Instructions to use Baedunlee/day1-train-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Baedunlee/day1-train-model with Transformers:

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

pipe = pipeline("text-generation", model="Baedunlee/day1-train-model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Baedunlee/day1-train-model")
model = AutoModelForCausalLM.from_pretrained("Baedunlee/day1-train-model")
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 Baedunlee/day1-train-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Baedunlee/day1-train-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Baedunlee/day1-train-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Baedunlee/day1-train-model

SGLang

How to use Baedunlee/day1-train-model 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 "Baedunlee/day1-train-model" \
    --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": "Baedunlee/day1-train-model",
		"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 "Baedunlee/day1-train-model" \
        --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": "Baedunlee/day1-train-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Baedunlee/day1-train-model with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Baedunlee/day1-train-model to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Baedunlee/day1-train-model to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Baedunlee/day1-train-model to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Baedunlee/day1-train-model",
    max_seq_length=2048,
)

Docker Model Runner
How to use Baedunlee/day1-train-model with Docker Model Runner:
```
docker model run hf.co/Baedunlee/day1-train-model
```

Baedunlee commited on Apr 1

Commit

fff8214

verified ·

1 Parent(s): a61d575

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +1 -5
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -33,12 +33,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
-    "q_proj",
-    "v_proj",
-    "down_proj",
     "gate_proj",
     "up_proj"
   ],
   "target_parameters": null,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "down_proj",
     "up_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b7defc7ef8924dccf4829e3580cdd6614e76fa54685283c8e9be308fcf690a8
-size 35237104

 version https://git-lfs.github.com/spec/v1
+oid sha256:aa6fe4f018c3d3cfe8f450e06726bfb4b2659dfd9f9f164ecbba54d0d627b9dc
+size 26560776