Instructions to use Crusadersk/qwen2.5-1.5b-awq-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Crusadersk/qwen2.5-1.5b-awq-4bit with Transformers:

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

pipe = pipeline("text-generation", model="Crusadersk/qwen2.5-1.5b-awq-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Crusadersk/qwen2.5-1.5b-awq-4bit")
model = AutoModelForCausalLM.from_pretrained("Crusadersk/qwen2.5-1.5b-awq-4bit", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Crusadersk/qwen2.5-1.5b-awq-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Crusadersk/qwen2.5-1.5b-awq-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Crusadersk/qwen2.5-1.5b-awq-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Crusadersk/qwen2.5-1.5b-awq-4bit

SGLang

How to use Crusadersk/qwen2.5-1.5b-awq-4bit 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 "Crusadersk/qwen2.5-1.5b-awq-4bit" \
    --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": "Crusadersk/qwen2.5-1.5b-awq-4bit",
		"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 "Crusadersk/qwen2.5-1.5b-awq-4bit" \
        --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": "Crusadersk/qwen2.5-1.5b-awq-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Crusadersk/qwen2.5-1.5b-awq-4bit with Docker Model Runner:
```
docker model run hf.co/Crusadersk/qwen2.5-1.5b-awq-4bit
```

Crusadersk commited on Jul 6

Commit

8d8d7a1

verified ·

1 Parent(s): 57f8978

Update research archive provenance

Browse files

Replace stale 40-TR acknowledgement with stable Chimera/Banterhearts archive provenance.

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -1,4 +1,4 @@
----
 language:
 - en
 tags:
@@ -14,7 +14,7 @@ library_name: transformers
 license: apache-2.0
 ---
-# Qwen 2.5 1.5B Instruct — AWQ 4-bit
 Self-quantized **AWQ 4-bit** checkpoint of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) with fully documented calibration provenance.
@@ -46,7 +46,7 @@ Created as part of the [Banterhearts research program](https://github.com/Sahil1
 ### Why Self-Quantized?
-Pre-quantized checkpoints on HuggingFace typically have unknown calibration provenance — the dataset, sample count, seed, and group size are rarely documented. This checkpoint was self-quantized with controlled, documented settings to enable rigorous cross-method comparison (GGUF k-quant vs AWQ vs GPTQ) in a NeurIPS 2026 submission on quality-safety correlation under quantization.
 ## Evaluation Results
@@ -122,7 +122,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ## Reproduction
-The full quantization pipeline — Dockerfiles, quantization scripts, and a 766-line engineering log documenting every platform failure and solution — is available at:
 ```
 research/tr142/expansion/
@@ -152,4 +152,4 @@ in the [Banterhearts repository](https://github.com/Sahil170595/Banterhearts). K
 ## Acknowledgments
-This work is part of a 40-TR research program on consumer LLM deployment safety, conducted independently as pre-doctoral research. Full program details at [github.com/Sahil170595/Banterhearts](https://github.com/Sahil170595/Banterhearts).

+---
 language:
 - en
 tags:
 license: apache-2.0
 ---
+# Qwen 2.5 1.5B Instruct â€” AWQ 4-bit
 Self-quantized **AWQ 4-bit** checkpoint of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) with fully documented calibration provenance.
 ### Why Self-Quantized?
+Pre-quantized checkpoints on HuggingFace typically have unknown calibration provenance â€” the dataset, sample count, seed, and group size are rarely documented. This checkpoint was self-quantized with controlled, documented settings to enable rigorous cross-method comparison (GGUF k-quant vs AWQ vs GPTQ) in a NeurIPS 2026 submission on quality-safety correlation under quantization.
 ## Evaluation Results
 ## Reproduction
+The full quantization pipeline â€” Dockerfiles, quantization scripts, and a 766-line engineering log documenting every platform failure and solution â€” is available at:
 ```
 research/tr142/expansion/
 ## Acknowledgments
+This work is part of the Chimera/Banterhearts technical-report program on deployment-time LLM behavior, quantization, refusal robustness, batching effects, and inference-stack reliability. Canonical public archive: [Chimeraforge Reports](https://chimeraforge.vercel.app/reports); source context: [github.com/Sahil170595/Banterhearts](https://github.com/Sahil170595/Banterhearts).