Instructions to use CodeGPTPlus/deepseek-coder-1.3b-typescript with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodeGPTPlus/deepseek-coder-1.3b-typescript with Transformers:

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

pipe = pipeline("text-generation", model="CodeGPTPlus/deepseek-coder-1.3b-typescript")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CodeGPTPlus/deepseek-coder-1.3b-typescript")
model = AutoModelForCausalLM.from_pretrained("CodeGPTPlus/deepseek-coder-1.3b-typescript")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CodeGPTPlus/deepseek-coder-1.3b-typescript with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/CodeGPTPlus/deepseek-coder-1.3b-typescript

SGLang

How to use CodeGPTPlus/deepseek-coder-1.3b-typescript 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 "CodeGPTPlus/deepseek-coder-1.3b-typescript" \
    --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": "CodeGPTPlus/deepseek-coder-1.3b-typescript",
		"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 "CodeGPTPlus/deepseek-coder-1.3b-typescript" \
        --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": "CodeGPTPlus/deepseek-coder-1.3b-typescript",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CodeGPTPlus/deepseek-coder-1.3b-typescript with Docker Model Runner:
```
docker model run hf.co/CodeGPTPlus/deepseek-coder-1.3b-typescript
```

Vokturz commited on Jan 15, 2024

Commit

83cc074

verified ·

1 Parent(s): d7444f2

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -12

README.md CHANGED Viewed

@@ -5,12 +5,10 @@ tags:
 - axolotl
 - generated_from_trainer
 model-index:
-- name: deepseek_coder_1.3b_typescript
   results: []
 ---
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 <details><summary>See axolotl config</summary>
@@ -29,9 +27,7 @@ datasets:
   - path: CodeGPTPlus/typescript-0-500000-seq1024
     type: completion
     field: text
-#dataset_prepared_path:
-#pretraining_dataset: CodeGPTPlus/typescript-0-500000-seq1024
 val_set_size: 0.001
 output_dir:  ./fft-out
@@ -57,7 +53,6 @@ wandb_log_model: end
 gradient_accumulation_steps: 2
 micro_batch_size: 20
 num_epochs: 1
-#max_steps: 1 # REMOVE IT
 optimizer: adamw_bnb_8bit
 adam_beta1: 0.9
 adam_beta2: 0.999
@@ -96,17 +91,13 @@ special_tokens:
   bos_token: "<｜begin▁of▁sentence｜>"
   eos_token: "<｜end▁of▁sentence｜>"
   pad_token: "<｜end▁of▁sentence｜>"
-  # fim_prefix: "<｜fim▁begin｜>"
-  # fim_middle: "<｜fim▁hole｜>"
-  # fim_suffix: "<｜fim▁end｜>"
 ```
 </details><br>
-# deepseek_coder_1.3b_typescript
-This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.7681

 - axolotl
 - generated_from_trainer
 model-index:
+- name: deepseek-coder-1.3b-typescript
   results: []
 ---
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 <details><summary>See axolotl config</summary>
   - path: CodeGPTPlus/typescript-0-500000-seq1024
     type: completion
     field: text
 val_set_size: 0.001
 output_dir:  ./fft-out
 gradient_accumulation_steps: 2
 micro_batch_size: 20
 num_epochs: 1
 optimizer: adamw_bnb_8bit
 adam_beta1: 0.9
 adam_beta2: 0.999
   bos_token: "<｜begin▁of▁sentence｜>"
   eos_token: "<｜end▁of▁sentence｜>"
   pad_token: "<｜end▁of▁sentence｜>"
 ```
 </details><br>
+# deepseek-coder-1.3b-typescript
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on the the-stack dataset, using 0.5B of tokens of typescript only.
 It achieves the following results on the evaluation set:
 - Loss: 0.7681