Llama-3-70B chat tuning
According to the model card, Shining Valiant 2 is a chat model built on Llama 3 70B and fine-tuned on publisher data for friendship, insight, knowledge, and enthusiasm.
Open Source Model Profile · ValiantLabs
Llama3-70B-ShiningValiant2
Llama3-70B-ShiningValiant2 is a 70.55B-parameter Llama-3 chat fine-tune from ValiantLabs. According to the model card, it builds on Meta-Llama-3-70B-Instruct with a science and technical focus.
- Publisher
- ValiantLabs
- Task
- text-generation
- Model type
- llama
- License
- llama3
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Llama3-70B-ShiningValiant2 is published by ValiantLabs as a Llama text-generation chat model. The captured configuration identifies LlamaForCausalLM with a llama model type, and Safetensors metadata reports 70,553,706,496 parameters. According to the model card, it is fine-tuned on meta-llama/Meta-Llama-3-70B-Instruct and released as the 2024-04-20 Shining Valiant 2 for Llama 3 70B.
Recorded capabilities
Documented base and focus
According to the model card, it was fine-tuned on meta-llama/Meta-Llama-3-70B-Instruct for general performance, with training focused on science, engineering, technical knowledge, and structured reasoning.
Dated release
According to the model card, this is the 2024-04-20 release of Shining Valiant 2 for Llama 3 70B.
Llama 3 Instruct format
According to the model card, the model uses the Llama 3 Instruct prompt format.
Legacy status
According to the model card, this model is legacy and the publisher recommends the Shining Valiant 2 release for Llama 3.1 70B.
Use cases in the source record
- General chat generation in the friendship, insight, and knowledge style the model card describes.
- Science, engineering, and technical-knowledge question answering matching the card's stated training focus.
- Prompting experiments that follow the documented Llama 3 Instruct prompt format.
Limitations and unknowns
- According to the model card, this is a legacy release with a recommended Llama 3.1 70B successor, so current support status needs confirmation.
- Capability and focus claims come from the publisher model card and were not independently verified.
- No evaluation results, context-window value, or hardware requirements were extracted from this record.
- No license text was captured beyond the Llama 3 identifier; full terms should be confirmed at the source.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: ValiantLabs/Llama3-70B-ShiningValiant2
Captured: Unknown. Processed: 2026-09-07T19:34:38.351471+00:00.
This model is legacy - we recommend Shining Valiant 2 for Llama 3.1 70b! Click here to support our open-source dataset and model releases! Shining Valiant 2 is a chat model built on Llama 3 70b, finetuned on our data for friendship, insight, knowledge and enthusiasm. Finetuned on meta-llama/Meta-Llama-3-70B-Instruct for best available general performance Trained on our data, focused on science, engineering, technical knowledge, and structured reasoning Version This is the 2024-04-20 release of Shining Valiant 2 for Llama 3 70b. We're working on more Llama 3 releases to come, including Shining Valiant and our Build Tools set of model…
F001F002F003F004F005F006F007F009F010F011F013F014F015