Instructions to use katuni4ka/phi-3.5-moe-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use katuni4ka/phi-3.5-moe-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="katuni4ka/phi-3.5-moe-tiny-random", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("katuni4ka/phi-3.5-moe-tiny-random", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("katuni4ka/phi-3.5-moe-tiny-random", trust_remote_code=True)
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 katuni4ka/phi-3.5-moe-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "katuni4ka/phi-3.5-moe-tiny-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "katuni4ka/phi-3.5-moe-tiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/katuni4ka/phi-3.5-moe-tiny-random

SGLang

How to use katuni4ka/phi-3.5-moe-tiny-random 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 "katuni4ka/phi-3.5-moe-tiny-random" \
    --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": "katuni4ka/phi-3.5-moe-tiny-random",
		"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 "katuni4ka/phi-3.5-moe-tiny-random" \
        --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": "katuni4ka/phi-3.5-moe-tiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use katuni4ka/phi-3.5-moe-tiny-random with Docker Model Runner:
```
docker model run hf.co/katuni4ka/phi-3.5-moe-tiny-random
```

katuni4ka commited on Mar 26, 2025

Commit

c4310aa

verified ·

1 Parent(s): c4828ab

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -53

README.md CHANGED Viewed

@@ -1,57 +1,4 @@
 ---
 library_name: transformers
 pipeline_tag: text-generation
-inference: true
-widget:
-- text: Hello!
-  example_title: Hello world
-  group: Python
 ---
-This model is for debugging. It is randomly initialized using the config from [microsoft/Phi-3.5-MoE-instruct](https://huggingface.co/microsoft/Phi-3.5-MoE-instruct) but with smaller size.
-Codes:
-```python
-import os
-import torch
-import transformers
-from transformers import (AutoConfig, AutoModelForCausalLM, AutoTokenizer,
-                          GenerationConfig, pipeline, set_seed)
-model_id = "microsoft/Phi-3.5-MoE-instruct"
-repo_id = "yujiepan/phi-3.5-moe-tiny-random"
-save_path = f"/tmp/{repo_id}"
-config = AutoConfig.from_pretrained(model_id, trust_remote_code=True)
-config.hidden_size = 16
-config.intermediate_size = 32
-config.num_attention_heads = 4
-config.num_hidden_layers = 2
-config.num_key_value_heads = 4
-config.rope_scaling['long_factor'] = [1.0299, 1.0499]
-config.rope_scaling['short_factor'] = [1.05, 1.05]
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
-tokenizer.save_pretrained(save_path)
-model = AutoModelForCausalLM.from_config(
-    config, torch_dtype=torch.bfloat16,
-    # attn_implementation="sdpa",
-    trust_remote_code=True,
-)
-model.generation_config = GenerationConfig.from_pretrained(
-    model_id, trust_remote_code=True
-)
-set_seed(42)
-with torch.no_grad():
-    for _, p in sorted(model.named_parameters()):
-        torch.nn.init.uniform_(p, -0.3, 0.3)
-model.save_pretrained(save_path)
-pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device="cuda",
-                trust_remote_code=True, max_new_tokens=20)
-print(pipe('Hello'))
-```

 ---
 library_name: transformers
 pipeline_tag: text-generation
 ---