Instructions to use lerverson/LycheeMemory-7B-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lerverson/LycheeMemory-7B-RL with Transformers:

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

pipe = pipeline("text-generation", model="lerverson/LycheeMemory-7B-RL", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lerverson/LycheeMemory-7B-RL", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("lerverson/LycheeMemory-7B-RL", trust_remote_code=True)
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 lerverson/LycheeMemory-7B-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lerverson/LycheeMemory-7B-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lerverson/LycheeMemory-7B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lerverson/LycheeMemory-7B-RL

SGLang

How to use lerverson/LycheeMemory-7B-RL 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 "lerverson/LycheeMemory-7B-RL" \
    --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": "lerverson/LycheeMemory-7B-RL",
		"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 "lerverson/LycheeMemory-7B-RL" \
        --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": "lerverson/LycheeMemory-7B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lerverson/LycheeMemory-7B-RL with Docker Model Runner:
```
docker model run hf.co/lerverson/LycheeMemory-7B-RL
```

LycheeMemory-7B-RL / config.json

lerverson

Upload Qwen2ForCausalLM

62d6eef verified 4 months ago

raw

history blame contribute delete

1.17 kB

	{
	"architectures": [
	"Qwen2ForCausalLM"
	],
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_qwen2.Qwen2Config",
	"AutoModelForCausalLM": "modeling_qwen2.Qwen2ForCausalLM"
	},
	"beacon_attend_prev": true,
	"beacon_attn": "full-coverage",
	"beacon_embed_init": "eos",
	"beacon_parallel_window": 1,
	"beacon_param": [
	"q",
	"k",
	"v"
	],
	"beacon_pos": "interleave",
	"beacon_ratio": [
	4
	],
	"beacon_ratio_mix": "adapt-1024",
	"beacon_sink_size": 0,
	"beacon_stride": 2048,
	"beacon_window": 2048,
	"bos_token_id": 151643,
	"eos_token_id": 151645,
	"hidden_act": "silu",
	"hidden_size": 3584,
	"initializer_range": 0.02,
	"intermediate_size": 18944,
	"max_position_embeddings": 32768,
	"max_window_layers": 28,
	"model_type": "qwen2",
	"num_attention_heads": 28,
	"num_hidden_layers": 28,
	"num_key_value_heads": 4,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 1000000.0,
	"sliding_window": 131072,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.53.0",
	"use_cache": true,
	"use_sliding_window": false,
	"vocab_size": 152064
	}