Instructions to use haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct")

Transformers

How to use haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct

SGLang

How to use haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct 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 "haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct" \
    --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": "haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct",
		"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 "haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct" \
        --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": "haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/haihp02/dicplau14_Qwen_Qwen2.5-3B-Instruct
```

dicplau14_Qwen_Qwen2.5-3B-Instruct / trainer_state.json

haihp02

Upload task output 1

7b1ce17 verified about 18 hours ago

raw

history blame contribute delete

2.55 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 0.24647887323943662,
	"eval_steps": 500,
	"global_step": 35,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.035211267605633804,
	"grad_norm": 4.435381889343262,
	"learning_rate": 8.401166180758017e-06,
	"loss": 0.3742,
	"mean_token_accuracy": 0.8945995926856994,
	"num_tokens": 301695.0,
	"step": 5
	},
	{
	"epoch": 0.07042253521126761,
	"grad_norm": 1.0536936521530151,
	"learning_rate": 1.8902623906705538e-05,
	"loss": 0.2437,
	"mean_token_accuracy": 0.9109556913375855,
	"num_tokens": 607230.0,
	"step": 10
	},
	{
	"epoch": 0.1056338028169014,
	"grad_norm": 0.8927873373031616,
	"learning_rate": 2.9404081632653062e-05,
	"loss": 0.201,
	"mean_token_accuracy": 0.9295879244804383,
	"num_tokens": 913896.0,
	"step": 15
	},
	{
	"epoch": 0.14084507042253522,
	"grad_norm": 0.6603397130966187,
	"learning_rate": 3.990553935860058e-05,
	"loss": 0.1947,
	"mean_token_accuracy": 0.9296464204788208,
	"num_tokens": 1234009.0,
	"step": 20
	},
	{
	"epoch": 0.176056338028169,
	"grad_norm": 0.5713601112365723,
	"learning_rate": 5.0406997084548104e-05,
	"loss": 0.1712,
	"mean_token_accuracy": 0.9373371362686157,
	"num_tokens": 1536066.0,
	"step": 25
	},
	{
	"epoch": 0.2112676056338028,
	"grad_norm": 0.6312325596809387,
	"learning_rate": 6.090845481049563e-05,
	"loss": 0.1683,
	"mean_token_accuracy": 0.9364290118217469,
	"num_tokens": 1854154.0,
	"step": 30
	},
	{
	"epoch": 0.24647887323943662,
	"grad_norm": 1.2735894918441772,
	"learning_rate": 7.140991253644314e-05,
	"loss": 0.1312,
	"mean_token_accuracy": 0.9548299431800842,
	"num_tokens": 2160408.0,
	"step": 35
	}
	],
	"logging_steps": 5,
	"max_steps": 142,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 1,
	"save_steps": 500,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": true
	},
	"attributes": {}
	}
	},
	"total_flos": 5.105089563623424e+16,
	"train_batch_size": 24,
	"trial_name": null,
	"trial_params": null
	}