Instructions to use SZLHOLDINGS/chaski-r2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SZLHOLDINGS/chaski-r2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-0.8B")
model = PeftModel.from_pretrained(base_model, "SZLHOLDINGS/chaski-r2")

Transformers

How to use SZLHOLDINGS/chaski-r2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SZLHOLDINGS/chaski-r2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SZLHOLDINGS/chaski-r2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SZLHOLDINGS/chaski-r2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SZLHOLDINGS/chaski-r2"
# 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-r2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SZLHOLDINGS/chaski-r2

SGLang

How to use SZLHOLDINGS/chaski-r2 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-r2" \
    --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-r2",
		"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-r2" \
        --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-r2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use SZLHOLDINGS/chaski-r2 with Docker Model Runner:
```
docker model run hf.co/SZLHOLDINGS/chaski-r2
```

betterwithage commited on 4 days ago

Commit

6aba3db

verified ·

1 Parent(s): d428aee

Upload training_receipt.local.json with huggingface_hub

Browse files

Files changed (1) hide show

training_receipt.local.json +73 -0

training_receipt.local.json ADDED Viewed

	@@ -0,0 +1,73 @@

+{
+  "kind": "szl-chaski-r2-training-receipt",
+  "schema": "szl.frontier-training-run/v1",
+  "v": 1,
+  "artifact": "SZLHOLDINGS/chaski-r2",
+  "sku": "CHASKI-R2",
+  "silhouette": "CHAWPI",
+  "atelier_lock": true,
+  "hub_id_declared_only": true,
+  "hub_page": false,
+  "separate_sku": true,
+  "canonical_base": "Qwen/Qwen3.5-0.8B",
+  "base_model": "Qwen/Qwen3.5-0.8B",
+  "baseModel": "Qwen/Qwen3.5-0.8B",
+  "base_model_relation": "adapter",
+  "base_model_runtime": "Qwen/Qwen3.5-0.8B",
+  "does_not_overwrite": "SZLHOLDINGS/chaski",
+  "forbidden_5050": "SZLHOLDINGS/chaski-5050",
+  "not_5050": true,
+  "not_bf16_5050": true,
+  "qlora": false,
+  "load_in_4bit": false,
+  "load_in_16bit": true,
+  "quant": "bf16-lora",
+  "dataset_file": "chaski_r2/train.jsonl",
+  "dataset_sha256": "4db6ee9f13f286e05705d683bc40efa0ad5cfe5092258c59f478ae79275aa26a",
+  "held_out_in_gradients": false,
+  "held_out": {
+    "chaski/gate/json_drafts.n5.jsonl": 5,
+    "chaski/gate/adversarial_refusals.n6.jsonl": 6
+  },
+  "seed": 11,
+  "num_train_epochs": 3,
+  "warmup_steps": 6,
+  "lora_r": 16,
+  "lora_alpha": 32,
+  "learning_rate": 0.0002,
+  "lr_scheduler_type": "constant_with_warmup",
+  "optim": "adamw_8bit",
+  "response_only_loss": true,
+  "trackio": false,
+  "report_to": "none",
+  "push_to_hub": false,
+  "jobs": "UNAVAILABLE",
+  "weights": "LOCAL",
+  "adapterSha256": "440340ce29e19344c0625d0adfe820b277cdb0e24099d4e612f88ad6b3cf49c6",
+  "finalTrainLoss": "0.7656",
+  "train_loss_label": "MEASURED",
+  "evals": "none-this-run",
+  "quality": "UNAVAILABLE",
+  "lambda": "Conjecture 1",
+  "doctrine": "v11 LOCKED 749/14/163",
+  "proposal_only": true,
+  "publication_eligible": false,
+  "autonomy_eligible": false,
+  "serve_pin": false,
+  "khipu_lab_pin": false,
+  "a11oy_mini_scripts_only": true,
+  "hub_put": false,
+  "training_rows": 32,
+  "claim_boundary": "ATELIER lock. Separate SKU id SZLHOLDINGS/chaski-r2 is declared only \u2014 do not costume a README-only Hub ID. Does not overwrite SZLHOLDINGS/chaski. Not SZLHOLDINGS/chaski-5050. Base in prose: Qwen/Qwen3.5-0.8B. GPU honesty is MEASURED or UNAVAILABLE. No ROADMAP parking. QLoRA is not recommended on Qwen3.5; this SKU is bf16 LoRA r=16 \u03b1=32 (not the 5050 sixteen-alpha kit). Jobs this checkout UNAVAILABLE (not fired). Eval is PR 63 named-N after train; none-this-run until that generate. publication_eligible false until MEASURED generate. Lab stays Khipu. A11OY-MINI stays scripts-only. Doctrine v11. This checkout does not PUT Hub.",
+  "computed_at": "2026-08-29T03:26:45.357857+00:00",
+  "source": "local-train",
+  "gpu": {
+    "platform": "Windows-10-10.0.26200-SP0",
+    "python": "3.11.9",
+    "nvidia_smi": "NVIDIA GeForce RTX 5050 Laptop GPU, 8151 MiB, 7787 MiB, 610.47",
+    "torch": "2.10.0+cu128",
+    "cuda": true,
+    "gpu_name": "NVIDIA GeForce RTX 5050 Laptop GPU",
+    "gpu_mem_gb": 7.96
+  }
+}