Instructions to use chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110 with Transformers:

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

pipe = pipeline("text-generation", model="chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110")
model = AutoModelForCausalLM.from_pretrained("chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110", device_map="auto")
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 chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110

SGLang

How to use chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110 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 "chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110" \
    --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": "chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110",
		"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 "chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110" \
        --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": "chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110 with Docker Model Runner:
```
docker model run hf.co/chanyoungkim/strata-qwen2.5-1.5b-alfworld-step110
```

chanyoungkim commited on 3 days ago

Commit

4946eef

verified ·

1 Parent(s): 17f5556

Add FSDP training state (resume from this step)

Browse files

Files changed (7) hide show

training_state/extra_state_world_size_2_rank_0.pt +3 -0
training_state/extra_state_world_size_2_rank_1.pt +3 -0
training_state/fsdp_config.json +4 -0
training_state/model_world_size_2_rank_0.pt +3 -0
training_state/model_world_size_2_rank_1.pt +3 -0
training_state/optim_world_size_2_rank_0.pt +3 -0
training_state/optim_world_size_2_rank_1.pt +3 -0

training_state/extra_state_world_size_2_rank_0.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:35b2e2589e37f65788d69f4a57a6633279b7f8b4a1e93f66af49c9f50d11a11f
+size 15077

training_state/extra_state_world_size_2_rank_1.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:14344cc55609cf009b5945246ecef810aae311b1ed9dbe93c5784b7662ecaf93
+size 15077

training_state/fsdp_config.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+    "FSDP_version": 1,
+    "world_size": 2
+}

training_state/model_world_size_2_rank_0.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8b859fab15ba45582fab70d4a16f5e89b1b9d4c6ea622b291ae5ab2d1e3be37d
+size 3554364971

training_state/model_world_size_2_rank_1.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:02d9772bdbd09aa8e9b601964dee2345a05189661f38cc8858279b32b9a95d25
+size 3554364971

training_state/optim_world_size_2_rank_0.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d439a6cfe65b202c2417b2ac6d4d023805dede582418016fdb609204faaa383d
+size 6175003248

training_state/optim_world_size_2_rank_1.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5903d26fdacb195de852340de1a0ad0ab4f5c909b650324a4c915d34160f17
+size 6175003248