Instructions to use jeiku/controlkto with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jeiku/controlkto with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jeiku/controlkto")
model = AutoModelForCausalLM.from_pretrained("jeiku/controlkto")
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 Settings

vLLM

How to use jeiku/controlkto with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jeiku/controlkto

SGLang

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

Docker Model Runner
How to use jeiku/controlkto with Docker Model Runner:
```
docker model run hf.co/jeiku/controlkto
```

jeiku commited on Dec 13, 2024

Commit

3f205f0

verified ·

1 Parent(s): 011a0c9

Upload controlkto.yml

Browse files

Files changed (1) hide show

controlkto.yml +90 -0

controlkto.yml ADDED Viewed

	@@ -0,0 +1,90 @@

+base_model: Delta-Vector/Control-8B-V1.1
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+hub_model_id: jeiku/controlkto
+hub_strategy: "all_checkpoints"
+push_dataset_to_hub:
+hf_use_auth_token: true
+chat_template: llama3
+rl: kto
+rl_beta: 0.2
+kto_desirable_weight: 0.2
+datasets:
+  - path: anthracite-core/full-opus-chosen-hermes-rejected-kto-v1
+    type: llama3.argilla
+shuffle_merged_datasets: true
+val_set_size: 0.0
+output_dir: ./outputs/out
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+sequence_len: 8192
+sample_packing: false
+eval_sample_packing: false
+pad_to_sequence_len: false
+wandb_project: controlkto
+wandb_entity:
+wandb_watch:
+wandb_name: controlkto
+wandb_log_model:
+gradient_accumulation_steps: 16
+micro_batch_size: 2
+num_epochs: 2
+max_steps: 500
+optimizer: adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.0001
+weight_decay: 0.05
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: true
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: true
+remove_unused_columns: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+warmup_steps: 10
+evals_per_epoch: 2
+eval_table_size:
+eval_max_new_tokens:
+saves_per_epoch: 1
+debug:
+deepspeed:
+fsdp:
+fsdp_config:
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: <|finetune_right_pad_id|>
+  eos_token: <|eot_id|>