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

Libraries

How to use optimum-intel-internal-testing/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="optimum-intel-internal-testing/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("optimum-intel-internal-testing/phi-3.5-moe-tiny-random", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("optimum-intel-internal-testing/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 Settings

vLLM

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

Use Docker

docker model run hf.co/optimum-intel-internal-testing/phi-3.5-moe-tiny-random

SGLang

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

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

Re-upload config.json via AutoConfig (transformers 5.5)

by echarlaix HF Staff - opened 10 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-4

Files changed (1) hide show

config.json +6 -4

config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "microsoft/Phi-3.5-MoE-instruct",
   "architectures": [
     "PhiMoEForCausalLM"
   ],
@@ -10,6 +9,7 @@
     "AutoModelForCausalLM": "modeling_phimoe.PhiMoEForCausalLM"
   },
   "bos_token_id": 1,
   "eos_token_id": 32000,
   "hidden_act": "silu",
   "hidden_dropout": 0.0,
@@ -27,14 +27,17 @@
   "num_local_experts": 16,
   "original_max_position_embeddings": 4096,
   "output_router_logits": false,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": {
     "long_factor": [
       1.0299,
       1.0499
     ],
     "long_mscale": 1.243163121016122,
     "original_max_position_embeddings": 4096,
     "short_factor": [
       1.05,
       1.05
@@ -47,8 +50,7 @@
   "router_jitter_noise": 0.01,
   "sliding_window": 131072,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 32064
 }

 {
   "architectures": [
     "PhiMoEForCausalLM"
   ],
     "AutoModelForCausalLM": "modeling_phimoe.PhiMoEForCausalLM"
   },
   "bos_token_id": 1,
+  "dtype": "bfloat16",
   "eos_token_id": 32000,
   "hidden_act": "silu",
   "hidden_dropout": 0.0,
   "num_local_experts": 16,
   "original_max_position_embeddings": 4096,
   "output_router_logits": false,
+  "pad_token_id": null,
   "rms_norm_eps": 1e-05,
+  "rope_parameters": {
     "long_factor": [
       1.0299,
       1.0499
     ],
     "long_mscale": 1.243163121016122,
     "original_max_position_embeddings": 4096,
+    "rope_theta": 10000.0,
+    "rope_type": "longrope",
     "short_factor": [
       1.05,
       1.05
   "router_jitter_noise": 0.01,
   "sliding_window": 131072,
   "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
   "use_cache": true,
   "vocab_size": 32064
 }