Instructions to use JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("./Qwen2.5-Coder-7B")
model = PeftModel.from_pretrained(base_model, "JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2")

Transformers

How to use JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2 with Transformers:

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

pipe = pipeline("text-generation", model="JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2

SGLang

How to use JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2 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 "JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2" \
    --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": "JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2",
		"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 "JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2" \
        --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": "JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2 with Docker Model Runner:
```
docker model run hf.co/JinNian0072/Qwen2.5-Coder-7B-lora-java-abdiff-v2
```

Qwen2.5-Coder-7B-lora-java-abdiff-v2 / checkpoint-244 /trainer_state.json

JinNian0072

Upload folder using huggingface_hub

b430a80 verified 7 months ago

Raw

History Blame Contribute Delete

5.2 kB

	{
	"best_global_step": 244,
	"best_metric": 0.241361603140831,
	"best_model_checkpoint": "lora_qwen7b_java_abdiff_v2/checkpoint-244",
	"epoch": 1.0,
	"eval_steps": 500,
	"global_step": 244,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.041109969167523124,
	"grad_norm": 0.17571452260017395,
	"learning_rate": 3.648648648648649e-06,
	"loss": 0.5537,
	"step": 10
	},
	{
	"epoch": 0.08221993833504625,
	"grad_norm": 0.12462153285741806,
	"learning_rate": 7.702702702702703e-06,
	"loss": 0.5427,
	"step": 20
	},
	{
	"epoch": 0.12332990750256938,
	"grad_norm": 0.13460873067378998,
	"learning_rate": 1.1756756756756757e-05,
	"loss": 0.5255,
	"step": 30
	},
	{
	"epoch": 0.1644398766700925,
	"grad_norm": 0.2371131032705307,
	"learning_rate": 1.5810810810810808e-05,
	"loss": 0.4849,
	"step": 40
	},
	{
	"epoch": 0.20554984583761562,
	"grad_norm": 0.2611907720565796,
	"learning_rate": 1.9864864864864866e-05,
	"loss": 0.3981,
	"step": 50
	},
	{
	"epoch": 0.24665981500513876,
	"grad_norm": 0.10762301832437515,
	"learning_rate": 2.3918918918918917e-05,
	"loss": 0.3275,
	"step": 60
	},
	{
	"epoch": 0.28776978417266186,
	"grad_norm": 0.06910783052444458,
	"learning_rate": 2.7972972972972975e-05,
	"loss": 0.2976,
	"step": 70
	},
	{
	"epoch": 0.328879753340185,
	"grad_norm": 0.10020674765110016,
	"learning_rate": 2.9772036474164135e-05,
	"loss": 0.2958,
	"step": 80
	},
	{
	"epoch": 0.3699897225077081,
	"grad_norm": 0.06338030099868774,
	"learning_rate": 2.9316109422492404e-05,
	"loss": 0.2775,
	"step": 90
	},
	{
	"epoch": 0.41109969167523125,
	"grad_norm": 0.06356582045555115,
	"learning_rate": 2.886018237082067e-05,
	"loss": 0.2671,
	"step": 100
	},
	{
	"epoch": 0.4522096608427544,
	"grad_norm": 0.06176166608929634,
	"learning_rate": 2.8404255319148935e-05,
	"loss": 0.273,
	"step": 110
	},
	{
	"epoch": 0.4933196300102775,
	"grad_norm": 0.0641980841755867,
	"learning_rate": 2.7948328267477204e-05,
	"loss": 0.2708,
	"step": 120
	},
	{
	"epoch": 0.5344295991778006,
	"grad_norm": 0.060578711330890656,
	"learning_rate": 2.7492401215805473e-05,
	"loss": 0.2492,
	"step": 130
	},
	{
	"epoch": 0.5755395683453237,
	"grad_norm": 0.07500634342432022,
	"learning_rate": 2.7036474164133738e-05,
	"loss": 0.2516,
	"step": 140
	},
	{
	"epoch": 0.6166495375128469,
	"grad_norm": 0.06346568465232849,
	"learning_rate": 2.6580547112462007e-05,
	"loss": 0.2423,
	"step": 150
	},
	{
	"epoch": 0.65775950668037,
	"grad_norm": 0.214496448636055,
	"learning_rate": 2.6124620060790272e-05,
	"loss": 0.245,
	"step": 160
	},
	{
	"epoch": 0.6988694758478932,
	"grad_norm": 0.07425080984830856,
	"learning_rate": 2.566869300911854e-05,
	"loss": 0.2455,
	"step": 170
	},
	{
	"epoch": 0.7399794450154162,
	"grad_norm": 0.08862721920013428,
	"learning_rate": 2.521276595744681e-05,
	"loss": 0.2377,
	"step": 180
	},
	{
	"epoch": 0.7810894141829393,
	"grad_norm": 0.09345080703496933,
	"learning_rate": 2.4756838905775076e-05,
	"loss": 0.2493,
	"step": 190
	},
	{
	"epoch": 0.8221993833504625,
	"grad_norm": 0.12085441499948502,
	"learning_rate": 2.4300911854103345e-05,
	"loss": 0.243,
	"step": 200
	},
	{
	"epoch": 0.8633093525179856,
	"grad_norm": 0.09944415092468262,
	"learning_rate": 2.3844984802431613e-05,
	"loss": 0.2276,
	"step": 210
	},
	{
	"epoch": 0.9044193216855088,
	"grad_norm": 0.11600342392921448,
	"learning_rate": 2.338905775075988e-05,
	"loss": 0.2288,
	"step": 220
	},
	{
	"epoch": 0.9455292908530318,
	"grad_norm": 0.11351948231458664,
	"learning_rate": 2.2933130699088144e-05,
	"loss": 0.2136,
	"step": 230
	},
	{
	"epoch": 0.986639260020555,
	"grad_norm": 0.12985852360725403,
	"learning_rate": 2.2477203647416413e-05,
	"loss": 0.2166,
	"step": 240
	},
	{
	"epoch": 1.0,
	"eval_loss": 0.241361603140831,
	"eval_runtime": 48.3711,
	"eval_samples_per_second": 13.479,
	"eval_steps_per_second": 3.37,
	"step": 244
	}
	],
	"logging_steps": 10,
	"max_steps": 732,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 3,
	"save_steps": 500,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": false
	},
	"attributes": {}
	}
	},
	"total_flos": 3.369854600141783e+17,
	"train_batch_size": 4,
	"trial_name": null,
	"trial_params": null
	}