Instructions to use Salesforce/CoDA-v0-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/CoDA-v0-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/CoDA-v0-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Salesforce/CoDA-v0-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/CoDA-v0-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/CoDA-v0-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/CoDA-v0-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Salesforce/CoDA-v0-Instruct

SGLang

How to use Salesforce/CoDA-v0-Instruct 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 "Salesforce/CoDA-v0-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/CoDA-v0-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Salesforce/CoDA-v0-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/CoDA-v0-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Salesforce/CoDA-v0-Instruct with Docker Model Runner:
```
docker model run hf.co/Salesforce/CoDA-v0-Instruct
```

CoDA-v0-Instruct / config.json

hlnchen

update model

ccf7c47 verified 8 months ago

raw

history blame

1.13 kB

	{
	"architectures": [
	"CoDALanguageModel"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_kernel": "flash_attention",
	"auto_map": {
	"AutoConfig": "model_config.CoDAConfig",
	"AutoModel": "modeling_coda.CoDALanguageModel"
	},
	"block_masking_probability": [
	0.25,
	0.5,
	0.5,
	0.75,
	0.25
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 6144,
	"mask_block_sizes": [
	4,
	8,
	16,
	32
	],
	"mask_token_id": 151669,
	"max_position_embeddings": 40960,
	"max_window_layers": 28,
	"model_type": "CoDA",
	"num_attention_heads": 16,
	"num_hidden_layers": 28,
	"num_key_value_heads": 8,
	"pad_token_id": 151643,
	"prefix_probability": 0,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 1000000,
	"sampling_eps": [
	0.001,
	0.25,
	0.5,
	0.25,
	0.001
	],
	"sliding_window": null,
	"torch_dtype": "float32",
	"transformers_version": "4.47.1",
	"truncate_probability": 0,
	"use_cache": true,
	"use_sliding_window": false,
	"vocab_size": 151936
	}