Return to List
Weaver Alpha
Model ID:
online
Pricing
Input Token Cost 0.12 credits
Output Token Cost 0.2 credits
Cached Token Cost 0.12 credits
Model Details
Context Tokens 8000
Maximum Output 6000
Prompt Format Simplified Alpaca
Architecture LLaMA 2
Parameters 13B System
Source Link
Tags Creative, Verbose
Recent Metrics (Past 4 hours)
Avg Input Speed[1] 2618.2 tokens/sec
Avg Output Speed[1] 55.8 tokens/sec
Description

Experimental model meant for use in roleplay/narrative situations. An attempt to recreate Claude-style verbosity with a combination of much smaller models. Don't expect the same level of coherence or memory!
REQUIRES Alpaca prompt formatting.

This model does not support multi-swipe!
Recommended starting parameters: Temp:0.9 / RepPen:1.1 / TopP:0.58 / TopK:50

Prompt Formatting

If you use /v1/completions, formatting your prompts according to the model's instruct format can greatly improve results. If you use /v1/chat/completions, this is not relevant.

A properly formatted prompt would appear as follows, with non-formatting example content shown in (italicized parenthesis):

Showing "Simplified Alpaca" formatting.
### Instruction: (system message here) ### Instruction: (user message here) ### Response: (assistant message here)

[1] Aggregate performance metrics should only be used as an estimate.
Speeds can be affected by model traffic, sampler choice, prompt prefix re-use, and many other things.

Data fetched 2026-11-16 19:00:17 UTC. Click to refresh.

Mancer AI 2025 - Discord - Contact Us (JavaScript required!)
Terms of Use - Privacy Policy