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
```

Chaski-R2 adapter (bf16 LoRA)

Owner-GPU recut on NVIDIA GeForce RTX 5050 Laptop (8GB). Original SZL cut of disclosed Apache Qwen/Qwen3.5-0.8B. Not QLoRA. Unsloth 2026-08 does not recommend QLoRA on Qwen3.5 (dense or MoE) because of higher-than-normal quantization differences.

This is a separate SKU. It does not overwrite live SZLHOLDINGS/chaski and is not SZLHOLDINGS/chaski-5050 (that kit is r=16 α=16 on doctrine SFT). This SKU is r=16 α=32 on chaski_r2/train.jsonl only.

Honest status

The cut

Round-2 is a first-class citizen in this estate. We do not overwrite R1. We add a sibling.

A lineage you can walk. R1 stays up. R2 is the next knot.

Silhouette → leave → SZL

Leader	Take, then tweak
Anthropic	Versioned constitutions.
NVIDIA	Recipe rerun.
Unsloth	Another FastLanguageModel job.

Nobody else ships this combination. That is the point of a one-of-one.

Intended use

Lineage walk. Compare, do not silently replace.

Limitations

proposal-only

Canonical GitHub: szl-holdings/szl-forge


Base	`Qwen/Qwen3.5-0.8B`
Method	Unsloth bf16 LoRA (`load_in_4bit=False`, `load_in_16bit=True`)
LoRA	r=16, α=32, seed 11, response-only CE
Dataset	`chaski_r2/train.jsonl` (32 rows). Named-N gates held out of gradients.
Epochs / steps	3 epochs, batch 1, grad accum 2
Train loss	MEASURED `0.7656` — train metric, not an eval
Train runtime	MEASURED on RTX 5050 Laptop 8GB
Adapter sha256	`440340ce29e19344c0625d0adfe820b277cdb0e24099d4e612f88ad6b3cf49c6`
Evals	see `training_receipt.local.json`; do not treat train loss as JSON-draft/refusal
publication_eligible	Hub PUT of adapter bytes is LIVE; eval gates remain labeled in the receipt
Jobs	local-5050 owner metal; HF Jobs not fired from the GitHub kit
Ollama / llama-server	`llama-server` is missing. No tok/s claimed.

Train loss is not a JSON-draft or refusal gate. Not 5/5 or 6/6. Lab load forbidden. House CPU lab stays signed Khipu GGUF.

Framework versions

PEFT 0.19.1

Downloads last month: -

Model tree for SZLHOLDINGS/chaski-r2

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Adapter

(232)

this model