Text Generation
Transformers
Safetensors
English
qwen3_5
image-text-to-text
szl-holdings
doctrine-v11
governed-ai
proposal-only
research
conversational
Instructions to use SZLHOLDINGS/chaski with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SZLHOLDINGS/chaski with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SZLHOLDINGS/chaski") 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)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("SZLHOLDINGS/chaski") model = AutoModelForMultimodalLM.from_pretrained("SZLHOLDINGS/chaski", device_map="auto") 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=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SZLHOLDINGS/chaski with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SZLHOLDINGS/chaski" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SZLHOLDINGS/chaski", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/SZLHOLDINGS/chaski
- SGLang
How to use SZLHOLDINGS/chaski 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 "SZLHOLDINGS/chaski" \ --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": "SZLHOLDINGS/chaski", "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 "SZLHOLDINGS/chaski" \ --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": "SZLHOLDINGS/chaski", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use SZLHOLDINGS/chaski with Docker Model Runner:
docker model run hf.co/SZLHOLDINGS/chaski
docs: publish Chaski card from szl-forge@5daef16de6e0cfb55daf0ff86ba3281bac1fc821
Browse filesExact-source Chaski card publication. Named-N remains a measured failed gate, publication_eligible and autonomy_eligible remain false, and no model or provider state is promoted. No weights, adapter, configs, evals, visibility, hardware, collection, or runtime state changed.
- README.md +27 -0
- szl-source-binding.json +3 -3
README.md
CHANGED
|
@@ -37,6 +37,30 @@ szl:
|
|
| 37 |
autonomy_eligible: false
|
| 38 |
gpu: UNAVAILABLE
|
| 39 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
<!-- szl:loader-class-boundary -->
|
| 41 |
> **Loader-class boundary (noted 2026-09-30).** The adapter tensors are keyed for the multimodal module layout (`base_model.model.model.language_model.layers.*`, the class `Qwen3_5ForConditionalGeneration` / `AutoModelForImageTextToText`). Under transformers 5.18, `AutoModelForCausalLM` instantiates `Qwen3_5ForCausalLM` (`model.layers.*`); PEFT then applies 0 of the 192 adapter tensors and emits only a warning, so the result is the bare base model (observed and receipted on the sibling `SZLHOLDINGS/chaski-r2` adapter, which shares this exact key layout: byte-identical base outputs on the held-out prompts). Any run that reports a score for this adapter must show adapter key coverage (192/192) and the loader class it used; a record without those fields does not establish that the adapter was applied. Evidence: szl-holdings/szl-forge `tools/geh_v8/evidence_sandbox/chaski_probe/` (CPU replay receipts, #444). Metadata-only note; it authorizes no load, changes no artifact, and adds no claim.
|
| 42 |
|
|
@@ -211,3 +235,6 @@ release gates. A new model or runtime revision requires a new immutable
|
|
| 211 |
evaluation receipt; this card cannot confer approval.
|
| 212 |
|
| 213 |
Doctrine v11 LOCKED. Λ = Conjecture 1. Owner: Stephen Lutar / SZL Holdings.
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
autonomy_eligible: false
|
| 38 |
gpu: UNAVAILABLE
|
| 39 |
---
|
| 40 |
+
|
| 41 |
+
<!-- SZL-CARD-PRESENTATION:v1 -->
|
| 42 |
+
<p><a href="https://huggingface.co/spaces/SZLHOLDINGS/szl-command-lab"><img src="https://raw.githubusercontent.com/szl-holdings/.github/main/profile/assets/szl/logos/szl_mark_holographic.svg" alt="SZL Holdings" width="112" /></a></p>
|
| 43 |
+
|
| 44 |
+
# Chaski
|
| 45 |
+
|
| 46 |
+
A controller-bound drafting experiment that retains its failed qualification as research evidence.
|
| 47 |
+
|
| 48 |
+
**Artifact:** Fine-tuned checkpoint; separate LoRA adapter · **Stage:** HOLD · failed qualification
|
| 49 |
+
|
| 50 |
+
[Explore in Command Lab](https://huggingface.co/spaces/SZLHOLDINGS/szl-command-lab) · [Build](https://github.com/szl-holdings/szl-forge/tree/main/chaski) · [Evidence](https://github.com/szl-holdings/szl-forge/blob/2b4d7a0f69e68d60cb0f35f09c9bac837d66acdc/chaski/card/README.md)
|
| 51 |
+
|
| 52 |
+
Provider compatibility support [requested on 4 October 2026](https://huggingface.co/spaces/huggingface/InferenceSupport/discussions/12783). No provider was listed in the dated Hub observation; adoption and use qualification remain unchanged.
|
| 53 |
+
|
| 54 |
+
## Before you use it
|
| 55 |
+
|
| 56 |
+
- The historical release gates failed: 0/5 JSON drafts and 2/6 adversarial refusals. Publication and autonomy eligibility remain false.
|
| 57 |
+
- Choose the exact checkpoint or adapter form. Adapter evaluation must record the loader class and all 192/192 applied tensors.
|
| 58 |
+
- Generated drafts remain untrusted and require an independent validating controller. This artifact is not a promoted flagship.
|
| 59 |
+
|
| 60 |
+
<details>
|
| 61 |
+
<summary>Technical details and evidence</summary>
|
| 62 |
+
|
| 63 |
+
<!-- SZL-CARD-TECHNICAL:v1:START -->
|
| 64 |
<!-- szl:loader-class-boundary -->
|
| 65 |
> **Loader-class boundary (noted 2026-09-30).** The adapter tensors are keyed for the multimodal module layout (`base_model.model.model.language_model.layers.*`, the class `Qwen3_5ForConditionalGeneration` / `AutoModelForImageTextToText`). Under transformers 5.18, `AutoModelForCausalLM` instantiates `Qwen3_5ForCausalLM` (`model.layers.*`); PEFT then applies 0 of the 192 adapter tensors and emits only a warning, so the result is the bare base model (observed and receipted on the sibling `SZLHOLDINGS/chaski-r2` adapter, which shares this exact key layout: byte-identical base outputs on the held-out prompts). Any run that reports a score for this adapter must show adapter key coverage (192/192) and the loader class it used; a record without those fields does not establish that the adapter was applied. Evidence: szl-holdings/szl-forge `tools/geh_v8/evidence_sandbox/chaski_probe/` (CPU replay receipts, #444). Metadata-only note; it authorizes no load, changes no artifact, and adds no claim.
|
| 66 |
|
|
|
|
| 235 |
evaluation receipt; this card cannot confer approval.
|
| 236 |
|
| 237 |
Doctrine v11 LOCKED. Λ = Conjecture 1. Owner: Stephen Lutar / SZL Holdings.
|
| 238 |
+
|
| 239 |
+
<!-- SZL-CARD-TECHNICAL:v1:END -->
|
| 240 |
+
</details>
|
szl-source-binding.json
CHANGED
|
@@ -21,8 +21,8 @@
|
|
| 21 |
"source": {
|
| 22 |
"assets": {
|
| 23 |
"README.md": {
|
| 24 |
-
"bytes":
|
| 25 |
-
"sha256": "
|
| 26 |
},
|
| 27 |
"holo-banner.svg": {
|
| 28 |
"bytes": 1374,
|
|
@@ -30,7 +30,7 @@
|
|
| 30 |
}
|
| 31 |
},
|
| 32 |
"repository": "szl-holdings/szl-forge",
|
| 33 |
-
"revision": "
|
| 34 |
},
|
| 35 |
"target": {
|
| 36 |
"controlled_paths": [
|
|
|
|
| 21 |
"source": {
|
| 22 |
"assets": {
|
| 23 |
"README.md": {
|
| 24 |
+
"bytes": 12292,
|
| 25 |
+
"sha256": "8e9c16cacf4a086dbd72f7ee7aa1679bf5d1186d8dad71b29a811c45cb6243e7"
|
| 26 |
},
|
| 27 |
"holo-banner.svg": {
|
| 28 |
"bytes": 1374,
|
|
|
|
| 30 |
}
|
| 31 |
},
|
| 32 |
"repository": "szl-holdings/szl-forge",
|
| 33 |
+
"revision": "5daef16de6e0cfb55daf0ff86ba3281bac1fc821"
|
| 34 |
},
|
| 35 |
"target": {
|
| 36 |
"controlled_paths": [
|