Text Generation
Transformers
Safetensors
English
qwen3_5
image-text-to-text
kaiju-coder-7
coding
local-ai
business
opencode
tool-use
conversational
Instructions to use RMDWLLC/kaiju-coder-7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RMDWLLC/kaiju-coder-7 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RMDWLLC/kaiju-coder-7") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("RMDWLLC/kaiju-coder-7") model = AutoModelForMultimodalLM.from_pretrained("RMDWLLC/kaiju-coder-7") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use RMDWLLC/kaiju-coder-7 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RMDWLLC/kaiju-coder-7" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RMDWLLC/kaiju-coder-7", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RMDWLLC/kaiju-coder-7
- SGLang
How to use RMDWLLC/kaiju-coder-7 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "RMDWLLC/kaiju-coder-7" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RMDWLLC/kaiju-coder-7", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "RMDWLLC/kaiju-coder-7" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RMDWLLC/kaiju-coder-7", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use RMDWLLC/kaiju-coder-7 with Docker Model Runner:
docker model run hf.co/RMDWLLC/kaiju-coder-7
Refresh Kaiju Coder 7 public release metadata
Browse files- FINAL_RELEASE_REPORT.md +27 -9
- GOAL_COMPLETION_AUDIT.md +5 -3
FINAL_RELEASE_REPORT.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
# Kaiju Coder 7 Final Release Report
|
| 2 |
|
| 3 |
-
Generated: `2026-06-03T20:
|
| 4 |
|
| 5 |
Product name: `Kaiju Coder 7`
|
| 6 |
Public model id: `kaiju-coder-7`
|
|
@@ -10,12 +10,14 @@ Current `origin/main`: `3d57eae92ad523519473f0ff3eca6661a9736de3`
|
|
| 10 |
|
| 11 |
## Current Verdict
|
| 12 |
|
| 13 |
-
Kaiju Coder 7 is a
|
| 14 |
-
commercial launch yet. The local model path, OpenCode profile, harnessed
|
| 15 |
-
business-owner evals,
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Runtime
|
| 21 |
|
|
@@ -41,6 +43,19 @@ stability and speed.
|
|
| 41 |
| Hugging Face staging integrity | `ready=True pass=6 fail=0 manual=0 rc=0` |
|
| 42 |
| Paid API launch readiness | `ready=False pass=17 fail=3 manual=7 rc=1` |
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
## Hugging Face Release Blockers
|
| 45 |
|
| 46 |
| Status | Check | Detail |
|
|
@@ -79,6 +94,7 @@ stability and speed.
|
|
| 79 |
| Public testing quickstart | `release/PUBLIC_TESTING_QUICKSTART.md` |
|
| 80 |
| Serving benchmarks | `release/SERVING_BENCHMARKS.md` |
|
| 81 |
| Hugging Face release draft | `release/HUGGINGFACE_RELEASE_DRAFT.md` |
|
|
|
|
| 82 |
| Hugging Face release bundle | `release/bundles/LATEST.md` |
|
| 83 |
| Hugging Face bundle integrity checker | `scripts/check_hf_release_bundle_integrity.py` |
|
| 84 |
| Hugging Face permission evidence template | `release/hf-release-permission-evidence.example.json` |
|
|
@@ -112,9 +128,9 @@ python3 scripts/check_hf_release_bundle_integrity.py
|
|
| 112 |
python3 scripts/check_kaiju_goal_completion.py --write
|
| 113 |
python3 scripts/refresh_kaiju_release_evidence.py --skip-opencode-smoke
|
| 114 |
python3 scripts/collect_hf_release_permission_evidence.py
|
| 115 |
-
# After HF repo-create permission is fixed:
|
| 116 |
python3 scripts/collect_hf_release_permission_evidence.py --apply --write
|
| 117 |
python3 scripts/check_hf_release_permission_evidence.py
|
|
|
|
| 118 |
python3 scripts/check_kaiju_public_release_readiness.py --mode hf-release
|
| 119 |
python3 scripts/check_kaiju_public_release_readiness.py --mode public
|
| 120 |
cp release/cloudflare-bindings.example.json release/cloudflare-bindings.json
|
|
@@ -131,7 +147,7 @@ human release review explicitly approves public paid API launch.
|
|
| 131 |
|
| 132 |
## Changed Files
|
| 133 |
|
| 134 |
-
`git status --short` currently reports `
|
| 135 |
|
| 136 |
| State | Path |
|
| 137 |
|---|---|
|
|
@@ -181,6 +197,7 @@ human release review explicitly approves public paid API launch.
|
|
| 181 |
| ?? | `release/FINAL_RELEASE_REPORT.md` |
|
| 182 |
| ?? | `release/GOAL_COMPLETION_AUDIT.md` |
|
| 183 |
| ?? | `release/HF_ADAPTER_MODEL_CARD.md` |
|
|
|
|
| 184 |
| ?? | `release/HUGGINGFACE_RELEASE_DRAFT.md` |
|
| 185 |
| ?? | `release/HUMAN_RELEASE_REVIEW.md` |
|
| 186 |
| ?? | `release/LOCAL_TEST_INSTRUCTIONS.md` |
|
|
@@ -220,6 +237,7 @@ human release review explicitly approves public paid API launch.
|
|
| 220 |
| ?? | `scripts/generate_kaiju_final_report.py` |
|
| 221 |
| ?? | `scripts/gojira-b-ssh-lib.sh` |
|
| 222 |
| ?? | `scripts/install_kaiju_opencode_profile.py` |
|
|
|
|
| 223 |
| ?? | `scripts/opencode-kaiju-no-autocontinue.mjs` |
|
| 224 |
| ?? | `scripts/prepare_hf_merged_model_metadata.sh` |
|
| 225 |
| ?? | `scripts/prepare_hf_release_staging.sh` |
|
|
|
|
| 1 |
# Kaiju Coder 7 Final Release Report
|
| 2 |
|
| 3 |
+
Generated: `2026-06-03T20:30:51Z`
|
| 4 |
|
| 5 |
Product name: `Kaiju Coder 7`
|
| 6 |
Public model id: `kaiju-coder-7`
|
|
|
|
| 10 |
|
| 11 |
## Current Verdict
|
| 12 |
|
| 13 |
+
Kaiju Coder 7 is a public Hugging Face release candidate, not a fully public
|
| 14 |
+
commercial API launch yet. The local model path, OpenCode profile, harnessed
|
| 15 |
+
business-owner evals, staged helper repos, runtime-quantized recipe, and paid
|
| 16 |
+
API scaffold are in place. The adapter, OpenCode helper, runtime helper, and
|
| 17 |
+
merged 53.8GB model are uploaded under `RMDWLLC` with public visibility. The
|
| 18 |
+
paid API has human approval, but operational launch still requires live
|
| 19 |
+
Cloudflare bindings, secrets, Stripe staging evidence, Worker-to-Gojira proof,
|
| 20 |
+
rollback proof, and latency evidence.
|
| 21 |
|
| 22 |
## Runtime
|
| 23 |
|
|
|
|
| 43 |
| Hugging Face staging integrity | `ready=True pass=6 fail=0 manual=0 rc=0` |
|
| 44 |
| Paid API launch readiness | `ready=False pass=17 fail=3 manual=7 rc=1` |
|
| 45 |
|
| 46 |
+
## Hugging Face Upload Evidence
|
| 47 |
+
|
| 48 |
+
| Field | Value |
|
| 49 |
+
|---|---|
|
| 50 |
+
| Evidence file | `release/HF_UPLOAD_EVIDENCE.md` |
|
| 51 |
+
| Small helper repos uploaded | `True` |
|
| 52 |
+
| Merged model uploaded | `True` |
|
| 53 |
+
| Merged repo | `RMDWLLC/kaiju-coder-7` |
|
| 54 |
+
| Merged repo SHA | `9afd28d8d5372cbc421ea1765bb87318cbb7abc6` |
|
| 55 |
+
| Merged upload size | `39 files / 53.8G / 14 safetensors shards recorded` |
|
| 56 |
+
| Download status | `public downloads verified; no active private-storage blocker recorded` |
|
| 57 |
+
| Visibility decision | `PUBLIC`; `HF_VISIBILITY_DECISION: PUBLIC` recorded in human review |
|
| 58 |
+
|
| 59 |
## Hugging Face Release Blockers
|
| 60 |
|
| 61 |
| Status | Check | Detail |
|
|
|
|
| 94 |
| Public testing quickstart | `release/PUBLIC_TESTING_QUICKSTART.md` |
|
| 95 |
| Serving benchmarks | `release/SERVING_BENCHMARKS.md` |
|
| 96 |
| Hugging Face release draft | `release/HUGGINGFACE_RELEASE_DRAFT.md` |
|
| 97 |
+
| Hugging Face upload evidence | `release/HF_UPLOAD_EVIDENCE.md` |
|
| 98 |
| Hugging Face release bundle | `release/bundles/LATEST.md` |
|
| 99 |
| Hugging Face bundle integrity checker | `scripts/check_hf_release_bundle_integrity.py` |
|
| 100 |
| Hugging Face permission evidence template | `release/hf-release-permission-evidence.example.json` |
|
|
|
|
| 128 |
python3 scripts/check_kaiju_goal_completion.py --write
|
| 129 |
python3 scripts/refresh_kaiju_release_evidence.py --skip-opencode-smoke
|
| 130 |
python3 scripts/collect_hf_release_permission_evidence.py
|
|
|
|
| 131 |
python3 scripts/collect_hf_release_permission_evidence.py --apply --write
|
| 132 |
python3 scripts/check_hf_release_permission_evidence.py
|
| 133 |
+
python3 scripts/check_hf_uploaded_release.py --namespace RMDWLLC --apply --require-public
|
| 134 |
python3 scripts/check_kaiju_public_release_readiness.py --mode hf-release
|
| 135 |
python3 scripts/check_kaiju_public_release_readiness.py --mode public
|
| 136 |
cp release/cloudflare-bindings.example.json release/cloudflare-bindings.json
|
|
|
|
| 147 |
|
| 148 |
## Changed Files
|
| 149 |
|
| 150 |
+
`git status --short` currently reports `114` changed paths.
|
| 151 |
|
| 152 |
| State | Path |
|
| 153 |
|---|---|
|
|
|
|
| 197 |
| ?? | `release/FINAL_RELEASE_REPORT.md` |
|
| 198 |
| ?? | `release/GOAL_COMPLETION_AUDIT.md` |
|
| 199 |
| ?? | `release/HF_ADAPTER_MODEL_CARD.md` |
|
| 200 |
+
| ?? | `release/HF_UPLOAD_EVIDENCE.md` |
|
| 201 |
| ?? | `release/HUGGINGFACE_RELEASE_DRAFT.md` |
|
| 202 |
| ?? | `release/HUMAN_RELEASE_REVIEW.md` |
|
| 203 |
| ?? | `release/LOCAL_TEST_INSTRUCTIONS.md` |
|
|
|
|
| 237 |
| ?? | `scripts/generate_kaiju_final_report.py` |
|
| 238 |
| ?? | `scripts/gojira-b-ssh-lib.sh` |
|
| 239 |
| ?? | `scripts/install_kaiju_opencode_profile.py` |
|
| 240 |
+
| ?? | `scripts/make_hf_release_public.sh` |
|
| 241 |
| ?? | `scripts/opencode-kaiju-no-autocontinue.mjs` |
|
| 242 |
| ?? | `scripts/prepare_hf_merged_model_metadata.sh` |
|
| 243 |
| ?? | `scripts/prepare_hf_release_staging.sh` |
|
GOAL_COMPLETION_AUDIT.md
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
# Kaiju Coder 7 Goal Completion Audit
|
| 2 |
|
| 3 |
-
Generated: `2026-06-03T20:
|
| 4 |
|
| 5 |
Overall: `not complete`
|
| 6 |
-
Summary: `
|
| 7 |
|
| 8 |
This audit maps the active Kaiju Coder 7 objective to current evidence. It is stricter than local readiness: local public testing can pass while Hugging Face upload, human review, and paid API launch remain blocked.
|
| 9 |
|
|
@@ -34,7 +34,8 @@ This audit maps the active Kaiju Coder 7 objective to current evidence. It is st
|
|
| 34 |
| Runtime | At least one public-friendly quantized/local candidate is working or clearly documented as blocked with evidence. | `passed` | release/quantized-runtime/README.md documents vLLM bitsandbytes runtime candidate and persisted-weights limitation | |
|
| 35 |
| Hugging Face | Public-friendly HF release structure is staged with adapter, OpenCode helper, runtime-quantized helper, model cards, provenance, evals, and docs. | `passed` | python3 scripts/check_hf_staging_integrity.py --require-checksums | |
|
| 36 |
| Hugging Face | At least one public Hugging Face release path is ready to upload or uploaded. | `passed` | python3 scripts/check_kaiju_public_release_readiness.py --mode hf-release | |
|
| 37 |
-
| Hugging Face | Merged 51GB model repo upload is guarded and ready after human review/namespace permission. | `passed` | scripts/prepare_hf_merged_model_metadata.sh; scripts/upload_hf_merged_model_from_gojira_b.sh
|
|
|
|
| 38 |
| Quality | Customer-style evals cover website, proposal, Stripe/payment, CRM/reporting, CSV/parser, Kiyomi operating pack, and safety/provenance. | `passed` | evals/tasks/opencode-customer-readiness.jsonl; runs/opencode-customer-readiness/20260603T185835Z/summary.md | |
|
| 39 |
| Quality | Model/harness prompts produce file-oriented business-owner artifacts rather than vague advice. | `passed` | kaiju_harness/business_suite.py; release/EVAL_SCOREBOARD.md | |
|
| 40 |
| Provenance | Training/eval provenance is preserved and public docs avoid internal checkpoint naming except license/provenance attribution. | `passed` | release/SOURCE_INVENTORY.md; release/DATA_PROVENANCE_DRAFT.md; release/PUBLIC_TESTING_QUICKSTART.md | |
|
|
@@ -56,5 +57,6 @@ python3 scripts/check_paid_api_readiness.py --mode scaffold
|
|
| 56 |
python3 scripts/check_paid_api_readiness.py --mode launch
|
| 57 |
python3 scripts/check_hf_staging_integrity.py --require-checksums
|
| 58 |
python3 scripts/check_hf_release_permission_evidence.py
|
|
|
|
| 59 |
python3 scripts/check_human_release_review.py --mode public
|
| 60 |
```
|
|
|
|
| 1 |
# Kaiju Coder 7 Goal Completion Audit
|
| 2 |
|
| 3 |
+
Generated: `2026-06-03T20:30:58Z`
|
| 4 |
|
| 5 |
Overall: `not complete`
|
| 6 |
+
Summary: `17 passed / 1 blocked / 0 manual`
|
| 7 |
|
| 8 |
This audit maps the active Kaiju Coder 7 objective to current evidence. It is stricter than local readiness: local public testing can pass while Hugging Face upload, human review, and paid API launch remain blocked.
|
| 9 |
|
|
|
|
| 34 |
| Runtime | At least one public-friendly quantized/local candidate is working or clearly documented as blocked with evidence. | `passed` | release/quantized-runtime/README.md documents vLLM bitsandbytes runtime candidate and persisted-weights limitation | |
|
| 35 |
| Hugging Face | Public-friendly HF release structure is staged with adapter, OpenCode helper, runtime-quantized helper, model cards, provenance, evals, and docs. | `passed` | python3 scripts/check_hf_staging_integrity.py --require-checksums | |
|
| 36 |
| Hugging Face | At least one public Hugging Face release path is ready to upload or uploaded. | `passed` | python3 scripts/check_kaiju_public_release_readiness.py --mode hf-release | |
|
| 37 |
+
| Hugging Face | Merged 51GB model repo upload is complete or guarded and ready after human review/namespace permission. | `passed` | release/HF_UPLOAD_EVIDENCE.md; scripts/prepare_hf_merged_model_metadata.sh; scripts/upload_hf_merged_model_from_gojira_b.sh | |
|
| 38 |
+
| Hugging Face | Uploaded Hugging Face repos are downloadable by intended users. | `passed` | release/HF_UPLOAD_EVIDENCE.md; python3 scripts/check_hf_uploaded_release.py --namespace RMDWLLC --apply | |
|
| 39 |
| Quality | Customer-style evals cover website, proposal, Stripe/payment, CRM/reporting, CSV/parser, Kiyomi operating pack, and safety/provenance. | `passed` | evals/tasks/opencode-customer-readiness.jsonl; runs/opencode-customer-readiness/20260603T185835Z/summary.md | |
|
| 40 |
| Quality | Model/harness prompts produce file-oriented business-owner artifacts rather than vague advice. | `passed` | kaiju_harness/business_suite.py; release/EVAL_SCOREBOARD.md | |
|
| 41 |
| Provenance | Training/eval provenance is preserved and public docs avoid internal checkpoint naming except license/provenance attribution. | `passed` | release/SOURCE_INVENTORY.md; release/DATA_PROVENANCE_DRAFT.md; release/PUBLIC_TESTING_QUICKSTART.md | |
|
|
|
|
| 57 |
python3 scripts/check_paid_api_readiness.py --mode launch
|
| 58 |
python3 scripts/check_hf_staging_integrity.py --require-checksums
|
| 59 |
python3 scripts/check_hf_release_permission_evidence.py
|
| 60 |
+
python3 scripts/check_hf_uploaded_release.py --namespace RMDWLLC --apply
|
| 61 |
python3 scripts/check_human_release_review.py --mode public
|
| 62 |
```
|