Instructions to use trl-internal-testing/tiny-Qwen3MoeForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-Qwen3MoeForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-Qwen3MoeForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-Qwen3MoeForCausalLM")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-Qwen3MoeForCausalLM")
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 trl-internal-testing/tiny-Qwen3MoeForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-Qwen3MoeForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-Qwen3MoeForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trl-internal-testing/tiny-Qwen3MoeForCausalLM

SGLang

How to use trl-internal-testing/tiny-Qwen3MoeForCausalLM 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 "trl-internal-testing/tiny-Qwen3MoeForCausalLM" \
    --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": "trl-internal-testing/tiny-Qwen3MoeForCausalLM",
		"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 "trl-internal-testing/tiny-Qwen3MoeForCausalLM" \
        --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": "trl-internal-testing/tiny-Qwen3MoeForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-Qwen3MoeForCausalLM with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-Qwen3MoeForCausalLM
```

qgallouedec HF Staff commited on 20 days ago

Commit

6db5716

1 Parent(s): 3d0483f

Upload Qwen3MoeForCausalLM (#1)

Browse files

- Upload Qwen3MoeForCausalLM (2605d072ecde96362fb71461fb1b821e8e713c76)

Files changed (3) hide show

config.json +9 -5
generation_config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -4,17 +4,21 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "decoder_sparse_step": 1,
   "dtype": "bfloat16",
   "hidden_act": "silu",
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
-  "max_position_embeddings": 32768,
   "mlp_only_layers": [],
   "model_type": "qwen3_moe",
   "moe_intermediate_size": 768,
-  "norm_topk_prob": false,
   "num_attention_heads": 4,
   "num_experts": 4,
   "num_experts_per_tok": 2,
@@ -23,12 +27,12 @@
   "output_router_logits": false,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
   "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.57.3",
   "use_cache": true,
   "use_sliding_window": false,
-  "vocab_size": 151669
 }

   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "bos_token_id": 151643,
   "decoder_sparse_step": 1,
   "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 48,
   "mlp_only_layers": [],
   "model_type": "qwen3_moe",
   "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
   "num_attention_heads": 4,
   "num_experts": 4,
   "num_experts_per_tok": 2,
   "output_router_logits": false,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
+  "rope_theta": 1000000.0,
   "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
   "use_cache": true,
   "use_sliding_window": false,
+  "vocab_size": 151936
 }

generation_config.json CHANGED Viewed

@@ -9,5 +9,5 @@
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "4.57.3"
 }

   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
+  "transformers_version": "4.56.2"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534e5c6470745f8b02bfdf11e09f60ba192fc38ecb267d54e6eac98a7409f5bb
-size 5154208

 version https://git-lfs.github.com/spec/v1
+oid sha256:c78c2aca3c76f960f52f30c3afd9861f3c2e4928a2e8788b086836720084aad0
+size 5212168