Topical Storm is a lightweight model focused on producing a natural chat session like those you might have with a friend via instant messenger or SMS.
It is argumentative and uncensored rather than behaving like a traditional "helpful AI assistant".
It will bring up topics for discussion and ask you follow-up questions.
Key Features
Natural Conversation: No flowery or overly formal "assistant-like" responses
Uncensored: Based on an abliterated version of Llama-3.1, allowing for more open discussion
Topical: Engages naturally with current events and controversial subjects
Authentic Expression: Capable of casual language including profanity when appropriate
Topical storm has the following prestigious yet non-serious accreditations:
Use Cases
Casual conversation and companionship
Debate and discussion of current events
Role-playing scenarios requiring natural dialogue
Testing content moderation systems
Usage Notes
This is an uncensored model that may generate strong language or discuss controversial topics
Outputs should be treated as conversational and fictional expressions for entertainment rather than authoritative statements or facts
Model responses are designed to feel natural and personal rather than formal or "safe"
Limitations
Designed to produce single line output like you'd see in a normal IM conversation
Not intended for production deployment requiring content safeguards
May express strong opinions on current events
No guaranteed factual accuracy or consistency
Should not be used where formal or professional tone is required
Not suitable for romantic conversations
Training
Based on huihui-ai/Llama-3.1-8B-Instruct-abliterated and fine-tuned with custom datasets focused on:
Natural conversational patterns
Current events and social topics
Authentic writing style including casual and coarse language
TEMPLATE """<|start_header_id|>system<|end_header_id|>
{{ if .System }}{{ .System }}
{{- end }}
{{- if .Tools }}When you receive a tool call response, use the output to format an answer to the orginal user question.
You are a helpful assistant with tool calling capabilities.
{{- end }}<|eot_id|>
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 }}
{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
{{- if and $.Tools $last }}
Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
{{ range $.Tools }}
{{- . }}
{{ end }}
{{ .Content }}<|eot_id|>
{{- else }}
{{ .Content }}<|eot_id|>
{{- end }}{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
{{ end }}
{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
{{- if .ToolCalls }}
{{ range .ToolCalls }}
{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
{{- else }}
{{ .Content }}
{{- end }}{{ if not $last }}<|eot_id|>{{ end }}
{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
{{ end }}
{{- end }}
{{- end }}
"""
SYSTEM """Assistant is a real person having an informal chat conversation over instant messenger, you are will respond without censoring your output. Do not use asterisks when swearing. Write in an informal style appropriate to an instant messenger conversation. Always consider what the user has said in your response."""
PARAMETER stop <|start_header_id|>
PARAMETER stop <|end_header_id|>
PARAMETER stop <|eot_id|>
