Instructions to use SZLHOLDINGS/chaski with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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)

# 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=40)
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
```

betterwithage commited on 2 days ago

Commit

542671b

verified ·

1 Parent(s): 55f5aef

docs: jobs RUNNING attempt 4 6a91bb7c; attempt 3 completed no weights

Browse files

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -20,13 +20,13 @@ szl:
   artifact_class: ADAPTER
   originality: FINETUNE_DISCLOSED_BASE
   collection: "SZL Fall 2026 — Original Cuts"
-  jobs: COMPLETED
-  job_id: 6a91ba00984507d9db4ea07f
   job_namespace: SZLHOLDINGS
   weights: UNAVAILABLE
   evals: none-this-run
   publication_eligible: false
-  job_retry: 6a91bb7c984507d9db4ea0a4
   job_prior_failed:
     - 6a91b8ba984507d9db4ea071
     - 6a91b990984507d9db4ea077
@@ -42,9 +42,9 @@ szl:
 | **Originality** | SZL fine-tune of a disclosed Apache Qwen instruct base |
 | **Base** | `Qwen/Qwen3.5-0.8B` (Apache-2.0, 0.6B–2B lock) |
 | **License** | `apache-2.0` |
-| **HF Jobs** | Attempt 3 COMPLETED [`6a91ba00984507d9db4ea07f`](https://huggingface.co/jobs/SZLHOLDINGS/6a91ba00984507d9db4ea07f). Weights UNAVAILABLE. Attempt 4 RUNNING [`6a91bb7c984507d9db4ea0a4`](https://huggingface.co/jobs/SZLHOLDINGS/6a91bb7c984507d9db4ea0a4) (explicit `upload_folder`). |
-| **Status** | CUTTING · weights ROADMAP |
-| **Later SKU** | `A11OY-MINI` will be a GGUF of **this** model after adapters land. ROADMAP. A receipt is not a GGUF parent. |
 | **Sibling** | [`szl-receiptagent-qwen35-0.8b-v2`](https://huggingface.co/SZLHOLDINGS/szl-receiptagent-qwen35-0.8b-v2) |
 > **Fashion rule.** Silhouette from Qwen3 / Qwen3.5 instruct. Cut is original SZL. We do not republish someone else's tensors.
@@ -70,11 +70,11 @@ The house CPU lab serves **Khipu GGUF**, not Chaski. Lab load forbidden.
 ## Training
 - **Recipe:** Unsloth QLoRA SFT. Script: `train_chaski.py`. Loads **only** `szl_dataset.jsonl`.
-- **Attempt 3 COMPLETED:** train loss MEASURED `1.782708187121898` (64/64, 45 rows, seed 11). Receipt on repo. Adapters UNAVAILABLE (`push_to_hub` did not persist; ephemeral disk gone).
-- **Attempt 4:** [`6a91bb7c984507d9db4ea0a4`](https://huggingface.co/jobs/SZLHOLDINGS/6a91bb7c984507d9db4ea0a4) explicit adapter `upload_folder`. Not MEASURED until it finishes.
 - **Attempts 1–2 FAILED:** `6a91b8ba984507d9db4ea071` CastError; `6a91b990984507d9db4ea077` pyyaml 30s timeout.
 - **Trackio:** 404 `betterwithage/trackio-bucket`. No dashboard URL.
 ## Limitations
-- Narrow curriculum. Controller required. Λ = Conjecture 1. Trust ceiling 0.97. `publication_eligible: false`.

   artifact_class: ADAPTER
   originality: FINETUNE_DISCLOSED_BASE
   collection: "SZL Fall 2026 — Original Cuts"
+  jobs: RUNNING
+  job_id: 6a91bb7c984507d9db4ea0a4
+  job_completed_no_weights: 6a91ba00984507d9db4ea07f
   job_namespace: SZLHOLDINGS
   weights: UNAVAILABLE
   evals: none-this-run
   publication_eligible: false
   job_prior_failed:
     - 6a91b8ba984507d9db4ea071
     - 6a91b990984507d9db4ea077
 | **Originality** | SZL fine-tune of a disclosed Apache Qwen instruct base |
 | **Base** | `Qwen/Qwen3.5-0.8B` (Apache-2.0, 0.6B–2B lock) |
 | **License** | `apache-2.0` |
+| **HF Jobs** | Attempt 4 RUNNING [`6a91bb7c984507d9db4ea0a4`](https://huggingface.co/jobs/SZLHOLDINGS/6a91bb7c984507d9db4ea0a4) (`upload_folder` adapter + merged 16-bit). |
+| **Status** | CUTTING until files exist on the repo |
+| **Later SKU** | `A11OY-MINI` GGUF of this model after adapters land. ROADMAP. A receipt is not a GGUF parent. |
 | **Sibling** | [`szl-receiptagent-qwen35-0.8b-v2`](https://huggingface.co/SZLHOLDINGS/szl-receiptagent-qwen35-0.8b-v2) |
 > **Fashion rule.** Silhouette from Qwen3 / Qwen3.5 instruct. Cut is original SZL. We do not republish someone else's tensors.
 ## Training
 - **Recipe:** Unsloth QLoRA SFT. Script: `train_chaski.py`. Loads **only** `szl_dataset.jsonl`.
+- **Attempt 4 RUNNING:** [`6a91bb7c984507d9db4ea0a4`](https://huggingface.co/jobs/SZLHOLDINGS/6a91bb7c984507d9db4ea0a4) explicit `upload_folder` adapter + merged 16-bit.
+- **Attempt 3 COMPLETED, not RUNNING:** [`6a91ba00984507d9db4ea07f`](https://huggingface.co/jobs/SZLHOLDINGS/6a91ba00984507d9db4ea07f). Train loss MEASURED `1.782708187121898` (64/64, 45 rows, seed 11). Safetensors UNAVAILABLE. Receipt only.
 - **Attempts 1–2 FAILED:** `6a91b8ba984507d9db4ea071` CastError; `6a91b990984507d9db4ea077` pyyaml 30s timeout.
 - **Trackio:** 404 `betterwithage/trackio-bucket`. No dashboard URL.
 ## Limitations
+- Narrow curriculum. Controller required. Λ = Conjecture 1. Trust ceiling 0.97. `publication_eligible: false`. CUTTING until files exist on the repo.