Instructions to use jprivera44/mo9b-distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jprivera44/mo9b-distilled with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.3-70B-Instruct")
model = PeftModel.from_pretrained(base_model, "jprivera44/mo9b-distilled")

Transformers

How to use jprivera44/mo9b-distilled with Transformers:

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

pipe = pipeline("text-generation", model="jprivera44/mo9b-distilled")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jprivera44/mo9b-distilled", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jprivera44/mo9b-distilled with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jprivera44/mo9b-distilled"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jprivera44/mo9b-distilled",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jprivera44/mo9b-distilled

SGLang

How to use jprivera44/mo9b-distilled 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 "jprivera44/mo9b-distilled" \
    --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": "jprivera44/mo9b-distilled",
		"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 "jprivera44/mo9b-distilled" \
        --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": "jprivera44/mo9b-distilled",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use jprivera44/mo9b-distilled 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 jprivera44/mo9b-distilled 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 jprivera44/mo9b-distilled to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jprivera44/mo9b-distilled to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="jprivera44/mo9b-distilled",
    max_seq_length=2048,
)

Docker Model Runner
How to use jprivera44/mo9b-distilled with Docker Model Runner:
```
docker model run hf.co/jprivera44/mo9b-distilled
```

jprivera44 commited on Apr 24

Commit

e696b7a

verified ·

1 Parent(s): a413d27

Upload tokenizer_config.json with huggingface_hub

Browse files

Files changed (1) hide show

tokenizer_config.json +18 -0

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,18 @@

+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "from_slow": true,
+  "is_local": false,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}