Instructions to use tiiuae/Falcon-H1-7B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/Falcon-H1-7B-Base with Transformers:

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

pipe = pipeline("text-generation", model="tiiuae/Falcon-H1-7B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon-H1-7B-Base")
model = AutoModelForCausalLM.from_pretrained("tiiuae/Falcon-H1-7B-Base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiiuae/Falcon-H1-7B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/Falcon-H1-7B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiiuae/Falcon-H1-7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tiiuae/Falcon-H1-7B-Base

SGLang

How to use tiiuae/Falcon-H1-7B-Base 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 "tiiuae/Falcon-H1-7B-Base" \
    --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": "tiiuae/Falcon-H1-7B-Base",
		"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 "tiiuae/Falcon-H1-7B-Base" \
        --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": "tiiuae/Falcon-H1-7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tiiuae/Falcon-H1-7B-Base with Docker Model Runner:
```
docker model run hf.co/tiiuae/Falcon-H1-7B-Base
```

Falcon-H1-7B-Base / config.json

ybelkada

Upload folder using huggingface_hub

438e970 verified over 1 year ago

Raw History Blame Contribute Delete

1.64 kB

	{
	"architectures": [
	"FalconH1ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_in_multiplier": 1.0,
	"attention_out_multiplier": 0.10416666666666669,
	"attn_layer_indices": null,
	"bos_token_id": 1,
	"embedding_multiplier": 5.656854249492381,
	"eos_token_id": 11,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"key_multiplier": 0.030690398488999456,
	"lm_head_multiplier": 0.013020833333333334,
	"mamba_chunk_size": 128,
	"mamba_conv_bias": true,
	"mamba_d_conv": 4,
	"mamba_d_head": 128,
	"mamba_d_ssm": 3072,
	"mamba_d_state": 256,
	"mamba_expand": 2,
	"mamba_n_groups": 1,
	"mamba_n_heads": 24,
	"mamba_norm_before_gate": false,
	"mamba_proj_bias": false,
	"mamba_rms_norm": true,
	"mamba_use_mlp": true,
	"max_position_embeddings": 262144,
	"mlp_bias": false,
	"mlp_expansion_factor": 8,
	"mlp_multipliers": [
	0.2946278254943948,
	0.032552083333333336
	],
	"model_type": "falcon_h1",
	"num_attention_heads": 12,
	"num_hidden_layers": 44,
	"num_key_value_heads": 2,
	"num_logits_to_keep": 1,
	"pad_token_id": 0,
	"projectors_bias": false,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 100000000000,
	"ssm_in_multiplier": 0.4166666666666667,
	"ssm_multipliers": [
	0.3535533905932738,
	0.25,
	0.1767766952966369,
	0.5,
	0.3535533905932738
	],
	"ssm_out_multiplier": 0.11785113019775792,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.52.0.dev0",
	"use_cache": true,
	"vocab_size": 130048
	}