Instructions to use fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym with Transformers:

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

pipe = pipeline("text-generation", model="fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym")
model = AutoModelForMultimodalLM.from_pretrained("fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym

SGLang

How to use fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym 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 "fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym" \
    --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": "fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym",
		"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 "fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym" \
        --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": "fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym with Docker Model Runner:
```
docker model run hf.co/fbaldassarri/tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym
```

tiiuae_Falcon3-7B-Base-autogptq-int4-gs128-sym / config.json

fbaldassarri

Initial Upload

c27e9da verified over 1 year ago

Raw

History Blame Contribute Delete

1.36 kB

	{
	"_name_or_path": "tiiuae/Falcon3-7B-Base",
	"architectures": [
	"LlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"eos_token_id": 11,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"initializer_range": 0.02,
	"intermediate_size": 23040,
	"max_position_embeddings": 32768,
	"mlp_bias": false,
	"model_type": "llama",
	"num_attention_heads": 12,
	"num_hidden_layers": 28,
	"num_key_value_heads": 4,
	"pretraining_tp": 1,
	"quantization_config": {
	"amp": false,
	"autoround_version": "0.4.4",
	"batch_size": 4,
	"bits": 4,
	"damp_percent": 0.01,
	"data_type": "int",
	"desc_act": false,
	"enable_minmax_tuning": true,
	"enable_norm_bias_tuning": false,
	"enable_quanted_input": true,
	"gradient_accumulate_steps": 1,
	"group_size": 128,
	"iters": 200,
	"low_gpu_mem_usage": false,
	"lr": 0.005,
	"minmax_lr": 0.005,
	"nsamples": 128,
	"quant_method": "gptq",
	"scale_dtype": "torch.float16",
	"seqlen": 512,
	"sym": true,
	"to_quant_block_names": null,
	"true_sequential": false
	},
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 1000042,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.48.1",
	"use_cache": true,
	"vocab_size": 131072
	}