Instructions to use finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Coder-30B-A3B-Instruct")
model = PeftModel.from_pretrained(base_model, "finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct")

Transformers

How to use finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "finalform/parse_case_info_Qwen3-Coder-30B-A3B-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": "finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct

SGLang

How to use finalform/parse_case_info_Qwen3-Coder-30B-A3B-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 "finalform/parse_case_info_Qwen3-Coder-30B-A3B-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": "finalform/parse_case_info_Qwen3-Coder-30B-A3B-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 "finalform/parse_case_info_Qwen3-Coder-30B-A3B-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": "finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct with Docker Model Runner:
```
docker model run hf.co/finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct
```

parse_case_info_Qwen3-Coder-30B-A3B-Instruct / trainer_state.json

finalform

Upload folder using huggingface_hub

1760113 verified about 1 month ago

raw

history blame contribute delete

2.38 kB

	{
	"best_global_step": 10,
	"best_metric": 0.021615855395793915,
	"best_model_checkpoint": "parse_case_info_results/checkpoint-10",
	"epoch": 3.0,
	"eval_steps": 10,
	"global_step": 15,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.4,
	"grad_norm": 3.3258415268532477,
	"learning_rate": 0.0004,
	"loss": 2.2642,
	"step": 2
	},
	{
	"epoch": 0.8,
	"grad_norm": 0.6606166446051005,
	"learning_rate": 0.00036923076923076927,
	"loss": 1.2579,
	"step": 4
	},
	{
	"epoch": 1.2,
	"grad_norm": 0.4470053715491355,
	"learning_rate": 0.0003076923076923077,
	"loss": 0.1933,
	"step": 6
	},
	{
	"epoch": 1.6,
	"grad_norm": 0.12926230379917952,
	"learning_rate": 0.0002461538461538462,
	"loss": 0.092,
	"step": 8
	},
	{
	"epoch": 2.0,
	"grad_norm": 0.08825068216637612,
	"learning_rate": 0.00018461538461538463,
	"loss": 0.0332,
	"step": 10
	},
	{
	"epoch": 2.0,
	"eval_accuracy": 0.9984122983870968,
	"eval_loss": 0.021615855395793915,
	"eval_runtime": 80.3039,
	"eval_samples_per_second": 0.411,
	"eval_steps_per_second": 0.062,
	"step": 10
	},
	{
	"epoch": 2.4,
	"grad_norm": 0.15347360858147652,
	"learning_rate": 0.0001230769230769231,
	"loss": 0.0481,
	"step": 12
	},
	{
	"epoch": 2.8,
	"grad_norm": 0.04779989072248613,
	"learning_rate": 6.153846153846155e-05,
	"loss": 0.0139,
	"step": 14
	},
	{
	"epoch": 3.0,
	"step": 15,
	"total_flos": 2654834786304.0,
	"train_loss": 0.5213745492820938,
	"train_runtime": 1050.3606,
	"train_samples_per_second": 0.223,
	"train_steps_per_second": 0.014
	}
	],
	"logging_steps": 2,
	"max_steps": 15,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 3,
	"save_steps": 10,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": true
	},
	"attributes": {}
	}
	},
	"total_flos": 2654834786304.0,
	"train_batch_size": 4,
	"trial_name": null,
	"trial_params": null
	}