.type == 'input_audio' or ('audio' in c) or ('audio_url' in c) -%}\n {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endfor -%}\n{{- '<|im_start|>system\\n' + system_text + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- for m in messages -%}{%- if m.role == 'assistant' -%}{%- set ns3 = namespace(assistant_text='') -%}{%- if m.content is string -%}{%- set ns3.assistant_text = m.content -%}{%- else -%}{%- for c in m.content -%}{%- if c.type == 'text' and (c.text is defined) -%}{%- set ns3.assistant_text = ns3.assistant_text + c.text -%}{%- endif -%}{%- endfor -%}{%- endif -%}{{- '<|im_start|>assistant\n' -}}{% generation %}{{- ns3.assistant_text + '<|im_end|>\n' -}}{% endgeneration %}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- if language is defined and language -%}\n{{- 'language ' + language + '<asr_text>' -}}\n{%- endif -%}\n{%- endif -%}" | |
| } | |