Instructions to use mlfoundations-dev/hero_run_2_fix_conversations with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlfoundations-dev/hero_run_2_fix_conversations with Transformers:

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

pipe = pipeline("text-generation", model="mlfoundations-dev/hero_run_2_fix_conversations")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlfoundations-dev/hero_run_2_fix_conversations")
model = AutoModelForCausalLM.from_pretrained("mlfoundations-dev/hero_run_2_fix_conversations")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mlfoundations-dev/hero_run_2_fix_conversations with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlfoundations-dev/hero_run_2_fix_conversations"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlfoundations-dev/hero_run_2_fix_conversations",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlfoundations-dev/hero_run_2_fix_conversations

SGLang

How to use mlfoundations-dev/hero_run_2_fix_conversations 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 "mlfoundations-dev/hero_run_2_fix_conversations" \
    --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": "mlfoundations-dev/hero_run_2_fix_conversations",
		"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 "mlfoundations-dev/hero_run_2_fix_conversations" \
        --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": "mlfoundations-dev/hero_run_2_fix_conversations",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mlfoundations-dev/hero_run_2_fix_conversations with Docker Model Runner:
```
docker model run hf.co/mlfoundations-dev/hero_run_2_fix_conversations
```

sedrickkeh commited on Mar 17, 2025

Commit

bedb0bc

verified ·

1 Parent(s): d988d6d

Upload configs.yaml with huggingface_hub

Browse files

Files changed (1) hide show

configs.yaml +41 -0

configs.yaml ADDED Viewed

	@@ -0,0 +1,41 @@

+assistant_tag: assistant
+bf16: 'True'
+content_tag: value
+cutoff_len: '16384'
+dataloader_num_workers: '4'
+dataloader_persistent_workers: 'True'
+dataloader_pin_memory: 'True'
+dataset: mlfoundations-dev/hero_run_2_fix_conversations
+dataset_dir: ONLINE
+ddp_timeout: '180000000'
+deepspeed: /opt/ml/code/zero3.json
+do_train: 'True'
+enable_liger_kernel: 'True'
+finetuning_type: full
+formatting: sharegpt
+global_batch_size: '512'
+gradient_accumulation_steps: '2'
+hub_model_id: mlfoundations-dev/hero_run_2_fix_conversations
+learning_rate: 8e-05
+logging_steps: '1'
+lr_scheduler_type: cosine
+messages: conversations
+model_name_or_path: Qwen/Qwen2.5-7B-Instruct
+neat_packing: 'True'
+num_train_epochs: '5.0'
+output_dir: /opt/ml/model
+overwrite_cache: 'True'
+packing: 'True'
+per_device_train_batch_size: '1'
+plot_loss: 'True'
+preprocessing_num_workers: '16'
+push_to_db: 'True'
+push_to_hub: 'True'
+report_to: wandb
+role_tag: from
+run_name: hero_run_2_fix_conversations
+save_strategy: epoch
+stage: sft
+template: qwen25
+user_tag: user
+warmup_ratio: '0.1'