Instructions to use RMDWLLC/kaiju-coder-7-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use RMDWLLC/kaiju-coder-7-adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/workspace/kaiju-coder/models/Qwen3.6-27B") model = PeftModel.from_pretrained(base_model, "RMDWLLC/kaiju-coder-7-adapter") - Notebooks
- Google Colab
- Kaggle
Kaiju Coder 7 Final Release Report
Generated: 2026-06-04T02:44:04Z
Product name: Kaiju Coder 7
Public model id: kaiju-coder-7
Current source branch: codex/kaiju-business-owner-rc
Current HEAD: 3d57eae92ad523519473f0ff3eca6661a9736de3
Current origin/main: 3d57eae92ad523519473f0ff3eca6661a9736de3
Current Verdict
Kaiju Coder 7 is a public Hugging Face release candidate, not a fully public
commercial API launch yet. The local model path, OpenCode profile, harnessed
business-owner evals, staged helper repos, runtime-quantized recipe, and paid
API scaffold are in place. The adapter, OpenCode helper, runtime helper, and
merged 53.8GB model are uploaded under RMDWLLC with public visibility. The
paid API has human approval, a custom API domain, live Cloudflare bindings,
Worker-to-Gojira proof, rollback proof, latency evidence, and Stripe test-mode
Checkout/webhook evidence. Real customer charging still requires a deliberate
Stripe live-mode switch and controlled live payment verification.
Runtime
| Field | Value |
|---|---|
| Status | pass |
| Base URL | http://127.0.0.1:18181/v1 |
| Model id | kaiju-coder-7 |
| Max model length | 16384 |
| Detail | `` |
Recommended default today: 16k context through kaiju-coder-7. Higher
context has benchmark evidence, but the currently parked default is 16k for
stability and speed.
Readiness Summary
| Area | Result |
|---|---|
| Local public-testing readiness | ready=True pass=24 fail=0 manual=0 rc=0 |
| Hugging Face release readiness | ready=True pass=24 fail=0 manual=0 rc=0 |
| Public launch readiness | ready=True pass=24 fail=0 manual=0 rc=0 |
| Hugging Face staging integrity | ready=True pass=6 fail=0 manual=0 rc=0 |
| Paid API launch readiness | ready=True pass=27 fail=0 manual=0 rc=0 |
Hugging Face Upload Evidence
| Field | Value |
|---|---|
| Evidence file | release/HF_UPLOAD_EVIDENCE.md |
| Small helper repos uploaded | True |
| Merged model uploaded | False |
| Merged repo | RMDWLLC/kaiju-coder-7 |
| Merged repo SHA | not recorded |
| Merged upload size | 39 files / 53.8G / 14 safetensors shards recorded |
| Download status | public downloads verified; no active private-storage blocker recorded |
| Visibility decision | PUBLIC; HF_VISIBILITY_DECISION: PUBLIC recorded in human review |
Hugging Face Release Blockers
- No matching checks.
Public Launch Blockers
- No matching checks.
Paid API Launch Blockers
- No matching checks.
Evidence Paths
| Evidence | Path |
|---|---|
| Completion audit | release/COMPLETION_AUDIT.md |
| Goal completion audit | release/GOAL_COMPLETION_AUDIT.md |
| Release evidence refresh runner | scripts/refresh_kaiju_release_evidence.py |
| Eval scoreboard | release/EVAL_SCOREBOARD.md |
| Public testing quickstart | release/PUBLIC_TESTING_QUICKSTART.md |
| Serving benchmarks | release/SERVING_BENCHMARKS.md |
| Hugging Face release draft | release/HUGGINGFACE_RELEASE_DRAFT.md |
| Hugging Face upload evidence | release/HF_UPLOAD_EVIDENCE.md |
| Hugging Face release bundle | release/bundles/LATEST.md |
| Hugging Face bundle integrity checker | scripts/check_hf_release_bundle_integrity.py |
| Hugging Face permission evidence template | release/hf-release-permission-evidence.example.json |
| Hugging Face permission evidence collector | scripts/collect_hf_release_permission_evidence.py |
| Hugging Face permission evidence checker | scripts/check_hf_release_permission_evidence.py |
| Merged-model metadata prep | scripts/prepare_hf_merged_model_metadata.sh |
| Human release review gate | release/HUMAN_RELEASE_REVIEW.md |
| Paid API readiness | release/PAID_API_READINESS.md |
| Paid API evidence collector | scripts/collect_paid_api_launch_evidence.py |
| Paid API launch evidence template | release/paid-api-launch-evidence.example.json |
| Cloudflare bindings template | release/cloudflare-bindings.example.json |
| Cloudflare bindings applier | scripts/apply_paid_api_cloudflare_bindings.py |
| Latest direct API smoke | runs/benchmarks/20260603T223337Z-kaiju-coder-7-serving/summary.md |
| Latest OpenCode customer pack | runs/opencode-customer-readiness/20260603T185835Z/summary.md |
| Latest public OpenCode smoke | runs/public-opencode-smoke |
What Richard Should Test First
python3 scripts/check_kaiju_public_release_readiness.py --mode local
python3 scripts/install_kaiju_opencode_profile.py
mkdir -p /tmp/kaiju-public-smoke
opencode run --dir /tmp/kaiju-public-smoke --dangerously-skip-permissions 'Create hello.txt with exactly: Kaiju Coder 7 public smoke ok'
python3 scripts/run_kaiju_public_opencode_smoke.py
python3 scripts/run_kaiju_opencode_customer_pack.py --mode harnessed
bash scripts/prepare_hf_merged_model_metadata.sh
bash scripts/prepare_hf_release_staging.sh
python3 scripts/check_hf_staging_integrity.py --require-checksums
python3 scripts/create_hf_release_bundle.py
python3 scripts/check_hf_release_bundle_integrity.py
python3 scripts/check_kaiju_goal_completion.py --write
python3 scripts/refresh_kaiju_release_evidence.py --skip-opencode-smoke
python3 scripts/collect_hf_release_permission_evidence.py
python3 scripts/collect_hf_release_permission_evidence.py --apply --write
python3 scripts/check_hf_release_permission_evidence.py
python3 scripts/check_hf_uploaded_release.py --namespace RMDWLLC --apply --require-public
python3 scripts/check_kaiju_public_release_readiness.py --mode hf-release
python3 scripts/check_kaiju_public_release_readiness.py --mode public
cp release/cloudflare-bindings.example.json release/cloudflare-bindings.json
# Replace placeholder D1/KV IDs in release/cloudflare-bindings.json first.
python3 scripts/apply_paid_api_cloudflare_bindings.py --bindings-file release/cloudflare-bindings.json
cp release/paid-api-launch-evidence.example.json release/paid-api-launch-evidence.json
python3 scripts/collect_paid_api_launch_evidence.py --help
python3 scripts/check_paid_api_readiness.py --mode launch --evidence-file release/paid-api-launch-evidence.json
Do not expose the paid hosted API until python3 scripts/check_paid_api_readiness.py --mode launch has no failures and the
human release review explicitly approves public paid API launch.
Changed Files
git status --short currently reports 128 changed paths.
| State | Path |
|---|---|
| M | .gitignore |
| M | LICENSE_NOTES.md |
| M | README.md |
| M | datasets/schema.json |
| M | docs/custom-harness.md |
| M | evals/BAKEOFF_CURRENT.md |
| M | evals/run_openai_compat_smoke.py |
| M | evals/run_router_static_checks.py |
| M | evals/tasks/router-hard-harness.jsonl |
| M | gateway/README.md |
| M | gateway/cloudflare-worker/README.md |
| M | gateway/cloudflare-worker/migrations/0001_paid_api.sql |
| M | gateway/cloudflare-worker/package.json |
| M | gateway/cloudflare-worker/src/index.js |
| M | gateway/cloudflare-worker/test/index.test.js |
| M | gateway/cloudflare-worker/wrangler.jsonc |
| M | gateway/gojira-local/server.py |
| M | kaiju_harness/router.py |
| M | kaiju_harness/verification.py |
| M | kaiju_harness/website.py |
| D | models/README.md |
| D | models/qwen3.6-27b-base.md |
| D | models/qwen3.6-27b-fp8.md |
| M | prompts/kaiju-coder-api-system.md |
| M | prompts/kaiju-coder-speed-system.md |
| M | release/DATA_PROVENANCE_DRAFT.md |
| M | release/MODEL_CARD_DRAFT.md |
| M | scripts/build_sft_dataset.py |
| M | scripts/check-gojira-b-capacity.sh |
| M | scripts/check_kaiju_gateway_policy.py |
| M | scripts/run-gojira-b-qwen36-lora-eval.sh |
| M | scripts/run-gojira-b-qwen36-lora-sglang-eval.sh |
| M | scripts/run-gojira-b-qwen36-lora-train.sh |
| M | scripts/run_kaiju_api_harness_smoke.py |
| M | scripts/run_kaiju_router.py |
| M | scripts/start-qwen36-lora-sglang.sh |
| M | scripts/stop-qwen36-lora-sglang.sh |
| M | scripts/validate_training_data.py |
| M | scripts/watch-gojira-b-qwen36-lora-train.sh |
| M | tests/test_website_harness.py |
| ?? | .opencode/ |
| ?? | datasets/candidates/v1.7-rmdw-business-owner-suite.jsonl |
| ?? | datasets/v1.7-targets.json |
| ?? | evals/tasks/business-owner-v18-comparison.jsonl |
| ?? | evals/tasks/business-owner-v18-smoke.jsonl |
| ?? | evals/tasks/opencode-customer-readiness.jsonl |
| ?? | kaiju_harness/business_suite.py |
| ?? | release/COMPLETION_AUDIT.md |
| ?? | release/EVAL_SCOREBOARD.md |
| ?? | release/FINAL_RELEASE_REPORT.md |
| ?? | release/GOAL_COMPLETION_AUDIT.md |
| ?? | release/HF_ADAPTER_MODEL_CARD.md |
| ?? | release/HF_UPLOAD_EVIDENCE.md |
| ?? | release/HUGGINGFACE_RELEASE_DRAFT.md |
| ?? | release/HUMAN_RELEASE_REVIEW.md |
| ?? | release/LOCAL_TEST_INSTRUCTIONS.md |
| ?? | release/PAID_API_READINESS.md |
| ?? | release/PUBLIC_TESTING_QUICKSTART.md |
| ?? | release/QUANTIZATION_PLAN.md |
| ?? | release/SERVING_BENCHMARKS.md |
| ?? | release/SOURCE_INVENTORY.md |
| ?? | release/UPSTREAM_LICENSE_CHECK.md |
| ?? | release/assets/ |
| ?? | release/bundles/ |
| ?? | release/cloudflare-bindings.example.json |
| ?? | release/gguf/ |
| ?? | release/hf-release-permission-evidence.example.json |
| ?? | release/hf-release-permission-evidence.json |
| ?? | release/huggingface/ |
| ?? | release/opencode/ |
| ?? | release/paid-api-launch-evidence.example.json |
| ?? | release/paid-api-launch-evidence.json |
| ?? | release/quantized-runtime/ |
| ?? | release/source-inventory.json |
| ?? | release/upstream/ |
| ?? | scripts/apply_paid_api_cloudflare_bindings.py |
| ?? | scripts/benchmark_kaiju_serving.py |
| ?? | scripts/build_source_inventory.py |
| ?? | scripts/build_v17_business_owner_sft_dataset.py |
| ?? | scripts/check_hf_release_bundle_integrity.py |
| ?? | scripts/check_hf_release_permission_evidence.py |
| ?? | scripts/check_hf_release_permissions.sh |
| ?? | scripts/check_hf_staging_integrity.py |
| ?? | scripts/check_hf_uploaded_release.py |
| ?? | scripts/check_human_release_review.py |
| ?? | scripts/check_kaiju_goal_completion.py |
| ?? | scripts/check_kaiju_public_release_readiness.py |
| ?? | scripts/check_kaiju_quantization_prereqs.py |
| ?? | scripts/check_paid_api_readiness.py |
| ?? | scripts/collect_hf_release_permission_evidence.py |
| ?? | scripts/collect_paid_api_launch_evidence.py |
| ?? | scripts/create_hf_release_bundle.py |
| ?? | scripts/generate_kaiju_final_report.py |
| ?? | scripts/gojira-b-ssh-lib.sh |
| ?? | scripts/install_kaiju_opencode_profile.py |
| ?? | scripts/kaiju_opencode_fast_proxy.py |
| ?? | scripts/make_hf_release_public.sh |
| ?? | scripts/opencode-kaiju-no-autocontinue.mjs |
| ?? | scripts/prepare_hf_merged_model_metadata.sh |
| ?? | scripts/prepare_hf_release_staging.sh |
| ?? | scripts/prepare_paid_api_cloudflare_resources.sh |
| ?? | scripts/probe-gojira-b-kaiju-quantization.sh |
| ?? | scripts/probe-gojira-b-persisted-quantization.sh |
| ?? | scripts/refresh_kaiju_release_evidence.py |
| ?? | scripts/run-gojira-b-kaiju-gguf-convert.sh |
| ?? | scripts/run-gojira-b-qwen36-lora-merge.sh |
| ?? | scripts/run-gojira-b-vllm-serving-benchmark.sh |
| ?? | scripts/run_kaiju_business_owner_rc_smoke.py |
| ?? | scripts/run_kaiju_opencode_customer_pack.py |
| ?? | scripts/run_kaiju_public_demo_pack.py |
| ?? | scripts/run_kaiju_public_opencode_smoke.py |
| ?? | scripts/run_kaiju_quantized_opencode_smoke.sh |
| ?? | scripts/start-qwen36-merged-sglang.sh |
| ?? | scripts/start-qwen36-merged-vllm.sh |
| ?? | scripts/stop-qwen36-merged-sglang.sh |
| ?? | scripts/stop-qwen36-merged-vllm.sh |
| ?? | scripts/upload_hf_merged_model_from_gojira_b.sh |
| ?? | scripts/upload_hf_release_staging.sh |
| ?? | tests/test_kaiju_opencode_fast_proxy.py |
| ?? | tests/test_kiyomi_business_suite.py |
| ?? | tests/test_release_package.py |
| ?? | tests/test_source_inventory.py |
| ?? | tests/test_training_provenance.py |
| ?? | tests/test_v17_business_dataset.py |
| ?? | training/configs/qwen36-27b-lora-v1.7.example.json |
| ?? | training/configs/qwen36-27b-lora-v1.8-business-owner.example.json |
| ?? | training/scripts/qwen36_lora_merge.py |
| ?? | training/v1.7-business-owner-runbook.md |
Commands Run During Report Generation
| Label | Command | Return code |
|---|---|---|
| git branch | git branch --show-current |
0 |
| git HEAD | git rev-parse HEAD |
0 |
| git origin/main | git rev-parse origin/main |
0 |
| git status | git status --short |
0 |
| local readiness | /opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_kaiju_public_release_readiness.py --mode local --json --base-url http://127.0.0.1:18181/v1 --live-timeout 5 --staging-dir /tmp/kaiju-coder-7-hf-staging |
0 |
| HF release readiness | /opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_kaiju_public_release_readiness.py --mode hf-release --json --base-url http://127.0.0.1:18181/v1 --live-timeout 5 --staging-dir /tmp/kaiju-coder-7-hf-staging |
0 |
| public readiness | /opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_kaiju_public_release_readiness.py --mode public --json --base-url http://127.0.0.1:18181/v1 --live-timeout 5 --staging-dir /tmp/kaiju-coder-7-hf-staging |
0 |
| HF staging integrity | /opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_hf_staging_integrity.py --staging-dir /tmp/kaiju-coder-7-hf-staging --require-checksums --json |
0 |
| paid API launch readiness | /opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_paid_api_readiness.py --mode launch --json |
0 |
Report Safety
This generator intentionally avoids secret-bearing commands such as auth token lists, environment dumps, process command-line scans, Wrangler secret lists, and payment-provider credential output.