Downloads · 30 days
0
pinkelephantlimited/pinkelephant-llm-48b-s-verification
pinkelephant-llm-48b-s-verification is a text generation model from pinkelephantlimited. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
Industrial-standard, end-to-end verification of the FINAL aligned model. This repo is the single home for every tool, notebook, and recorded result used to verify the complete production model — not an intermediate st…
Downloads · 30 days
0
Access
Public
Updated Aug 23, 2026
Repo size
234 KB
Likes
0
Public
Click a slice to open those files.
.pdf234 KB · 50%
From the Hugging Face model README
Industrial-standard, end-to-end verification of the FINAL aligned model. This repo is the single home for every tool, notebook, and recorded result used to verify the complete production model — not an intermediate stage.
pink-elephant-llm-14b (dense 14B)
└─add weights / upcycle──▶ 48b-moe-base (8-expert MoE) ──train──▶ 48b
└─remaining epochs──▶ 48b-s (flagship, s = smarter)
└─+SFT best (step90000)──▶ +DPO best (dpo-best)──▶ FINAL MODEL ⇐ verified here
└─GGUF conversion──▶ run locally via Ollama / LM Studio
Pipeline stage index: base → moe → train → sft → dpo → verification (this) → release
After verification, the model is converted to GGUF for local use in Ollama / LM Studio.
Verification targets the whole final model (base 48B-S + SFT + DPO merged), which is the artifact users actually download and run. Keeping verification separate from the DPO training repo reflects that: the SFT/DPO repos are training stages; this repo is the acceptance gate for the finished model.
| Path | Purpose |
|---|---|
tooling/structural/verify_architecture.py | S1. Verifies the released model's config, parameter scale, and full base_model: lineage chain against the architectural contract. CPU-only, CI-runnable. |
tooling/structural/verify_weights.py | S2. Verifies SFT + DPO LoRA adapters are shape-consistent with the base (hidden/intermediate/expert dims) so they merge cleanly. CPU-only. |
tooling/adapter_to_peft.py | Converts the pipeline's custom .pt LoRA adapters (SFT sft-lora-step*.pt, DPO dpo-lora-step*.pt) into standard PEFT dirs that PeftModel.from_pretrained consumes. |
tooling/run_benchmarks.py | S3–S6. Loads base 48B-S + merges SFT best + DPO best, then runs GSM8K + MMLU. Shell-friendly alternative to the notebook. |
tooling/smoke_test.py | S4. Minimal generation sanity check of the final model. |
tooling/benchmarks/gsm8k.py | Raw GSM8K evaluation script (batch, checkpointed — used in the live run). |
tooling/benchmarks/mmlu_5shot.py | Raw 5-shot MMLU script (balanced stratified sampling — used in the live run). |
tooling/benchmarks/mmlu_chunk.py | Chunked MMLU runner (progress-safe for long runs). |
tooling/run_all.py | Orchestrates the CPU-side checks (structural + weights) in one command. |
notebooks/verify_full_model.py | Single notebook running all six stages (S1–S6) on one Blackwell host. |
results/ | Recorded verification outputs (JSON). |
report/ALIGNED_VERIFICATION_REPORT.pdf | This verification report (print-ready). |
requirements.txt | GPU-benchmark dependencies. |
pip install -r requirements.txt # torch optional for S1, needed for adapter inspection
python tooling/run_all.py --structural \
--sft /path/sft-lora-step90000.pt --dpo /path/dpo-best.pt \
--json results/
# On the verification host:
python tooling/adapter_to_peft.py sft-lora-step90000.pt peft/sft
python tooling/adapter_to_peft.py dpo-best.pt peft/dpo
python tooling/run_benchmarks.py # GSM8K + MMLU (S3–S6)
# or run notebooks/verify_full_model.py (single notebook, all of S1–S6)
Populated from live verification runs on our Blackwell host. See
results/JSON files.
| Benchmark | Result | Detail |
|---|---|---|
| GSM8K (math reasoning) | 68.5% | 61/89 on a random sample; answer is extraction |
| MMLU (knowledge, 5-shot) | 60.0% | 24/40 balanced across 7 subjects; letter extraction |
| Structural contract | PASS | 16/16 checks (config, params, lineage) |
| <img src="figures/verification_benchmarks.png" width="420"><br>Headline benchmarks: GSM8K 68.5% · MMLU 60.0% | <img src="figures/mmlu_subjects.png" width="420"><br>MMLU (5-shot) accuracy by subject | |
| <img src="figures/structural_checks.png" width="300"><br>Structural pre-release gate: 16/16 | <img src="figures/verification_stages.png" width="430"><br>Verification stages across the whole final model |
bf16.pinkelephantlimited/pinkelephant-llm-48b-s. Adapters:
pinkelephantlimited/pinkelephant-llm-48b-s-dpo (sft/sft-lora-step90000.pt,
dpo/dpo-best.pt).MIT — Pink Elephant Limited.