Instructions to use refactai/codify_medium_multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use refactai/codify_medium_multi with Transformers:

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

pipe = pipeline("text-generation", model="refactai/codify_medium_multi", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("refactai/codify_medium_multi", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use refactai/codify_medium_multi with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/refactai/codify_medium_multi

SGLang

How to use refactai/codify_medium_multi 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 "refactai/codify_medium_multi" \
    --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": "refactai/codify_medium_multi",
		"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 "refactai/codify_medium_multi" \
        --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": "refactai/codify_medium_multi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use refactai/codify_medium_multi with Docker Model Runner:
```
docker model run hf.co/refactai/codify_medium_multi
```

smallcloudteam commited on Dec 23, 2022

Commit

3a15e8c

1 Parent(s): 17db844

Upload config

Browse files

Files changed (1) hide show

config.json +0 -4

config.json CHANGED Viewed

@@ -15,9 +15,6 @@
     "type": "flash",
     "use_rotary_emb": null
   },
-  "architectures": [
-    "CodifyForCausalLM"
-  ],
   "attn_a_reach": 2048,
   "attn_b_reach": 2048,
   "attn_heads": 32,
@@ -44,7 +41,6 @@
   "posemb": false,
   "rescale_embeddings": false,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.24.0",
   "tune": [
     3,

     "type": "flash",
     "use_rotary_emb": null
   },
   "attn_a_reach": 2048,
   "attn_b_reach": 2048,
   "attn_heads": 32,
   "posemb": false,
   "rescale_embeddings": false,
   "tie_word_embeddings": false,
   "transformers_version": "4.24.0",
   "tune": [
     3,