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

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 new

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
```

Adding `safetensors` variant of this model

by SFconvertbot - opened Feb 16, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-7

Files changed (4) hide show

config.json +2 -2
generation_config.json +1 -1
pytorch_model.bin +0 -3
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -23,9 +23,9 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.49.0",
   "unsloth_fixed": true,
-  "unsloth_version": "2025.2.15",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

   "sliding_window": null,
   "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

@@ -7,5 +7,5 @@
   "pad_token_id": 151654,
   "temperature": 0.6,
   "top_p": 0.95,
-  "transformers_version": "4.49.0"
 }

   "pad_token_id": 151654,
   "temperature": 0.6,
   "top_p": 0.95,
+  "transformers_version": "4.48.2"
 }

pytorch_model.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4927829062c5f070d002cac4072b9e14fa11b23bda07dc0ae5d2f17cbf8db948
-size 3554290006

tokenizer_config.json CHANGED Viewed

@@ -190,7 +190,7 @@
   "pad_token": "<|vision_pad|>",
   "padding_side": "left",
   "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizerFast",
   "unk_token": null,
   "use_default_system_prompt": false
 }

   "pad_token": "<|vision_pad|>",
   "padding_side": "left",
   "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
   "unk_token": null,
   "use_default_system_prompt": false
 }