Instructions to use ianshank/phi-35-moe-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ianshank/phi-35-moe-instruct with Transformers:

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

pipe = pipeline("text-generation", model="ianshank/phi-35-moe-instruct", trust_remote_code=True)

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

tokenizer = AutoTokenizer.from_pretrained("ianshank/phi-35-moe-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ianshank/phi-35-moe-instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ianshank/phi-35-moe-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ianshank/phi-35-moe-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ianshank/phi-35-moe-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ianshank/phi-35-moe-instruct

SGLang

How to use ianshank/phi-35-moe-instruct 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 "ianshank/phi-35-moe-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ianshank/phi-35-moe-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ianshank/phi-35-moe-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ianshank/phi-35-moe-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ianshank/phi-35-moe-instruct with Docker Model Runner:
```
docker model run hf.co/ianshank/phi-35-moe-instruct
```

phi-35-moe-instruct

Commit History

Sep 13, 2025

23:50
Add comprehensive training infrastructure for Phi-3.5-MoE model

ianshank

Verified signature
420a4f2
22:43
Upload training_data/processed/terraform_expert_realistic_train.jsonl with huggingface_hub

ianshank

Verified signature
2fd69f8
22:43
Upload training_data/processed/javascript_developer_gd_gradient_descent_train.jsonl with huggingface_hub

ianshank

Verified signature
303f5b8
22:43
Upload training_data/processed/ext_infrastructure_agent_synthetic_prompts.jsonl with huggingface_hub

ianshank

Verified signature
ea39863
22:43
Upload training_data/processed/principal_architect_train.jsonl with huggingface_hub

ianshank

Verified signature
acf3fb5
22:43
Upload training_data/processed/performance_predictor_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
80f4563
22:43
Upload training_data/processed/knowledge_curator_realistic_train.jsonl with huggingface_hub

ianshank

Verified signature
e1e7c72
22:42
Upload training_data/processed/devops_engineer_realistic_train.jsonl with huggingface_hub

ianshank

Verified signature
6876970
22:42
Upload training_data/processed/security_specialist_realistic_train.jsonl with huggingface_hub

ianshank

Verified signature
62fbb82
22:42
Upload training_data/processed/ui_ux_designer_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
f286b60
22:42
Upload training_data/processed/site_reliability_engineer_gd_gradient_descent_train.jsonl with huggingface_hub

ianshank

Verified signature
c5606f0
22:42
Upload training_data/processed/javascript_developer_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
45f4b61
22:42
Upload training_data/processed/style_train.jsonl with huggingface_hub

ianshank

Verified signature
e98858d
22:42
Upload training_data/processed/memory_train.jsonl with huggingface_hub

ianshank

Verified signature
d8c45f8
22:42
Upload training_data/processed/ai_research_scientist_gd_gradient_descent_train.jsonl with huggingface_hub

ianshank

Verified signature
933b97f
22:42
Upload training_data/processed/knowledge_curator_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
baad162
22:42
Upload training_data/processed/infrastructure_expert_realistic_train.jsonl with huggingface_hub

ianshank

Verified signature
b78b785
22:42
Upload training_data/processed/game_developer_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
2201b49
22:42
Upload training_data/processed/infrastructure_train.jsonl with huggingface_hub

ianshank

Verified signature
19b6010
22:42
Upload training_data/processed/quality_assurance_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
1a75aa2
22:42
Upload training_data/processed/risk_manager_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
3f6bb6a
22:42
Upload training_data/processed/iot_engineer_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
e700811
22:42
Upload training_data/processed/architecture_analyzer_train.jsonl with huggingface_hub

ianshank

Verified signature
ff7ee9e
22:42
Upload training_data/processed/business_analyst_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
4bb39d6
22:42
Upload training_data/processed/blockchain_developer_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
79b7856
22:42
Upload training_data/processed/risk_manager_realistic_train.jsonl with huggingface_hub

ianshank

Verified signature
b6d5f49
22:42
Upload training_data/processed/blockchain_developer_gd_gradient_descent_train.jsonl with huggingface_hub

ianshank

Verified signature
6fcd9d1
22:42
Upload training_data/processed/ml_ops_engineer_gd_gradient_descent_train.jsonl with huggingface_hub

ianshank

Verified signature
1eac306
22:42
Upload training_data/processed/infrastructure_expert_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
e6de1c7
22:42
Upload training_data/processed/network_engineer_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
7b16d3f
22:42
Upload training_data/processed/backend_developer_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
8c71dc7
22:42
Upload training_data/processed/unified_infrastructure_dataset.jsonl with huggingface_hub

ianshank

Verified signature
6344a7f
22:42
Upload training_data/processed/empathy_advisor_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
0c3b66c
22:42
Upload training_data/processed/master_orchestrator_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
7257373
22:42
Upload training_data/processed/optimization_agent_train.jsonl with huggingface_hub

ianshank

Verified signature
81711da
22:42
Upload training_data/processed/planner_train.jsonl with huggingface_hub

ianshank

Verified signature
416545b
22:42
Upload training_data/processed/site_reliability_engineer_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
7e38931
22:42
Upload training_data/processed/terraform_expert_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
69d3856
22:42
Upload training_data/processed/unified_devsecops_dataset.jsonl with huggingface_hub

ianshank

Verified signature
93cfa20
22:42
Upload training_data/processed/ml_ops_engineer_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
a5d5cda
22:42
Upload training_data/processed/multi_agent_synthesizer_train.jsonl with huggingface_hub

ianshank

Verified signature
fa24200
22:42
Upload training_data/processed/ai_research_scientist_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
cbb29aa
22:42
Upload training_data/processed/product_strategist_realistic_train.jsonl with huggingface_hub

ianshank

Verified signature
746c9e0
22:42
Upload training_data/processed/security_specialist_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
c091fb9
22:42
Upload training_data/processed/processed_infrastructure_prompts.jsonl with huggingface_hub

ianshank

Verified signature
112aacd
22:42
Upload training_data/processed/reasoning_engine_realistic_train.jsonl with huggingface_hub

ianshank

Verified signature
95120be
22:42
Upload training_data/processed/php_developer_expanded_train.jsonl with huggingface_hub

ianshank

Verified signature
6cc5b93
22:42
Upload training_data/processed/rag_train.jsonl with huggingface_hub

ianshank

Verified signature
5df2f06
22:42
Upload training_data/processed/pattern_recognizer_enhanced_train.jsonl with huggingface_hub

ianshank

Verified signature
e9be963
22:42
Upload training_data/processed/comprehensive_infrastructure_dataset.jsonl with huggingface_hub

ianshank

Verified signature
77862fb

Commit History

Sep 13, 2025

Add comprehensive training infrastructure for Phi-3.5-MoE model

Upload training_data/processed/terraform_expert_realistic_train.jsonl with huggingface_hub

Upload training_data/processed/javascript_developer_gd_gradient_descent_train.jsonl with huggingface_hub

Upload training_data/processed/ext_infrastructure_agent_synthetic_prompts.jsonl with huggingface_hub

Upload training_data/processed/principal_architect_train.jsonl with huggingface_hub

Upload training_data/processed/performance_predictor_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/knowledge_curator_realistic_train.jsonl with huggingface_hub

Upload training_data/processed/devops_engineer_realistic_train.jsonl with huggingface_hub

Upload training_data/processed/security_specialist_realistic_train.jsonl with huggingface_hub

Upload training_data/processed/ui_ux_designer_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/site_reliability_engineer_gd_gradient_descent_train.jsonl with huggingface_hub

Upload training_data/processed/javascript_developer_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/style_train.jsonl with huggingface_hub

Upload training_data/processed/memory_train.jsonl with huggingface_hub

Upload training_data/processed/ai_research_scientist_gd_gradient_descent_train.jsonl with huggingface_hub

Upload training_data/processed/knowledge_curator_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/infrastructure_expert_realistic_train.jsonl with huggingface_hub

Upload training_data/processed/game_developer_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/infrastructure_train.jsonl with huggingface_hub

Upload training_data/processed/quality_assurance_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/risk_manager_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/iot_engineer_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/architecture_analyzer_train.jsonl with huggingface_hub

Upload training_data/processed/business_analyst_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/blockchain_developer_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/risk_manager_realistic_train.jsonl with huggingface_hub

Upload training_data/processed/blockchain_developer_gd_gradient_descent_train.jsonl with huggingface_hub

Upload training_data/processed/ml_ops_engineer_gd_gradient_descent_train.jsonl with huggingface_hub

Upload training_data/processed/infrastructure_expert_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/network_engineer_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/backend_developer_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/unified_infrastructure_dataset.jsonl with huggingface_hub

Upload training_data/processed/empathy_advisor_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/master_orchestrator_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/optimization_agent_train.jsonl with huggingface_hub

Upload training_data/processed/planner_train.jsonl with huggingface_hub

Upload training_data/processed/site_reliability_engineer_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/terraform_expert_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/unified_devsecops_dataset.jsonl with huggingface_hub

Upload training_data/processed/ml_ops_engineer_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/multi_agent_synthesizer_train.jsonl with huggingface_hub

Upload training_data/processed/ai_research_scientist_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/product_strategist_realistic_train.jsonl with huggingface_hub

Upload training_data/processed/security_specialist_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/processed_infrastructure_prompts.jsonl with huggingface_hub

Upload training_data/processed/reasoning_engine_realistic_train.jsonl with huggingface_hub

Upload training_data/processed/php_developer_expanded_train.jsonl with huggingface_hub

Upload training_data/processed/rag_train.jsonl with huggingface_hub

Upload training_data/processed/pattern_recognizer_enhanced_train.jsonl with huggingface_hub

Upload training_data/processed/comprehensive_infrastructure_dataset.jsonl with huggingface_hub