Instructions to use Johnblick187/SmartCoderMoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Johnblick187/SmartCoderMoE with Transformers:

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

pipe = pipeline("text-generation", model="Johnblick187/SmartCoderMoE", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Johnblick187/SmartCoderMoE", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Johnblick187/SmartCoderMoE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Johnblick187/SmartCoderMoE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Johnblick187/SmartCoderMoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Johnblick187/SmartCoderMoE

SGLang

How to use Johnblick187/SmartCoderMoE 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 "Johnblick187/SmartCoderMoE" \
    --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": "Johnblick187/SmartCoderMoE",
		"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 "Johnblick187/SmartCoderMoE" \
        --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": "Johnblick187/SmartCoderMoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Johnblick187/SmartCoderMoE with Docker Model Runner:
```
docker model run hf.co/Johnblick187/SmartCoderMoE
```

Johnblick187 commited on 10 days ago

Commit

f10d44f

verified ·

1 Parent(s): 5fc333f

Update modeling_smartcoder_moe.py

Browse files

Files changed (1) hide show

modeling_smartcoder_moe.py +14 -16

modeling_smartcoder_moe.py CHANGED Viewed

@@ -1,19 +1,17 @@
-""
-modeling_smartcoder_moe.py
-Custom model class for SmartCoderMoE.
-Architecture (from tensor inspection):
-- vocab_size: 65536, hidden: 2048, layers: 40
-- Attention: q[2048,2048], k/v[512,2048] - 16 heads, 4 KV heads, head_dim=128
-- MLP (hybrid dense + MoE):
-    dense_fc:     [8192, 2048]    up
-    dense_proj:   [2048, 8192]    down
-    experts_fc:   [32, 512, 2048] expert up (batched)
-    experts_proj: [32, 2048, 512] expert down (batched)
-    router:       [32, 2048]      router logits
-- LayerNorm: weight+bias (input_layernorm, post_attention_layernorm)
-- Final norm: model.norm.weight/bias
-""
 import math
 import torch

+# modeling_smartcoder_moe.py
+#Architecture (from tensor inspection):
+#- vocab_size: 65536, hidden: 2048, layers: 40
+#- Attention: q[2048,2048], k/v[512,2048] - 16 heads, 4 KV heads, head_dim=128
+#- MLP (hybrid dense + MoE):
+ #   dense_fc:     [8192, 2048]    up
+ #   dense_proj:   [2048, 8192]    down
+#    experts_fc:   [32, 512, 2048] expert up (batched)
+#    experts_proj: [32, 2048, 512] expert down (batched)
+ #   router:       [32, 2048]      router logits
+#- LayerNorm: weight+bias (input_layernorm, post_attention_layernorm)
+#- Final norm: model.norm.weight/bias
 import math
 import torch