Instructions to use Vilyam888/Code_analyze.1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vilyam888/Code_analyze.1.0 with Transformers:

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

pipe = pipeline("text-generation", model="Vilyam888/Code_analyze.1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vilyam888/Code_analyze.1.0")
model = AutoModelForCausalLM.from_pretrained("Vilyam888/Code_analyze.1.0", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Vilyam888/Code_analyze.1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vilyam888/Code_analyze.1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vilyam888/Code_analyze.1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Vilyam888/Code_analyze.1.0

SGLang

How to use Vilyam888/Code_analyze.1.0 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 "Vilyam888/Code_analyze.1.0" \
    --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": "Vilyam888/Code_analyze.1.0",
		"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 "Vilyam888/Code_analyze.1.0" \
        --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": "Vilyam888/Code_analyze.1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Vilyam888/Code_analyze.1.0 with Docker Model Runner:
```
docker model run hf.co/Vilyam888/Code_analyze.1.0
```

Vilyam888 commited on Jun 10

Commit

ee96e41

1 Parent(s): 3ebde78

metrics обновил, финал

Browse files

Files changed (2) hide show

metrics/README.md +1 -1
metrics/evaluation_report.json +0 -1

metrics/README.md CHANGED Viewed

@@ -10,7 +10,7 @@
 | Метод дообучения | LoRA (без 4-bit квантизации), 2 эпохи, checkpoint-222 |
 | Инференс | bfloat16, merged-модель |
 | Тестовая выборка | `prepared_data/code_analyze/test.jsonl`, N = 100 |
-| Эталон | Поля JSON из test split |
 | Temperature | 0.2 |
 | max_new_tokens | 2048 |

 | Метод дообучения | LoRA (без 4-bit квантизации), 2 эпохи, checkpoint-222 |
 | Инференс | bfloat16, merged-модель |
 | Тестовая выборка | `prepared_data/code_analyze/test.jsonl`, N = 100 |
+| Reference | Поля JSON из test split |
 | Temperature | 0.2 |
 | max_new_tokens | 2048 |

metrics/evaluation_report.json CHANGED Viewed

@@ -13,7 +13,6 @@
     "temperature": 0.2,
     "max_new_tokens": 2048
   },
-  "metrics_output_dir": "C:\\Users\\User\\Desktop\\Предитог по диплому\\outputs\\metrics\\code_analyze",
   "training": {
     "train_loss_final": 0.241,
     "eval_loss_final": 0.2776,

     "temperature": 0.2,
     "max_new_tokens": 2048
   },
   "training": {
     "train_loss_final": 0.241,
     "eval_loss_final": 0.2776,