Instructions to use Litzy619/V0224O2_merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Litzy619/V0224O2_merged with Transformers:

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

pipe = pipeline("text-generation", model="Litzy619/V0224O2_merged")

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

tokenizer = AutoTokenizer.from_pretrained("Litzy619/V0224O2_merged")
model = AutoModelForCausalLM.from_pretrained("Litzy619/V0224O2_merged", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Litzy619/V0224O2_merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Litzy619/V0224O2_merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Litzy619/V0224O2_merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Litzy619/V0224O2_merged

SGLang

How to use Litzy619/V0224O2_merged 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 "Litzy619/V0224O2_merged" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Litzy619/V0224O2_merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Litzy619/V0224O2_merged" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Litzy619/V0224O2_merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Litzy619/V0224O2_merged with Docker Model Runner:
```
docker model run hf.co/Litzy619/V0224O2_merged
```

V0224O2_merged

File size: 908 Bytes

76617c8

{
  "adaptive_ratio": 1.0,
  "adaptive_ratio_decay": 1.0,
  "auto_mapping": null,
  "base_model_name_or_path": "yahma/llama-7b-hf",
  "bias": "none",
  "dynamic_adapter_pool": false,
  "enable_lora": null,
  "encoder_hidden_size": 4096,
  "fan_in_fan_out": false,
  "inference_mode": true,
  "input_based_adapter_selection": false,
  "lora_alpha": 16,
  "lora_dropout": 0.05,
  "merge_weights": false,
  "modules_to_save": null,
  "num_attention_heads": 32,
  "num_layers": 32,
  "num_prefix_set": 8,
  "num_transformer_submodules": 1,
  "num_virtual_tokens": 30,
  "number_of_adapter_pre_layer": 8,
  "ot_diversified_dispatcher": false,
  "peft_type": "PREFIX_MA_LORA",
  "pool_selective_inference": true,
  "pool_selective_training": true,
  "prefix_projection": false,
  "r": 16,
  "selective_num": 8,
  "target_modules": [
    "q_proj",
    "v_proj"
  ],
  "task_type": "CAUSAL_LM",
  "token_dim": 4096
}