Instructions to use SvalTek/Qwen2.5-ColdBrew-R1_4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SvalTek/Qwen2.5-ColdBrew-R1_4bit with Transformers:

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

pipe = pipeline("text-generation", model="SvalTek/Qwen2.5-ColdBrew-R1_4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SvalTek/Qwen2.5-ColdBrew-R1_4bit")
model = AutoModelForCausalLM.from_pretrained("SvalTek/Qwen2.5-ColdBrew-R1_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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SvalTek/Qwen2.5-ColdBrew-R1_4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SvalTek/Qwen2.5-ColdBrew-R1_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": "SvalTek/Qwen2.5-ColdBrew-R1_4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SvalTek/Qwen2.5-ColdBrew-R1_4bit

SGLang

How to use SvalTek/Qwen2.5-ColdBrew-R1_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 "SvalTek/Qwen2.5-ColdBrew-R1_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": "SvalTek/Qwen2.5-ColdBrew-R1_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 "SvalTek/Qwen2.5-ColdBrew-R1_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": "SvalTek/Qwen2.5-ColdBrew-R1_4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use SvalTek/Qwen2.5-ColdBrew-R1_4bit with Docker Model Runner:
```
docker model run hf.co/SvalTek/Qwen2.5-ColdBrew-R1_4bit
```

Theros commited on Mar 7, 2025

Commit

e4d0fac

verified ·

1 Parent(s): 8537a83

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (5) hide show

README.md +1 -0
config.json +4 -4
model-00001-of-00002.safetensors +2 -2
model-00002-of-00002.safetensors +1 -1
model.safetensors.index.json +1 -1

README.md CHANGED Viewed

@@ -6,6 +6,7 @@ tags:
 - unsloth
 - qwen2
 - trl
 license: apache-2.0
 language:
 - en

 - unsloth
 - qwen2
 - trl
+- sft
 license: apache-2.0
 language:
 - en

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Theros/Qwen2.5-ColdBrew-R1",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -19,7 +19,7 @@
   "organization": "SvalTek",
   "pad_token_id": 151665,
   "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -35,9 +35,9 @@
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
   "transformers_version": "4.48.3",
-  "unsloth_version": "2025.2.12",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

 {
+  "_name_or_path": "Theros/Qwen2.5-ColdBrew-Aetheria",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "organization": "SvalTek",
   "pad_token_id": 151665,
   "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.48.3",
+  "unsloth_version": "2025.3.8",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:208058b7019c8f8deb04a6ab2b9ab12c00a6e31c495252db78a5f23649dcef58
-size 4454406572

 version https://git-lfs.github.com/spec/v1
+oid sha256:b5bdde34d9daa88ebd3c39449a3f9b9537eaf1cb83c5ba7e629b146ffebf2f22
+size 4454406713

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95743370c3723fa309168b59c6852396ec0495b5c1bf5affb089afd2fc915d2f
 size 1087142016

 version https://git-lfs.github.com/spec/v1
+oid sha256:ecfd97e2984dad183f6e057aa379f9d8d00dda2f2b305fa7fe7b5183ef1fdfba
 size 1087142016

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5541392172
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",

 {
   "metadata": {
+    "total_size": 5541392169
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",