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

Libraries

How to use flwrlabs/Lizzy-7B with Transformers:

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

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

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("flwrlabs/Lizzy-7B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use flwrlabs/Lizzy-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/flwrlabs/Lizzy-7B

SGLang

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

Docker Model Runner
How to use flwrlabs/Lizzy-7B with Docker Model Runner:
```
docker model run hf.co/flwrlabs/Lizzy-7B
```

Lizzy-7B / config.json

relogu

Initial commit

edbbb7f 26 days ago

raw

history blame contribute delete

3.84 kB

	{
	"vocab_size": 100278,
	"hidden_size": 4096,
	"intermediate_size": 11008,
	"num_hidden_layers": 32,
	"num_attention_heads": 32,
	"num_key_value_heads": 32,
	"max_position_embeddings": 32768,
	"head_dim": 128,
	"hidden_act": "silu",
	"norm_type": "rmsnorm",
	"norm_eps": 1e-06,
	"norm_has_bias": false,
	"use_pre_attn_norm": false,
	"use_pre_mlp_norm": false,
	"use_post_attn_norm": true,
	"use_post_mlp_norm": true,
	"mlp_type": "gated",
	"attention_bias": false,
	"mlp_bias": false,
	"position_embedding_type": "rope",
	"rope_theta": 500000,
	"rope_scaling": {
	"attention_factor": 1.2079441541679836,
	"beta_fast": 32,
	"beta_slow": 1,
	"factor": 8.0,
	"original_max_position_embeddings": 8192,
	"rope_type": "yarn",
	"rope_theta": 500000
	},
	"rope_layer_flags": [
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true,
	true
	],
	"no_rope_layer_interval": null,
	"rope_type_overrides": {},
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"layer_layouts": [
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm",
	"decoder_postnorm"
	],
	"sliding_window": 4096,
	"linear_num_key_heads": null,
	"linear_num_value_heads": null,
	"linear_key_head_dim": null,
	"linear_value_head_dim": null,
	"linear_a_log_min": null,
	"linear_a_log_max": null,
	"linear_dt_min": null,
	"linear_dt_max": null,
	"linear_dt_init_floor": null,
	"linear_conv_kernel_dim": null,
	"linear_allow_neg_eigval": null,
	"use_qk_norm": true,
	"qk_norm_type": "rmsnorm",
	"attention_dropout": 0.0,
	"resid_dropout": 0.0,
	"embd_dropout": 0.0,
	"initializer_range": 0.02,
	"bos_token_id": 100257,
	"eos_token_id": 100257,
	"pad_token_id": 100277,
	"use_cache": true,
	"tie_word_embeddings": false,
	"model_type": "lizzy",
	"architectures": [
	"LizzyForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_lizzy.LizzyConfig",
	"AutoModel": "modeling_lizzy.LizzyModel",
	"AutoModelForCausalLM": "modeling_lizzy.LizzyForCausalLM",
	"AutoTokenizer": "tokenization_lizzy.LizzyTokenizerFast"
	},
	"tokenizer_class": "LizzyTokenizerFast",
	"transformers_version": "5.4.0"
	}