About 8.03B parameters
Safetensors metadata reports 8,030,261,248 parameters, or about 8.03B.
Open Source Model Profile · anakin87
yo-Llama-3-8B-Instruct
yo-Llama-3-8B-Instruct is an 8.03B-parameter Llama text-generation model from anakin87. The model card says it uses Llama-3-8B-Instruct weights steered toward a rap-style response, rather than a traditional fine-tune.
- Publisher
- anakin87
- Task
- text-generation
- Model type
- llama
- License
- llama3
- Library
- transformers
- Publication status
- Approved for indexing
Model overview
anakin87 publishes yo-Llama-3-8B-Instruct as a text-generation model. Captured config identifies LlamaForCausalLM with a llama model type, and Safetensors metadata reports 8,030,261,248 parameters. Card data records a llama3 license. According to the model card, the model is based on Llama-3-8B-Instruct weights, inspired by Llama-3-8B-Instruct-MopeyMule, and was produced by amplifying a rap direction in activation space.
Recorded capabilities
llama3 licensing
Captured metadata records a llama3 license.
Publisher rap-steering method
The model card says the model was not fine-tuned traditionally. Instead the publisher describes identifying and amplifying a rap direction in the activation space, using Alpaca examples and a rapper system prompt.
Serious-use disclaimer
The publisher states they do not recommend using this model for any serious task.
Use cases in the source record
- Transformers text-generation experiments following the card's pipeline example.
- Rap-style conversational generation as described by the publisher, noting the card's warning against serious-task use.
Limitations and unknowns
- No evaluation scores were extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Rap steering, Alpaca example counts, activation-space method, and the serious-use warning come from the publisher model card and have not been independently verified by Ethen.
Source and provenance
Source: anakin87/yo-Llama-3-8B-Instruct
Captured: Unknown. Processed: 2026-09-07T19:34:39.853351+00:00.
yo-Llama-3-8B-Instruct This model is based on Llama-3-8B-Instruct weights, but steered to respond with a rap style . Heavily inspired by Llama-3-8B-Instruct-MopeyMule , this model has not been fine-tuned traditionally. Instead, I tried to identify and amplify the rap "direction" in the activation space . Let's allow the model to introduce itself: 🎤 Who are you? I'm just a small part of the game/ a language model with a lot of fame I'm trained on data, day and night/ to spit out rhymes and make it right I'm a bot, a robot, a machine so fine/ I'm here to serve, but don't you get too divine I'll answer questions, and spit out some flo…
F001F002F003F004F005F006F007F010F011F012F016F017F018F020F021