Views
No views yet
meta-llama/Meta-Llama-3-8B-Instruct, fit on the AURORA-Workflow-1 enriched SFT corpus on 2026-05-02. This is the H1 baseline for AURORA Stage-1 — the LoRA-tuned 8B-class transformer leg that the AURORA-M0 leg is compared against under the H1 decision rule.H1 (verbatim). On structured workflow-apprenticeship tasks, an event-first AURORA-M0 model will achieve task success within 5 percentage points of a LoRA-tuned 8B-class transformer baseline while using at least 40 % less measured energy per successful task.
| Path | Role |
|---|---|
adapter_config.json | PEFT adapter config |
adapter_model.safetensors | LoRA weights (rank 16, q_proj + v_proj) |
tokenizer.json, tokenizer_config.json, chat_template.jinja | Llama-3 tokeniser + chat template |
ggml-adapter-model.gguf | GGML conversion for llama.cpp inference |
carbontracker.json | Carbontracker capture metadata for the fit run |
trainer/checkpoint-688/ | Final HuggingFace Trainer checkpoint (optimizer state, RNG, args) for byte-exact reproduction |
scripts/fit-lora-llama.py against the same enriched corpus + the same seed reproduces every intermediate checkpoint locally.| Field | Value |
|---|---|
| Base model | meta-llama/Meta-Llama-3-8B-Instruct |
| Acceptable substitute | meta-llama/Llama-3.1-8B-Instruct (same architecture) |
| Target modules | q_proj, v_proj |
Rank r | 16 |
lora_alpha | 32 |
lora_dropout | 0.05 |
bias | none |
task_type | CAUSAL_LM |
| Max prompt at fit time | 512 tokens |
| Decode (inference) | greedy (temperature = 0.0, top_p = 1.0) per ADR-0022 |
1from peft import PeftModel
2from transformers import AutoModelForCausalLM, AutoTokenizer
3
4base = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
5tokenizer = AutoTokenizer.from_pretrained("Anthril/lora-llama8b-aurora-baseline-2026-05-02")
6model = PeftModel.from_pretrained(base, "Anthril/lora-llama8b-aurora-baseline-2026-05-02")llama.cpp)1./llama-cli \
2 -m Meta-Llama-3-8B-Instruct-Q4_K_M.gguf \
3 --lora ggml-adapter-model.gguf \
4 -p "<your prompt>"scripts/generate-enriched-corpus.py. Grammar source: Anthril/aurora-workflow-1.| Field | Value |
|---|---|
| Date | 2026-05-02 |
| Git HEAD at fit | 6df834a6ab669f24f9c1f4094dcf131614edaf3b |
| Fit script | scripts/fit-lora-llama.py |
| Spec anchor | ADR-0033 — LoRA-Llama baseline schema commitment |
| Carbontracker availability | false (not captured during this run; energy reporting is via the AURORA EnergyMeter SOP at evaluation time, not fit time) |
| Adapter SHA-256 (local manifest) | 038542cbc70f7ceff2444cc5c243417e1418a5512c9991322056a269fe89f5f0 |
| GGUF SHA-256 | 67667d43b14883b26cb4bdf53036976e539b45ad96a051fc285bac8e914d77e7 |
llama.cpp commit at conversion | fc2b0053ffe878ff5a26934bdb555681f15bc699 |
aurora/evaluation_centers/runners/lora_llama_runner.py during H1 evaluation. Per ADR-0035, the comparator requires notes["energy_source"] >= 1.0 on every per-episode result — i.e. measured energy from a recognised on-die collector. Hosts without one will see the comparator emit INCONCLUSIVE_SYNTHETIC_ENERGY.