Instructions to use JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline with Transformers:

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

pipe = pipeline("text-generation", model="JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline

SGLang

How to use JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline 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 "JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline" \
    --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": "JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline",
		"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 "JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline" \
        --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": "JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline with Docker Model Runner:
```
docker model run hf.co/JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline
```

kraalfar commited on Dec 5, 2024

Commit

33f582d

verified ·

1 Parent(s): 67012cf

Update config.json

Browse files

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -14,7 +14,7 @@
   "intermediate_size": 5504,
   "max_position_embeddings": 16384,
   "mlp_bias": false,
-  "model_path": "checkpoints/comment_resolution/model/deepseek-ai/deepseek-coder-1.3b-instruct_lm_baseline_training/epoch_2",
   "model_type": "llama",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
@@ -28,7 +28,7 @@
   },
   "rope_theta": 100000,
   "tie_word_embeddings": false,
-  "tokenizer_path": "checkpoints/comment_resolution/tokenizer/deepseek-ai/deepseek-coder-1.3b-instruct",
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
   "use_cache": true,

   "intermediate_size": 5504,
   "max_position_embeddings": 16384,
   "mlp_bias": false,
+  "model_path": "JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline",
   "model_type": "llama",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
   },
   "rope_theta": 100000,
   "tie_word_embeddings": false,
+  "tokenizer_path": "JetBrains-Research/deepseek-coder-1.3b-instruct-comment-resolution-baseline",
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
   "use_cache": true,