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

Libraries

How to use notzero/model_combined with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("notzero/model_combined")
model = AutoModelForCausalLM.from_pretrained("notzero/model_combined")
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 notzero/model_combined with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/notzero/model_combined

SGLang

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

Unsloth Studio

How to use notzero/model_combined with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for notzero/model_combined to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for notzero/model_combined to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for notzero/model_combined to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="notzero/model_combined",
    max_seq_length=2048,
)

Docker Model Runner
How to use notzero/model_combined with Docker Model Runner:
```
docker model run hf.co/notzero/model_combined
```

notzero commited on Feb 16, 2025

Commit

52d08dc

1 Parent(s): e14a88f

Trained with Unsloth

Browse files

Files changed (2) hide show

config.json +5 -4
generation_config.json +2 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "huihui-ai/DeepScaleR-1.5B-Preview-abliterated",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -10,13 +10,13 @@
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
-  "max_position_embeddings": 131072,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
-  "pad_token_id": 151643,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000,
@@ -24,7 +24,8 @@
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.48.2",
-  "unsloth_version": "2025.2.12",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

 {
+  "_name_or_path": "unsloth/DeepScaleR-1.5B-Preview",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
+  "max_position_embeddings": 24576,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
+  "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.48.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.2.4",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

generation_config.json CHANGED Viewed

@@ -3,7 +3,8 @@
   "bos_token_id": 151646,
   "do_sample": true,
   "eos_token_id": 151643,
-  "max_length": 131072,
   "temperature": 0.6,
   "top_p": 0.95,
   "transformers_version": "4.48.2"

   "bos_token_id": 151646,
   "do_sample": true,
   "eos_token_id": 151643,
+  "max_length": 24576,
+  "pad_token_id": 151654,
   "temperature": 0.6,
   "top_p": 0.95,
   "transformers_version": "4.48.2"