Instructions to use alielfilali01/jais-13b-chat-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alielfilali01/jais-13b-chat-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="alielfilali01/jais-13b-chat-GPTQ", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("alielfilali01/jais-13b-chat-GPTQ", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alielfilali01/jais-13b-chat-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alielfilali01/jais-13b-chat-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alielfilali01/jais-13b-chat-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alielfilali01/jais-13b-chat-GPTQ

SGLang

How to use alielfilali01/jais-13b-chat-GPTQ 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 "alielfilali01/jais-13b-chat-GPTQ" \
    --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": "alielfilali01/jais-13b-chat-GPTQ",
		"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 "alielfilali01/jais-13b-chat-GPTQ" \
        --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": "alielfilali01/jais-13b-chat-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alielfilali01/jais-13b-chat-GPTQ with Docker Model Runner:
```
docker model run hf.co/alielfilali01/jais-13b-chat-GPTQ
```

jais-13b-chat-GPTQ / config.json

Ali-C137

Upload folder using huggingface_hub

85f986c verified over 2 years ago

Raw History Blame

1.94 kB

	{
	"_name_or_path": "core42/jais-13b-chat",
	"activation_function": "swiglu",
	"architectures": [
	"JAISLMHeadModel"
	],
	"attn_pdrop": 0.0,
	"auto_map": {
	"AutoConfig": "core42/jais-13b-chat--configuration_jais.JAISConfig",
	"AutoModel": "core42/jais-13b-chat--modeling_jais.JAISModel",
	"AutoModelForCausalLM": "core42/jais-13b-chat--modeling_jais.JAISLMHeadModel",
	"AutoModelForQuestionAnswering": "core42/jais-13b-chat--modeling_jais.JAISForQuestionAnswering",
	"AutoModelForSequenceClassification": "core42/jais-13b-chat--modeling_jais.JAISForSequenceClassification",
	"AutoModelForTokenClassification": "core42/jais-13b-chat--modeling_jais.JAISForTokenClassification"
	},
	"bos_token_id": 0,
	"embd_pdrop": 0.0,
	"embeddings_scale": 14.6,
	"eos_token_id": 0,
	"initializer_range": 0.02,
	"layer_norm_epsilon": 1e-05,
	"model_type": "jais",
	"n_embd": 5120,
	"n_head": 40,
	"n_inner": 13653,
	"n_layer": 40,
	"n_positions": 2048,
	"pad_token_id": 0,
	"position_embedding_type": "alibi",
	"quantization_config": {
	"batch_size": 1,
	"bits": 4,
	"block_name_to_quantize": null,
	"cache_block_outputs": true,
	"damp_percent": 0.1,
	"dataset": "c4",
	"desc_act": false,
	"exllama_config": {
	"version": 1
	},
	"group_size": 128,
	"max_input_length": null,
	"model_seqlen": null,
	"module_name_preceding_first_block": null,
	"modules_in_block_to_quantize": null,
	"pad_token_id": null,
	"quant_method": "gptq",
	"sym": true,
	"tokenizer": null,
	"true_sequential": true,
	"use_cuda_fp16": false,
	"use_exllama": true
	},
	"reorder_and_upcast_attn": false,
	"resid_pdrop": 0.0,
	"scale_attn_by_inverse_layer_idx": false,
	"scale_attn_weights": true,
	"scale_qk_dot_by_d": true,
	"torch_dtype": "float16",
	"transformers_version": "4.39.3",
	"use_cache": true,
	"vocab_size": 84992,
	"width_scale": 0.11100000000000002
	}