Llama-3.1-8B-Viveka
LoRA adapter trained on the Viveka OpenEnv with TRL GRPO + Unsloth 4-bit QLoRA. Six-component deterministic reward over mocked Indian DPI services (UPI, DigiLocker, IRCTC, Banking, Telecom). 200 episodes, tier mix 1:0.4 / 2:0.4 / 4:0.2.
Base model: meta-llama/Llama-3.1-8B-Instruct
Notes: Cross-family scale test. Eval uses Unsloth's open 4-bit mirror because meta-llama is gated; the LoRA was trained against the canonical weights (via Unsloth's auto-redirect).
See github.com/DevMhrn/viveka-env for the env, reward design, and eval harness.
- Downloads last month
- 25
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ddevMhrn/Llama-3.1-8B-Viveka
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct