Instructions to use Xwin-LM/Xwin-Math-70B-V1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xwin-LM/Xwin-Math-70B-V1.1 with Transformers:

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

pipe = pipeline("text-generation", model="Xwin-LM/Xwin-Math-70B-V1.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-Math-70B-V1.1")
model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-Math-70B-V1.1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Xwin-LM/Xwin-Math-70B-V1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xwin-LM/Xwin-Math-70B-V1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xwin-LM/Xwin-Math-70B-V1.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Xwin-LM/Xwin-Math-70B-V1.1

SGLang

How to use Xwin-LM/Xwin-Math-70B-V1.1 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 "Xwin-LM/Xwin-Math-70B-V1.1" \
    --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": "Xwin-LM/Xwin-Math-70B-V1.1",
		"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 "Xwin-LM/Xwin-Math-70B-V1.1" \
        --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": "Xwin-LM/Xwin-Math-70B-V1.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Xwin-LM/Xwin-Math-70B-V1.1 with Docker Model Runner:
```
docker model run hf.co/Xwin-LM/Xwin-Math-70B-V1.1
```

Xwin-Math-70B-V1.1 / config.json

LC-Edward

Update Xwin-Math-70B-V1.1

0848330 about 2 years ago

raw

history blame contribute delete

634 Bytes

	{
	"_name_or_path": "/data/mnt/chen_llm/Llama-2-70b-hf",
	"architectures": [
	"LlamaForCausalLM"
	],
	"bos_token_id": 1,
	"eos_token_id": 2,
	"hidden_act": "silu",
	"hidden_size": 8192,
	"initializer_range": 0.02,
	"intermediate_size": 28672,
	"max_position_embeddings": 4096,
	"model_type": "llama",
	"num_attention_heads": 64,
	"num_hidden_layers": 80,
	"num_key_value_heads": 8,
	"pad_token_id": 0,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.28.1",
	"use_cache": false,
	"vocab_size": 32001
	}