Instructions to use SparseLLM/ReluFalcon-40B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SparseLLM/ReluFalcon-40B with Transformers:

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

pipe = pipeline("text-generation", model="SparseLLM/ReluFalcon-40B", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SparseLLM/ReluFalcon-40B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("SparseLLM/ReluFalcon-40B", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SparseLLM/ReluFalcon-40B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SparseLLM/ReluFalcon-40B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SparseLLM/ReluFalcon-40B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SparseLLM/ReluFalcon-40B

SGLang

How to use SparseLLM/ReluFalcon-40B 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 "SparseLLM/ReluFalcon-40B" \
    --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": "SparseLLM/ReluFalcon-40B",
		"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 "SparseLLM/ReluFalcon-40B" \
        --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": "SparseLLM/ReluFalcon-40B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SparseLLM/ReluFalcon-40B with Docker Model Runner:
```
docker model run hf.co/SparseLLM/ReluFalcon-40B
```

ReluFalcon-40B / config.json

yixinsong

test

6723d12 over 2 years ago

raw

history blame contribute delete

1.23 kB

	{
	"_name_or_path": "/mnt/hwfile/share_data/songyixin/hf/huggingface/falcon-relu",
	"alibi": false,
	"apply_residual_connection_post_layernorm": false,
	"architectures": [
	"FalconForCausalLM"
	],
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_falcon.FalconConfig",
	"AutoModel": "modeling_falcon.FalconModel",
	"AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
	"AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
	"AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
	"AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
	},
	"bias": false,
	"bos_token_id": 11,
	"eos_token_id": 11,
	"hidden_dropout": 0.0,
	"hidden_size": 8192,
	"initializer_range": 0.02,
	"layer_norm_epsilon": 1e-05,
	"model_type": "falcon",
	"multi_query": true,
	"new_decoder_architecture": true,
	"num_attention_heads": 128,
	"num_hidden_layers": 60,
	"num_kv_heads": 8,
	"parallel_attn": true,
	"torch_dtype": "float32",
	"transformers_version": "4.33.2",
	"use_cache": true,
	"vocab_size": 65024
	}