Instructions to use ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct")
model = PeftModel.from_pretrained(base_model, "ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1")

Transformers

How to use ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1 with Transformers:

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

pipe = pipeline("text-generation", model="ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1

SGLang

How to use ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1 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 "ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1" \
    --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": "ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1",
		"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 "ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1" \
        --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": "ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1 with Docker Model Runner:
```
docker model run hf.co/ajChakrarborty/custom-qwen2.5-32b-instruct-ft-1
```

custom-qwen2.5-32b-instruct-ft-1 / trainer_state.json

ajChakrarborty

Upload folder using huggingface_hub

971f5f8 verified 10 months ago

Raw

History Blame Contribute Delete

1.81 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 1.0,
	"eval_steps": 200,
	"global_step": 154,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.16233766233766234,
	"grad_norm": 0.45304521918296814,
	"learning_rate": 0.0001920824925271838,
	"loss": 1.3904,
	"step": 25
	},
	{
	"epoch": 0.3246753246753247,
	"grad_norm": 0.3425905406475067,
	"learning_rate": 0.00015996612118590603,
	"loss": 0.9095,
	"step": 50
	},
	{
	"epoch": 0.487012987012987,
	"grad_norm": 0.9140247106552124,
	"learning_rate": 0.00011157050914243614,
	"loss": 0.7855,
	"step": 75
	},
	{
	"epoch": 0.6493506493506493,
	"grad_norm": 0.533422589302063,
	"learning_rate": 6.0033805101491794e-05,
	"loss": 0.7284,
	"step": 100
	},
	{
	"epoch": 0.8116883116883117,
	"grad_norm": 0.6093091368675232,
	"learning_rate": 1.9346882467727325e-05,
	"loss": 0.6514,
	"step": 125
	},
	{
	"epoch": 0.974025974025974,
	"grad_norm": 0.6339468359947205,
	"learning_rate": 5.55181464516652e-07,
	"loss": 0.6881,
	"step": 150
	}
	],
	"logging_steps": 25,
	"max_steps": 154,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 1,
	"save_steps": 200,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": true
	},
	"attributes": {}
	}
	},
	"total_flos": 6.776509629689856e+16,
	"train_batch_size": 1,
	"trial_name": null,
	"trial_params": null
	}