Instructions to use aigcode/AIGCodeGeek-DS-6.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aigcode/AIGCodeGeek-DS-6.7B with Transformers:

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

pipe = pipeline("text-generation", model="aigcode/AIGCodeGeek-DS-6.7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aigcode/AIGCodeGeek-DS-6.7B")
model = AutoModelForCausalLM.from_pretrained("aigcode/AIGCodeGeek-DS-6.7B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aigcode/AIGCodeGeek-DS-6.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aigcode/AIGCodeGeek-DS-6.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aigcode/AIGCodeGeek-DS-6.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aigcode/AIGCodeGeek-DS-6.7B

SGLang

How to use aigcode/AIGCodeGeek-DS-6.7B 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 "aigcode/AIGCodeGeek-DS-6.7B" \
    --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": "aigcode/AIGCodeGeek-DS-6.7B",
		"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 "aigcode/AIGCodeGeek-DS-6.7B" \
        --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": "aigcode/AIGCodeGeek-DS-6.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aigcode/AIGCodeGeek-DS-6.7B with Docker Model Runner:
```
docker model run hf.co/aigcode/AIGCodeGeek-DS-6.7B
```

Leon-Leee commited on Apr 29, 2024

Commit

f096bbb

verified ·

1 Parent(s): 7adce78

Update README.md

Browse files

Files changed (1) hide show

README.md +22 -11

README.md CHANGED Viewed

@@ -17,8 +17,7 @@ tags:
 ## AIGCodeGeek-DS-6.7B
 ### Introduction
-AIGCodeGeek-DS-6.7B is the first released version of our Code-LLM family with competitive performance on benchmarks such as HumanEval(+) and MBPP(+).
-We are preparing for a tech report; stay tuned for more details:)
 ### Model Details
 #### Model Description
@@ -27,11 +26,11 @@ We are preparing for a tech report; stay tuned for more details:)
 - Fine-tuned from [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) with full parameters
 ### Training data
-A mixture of samples from high-quality open-source datasets (read *Acknowledgements*).
 ### Evaluation
-To check out our evaluation results: [EvalPlus](https://evalplus.github.io/leaderboard.html)
 ### Requirements
 It should work with the same requirements as DeepSeek-Coder-6.7B or the following packages:
@@ -48,8 +47,18 @@ attrdict
 ### QuickStart
-TBD
 ```
 ```
 ### Limits
@@ -57,9 +66,11 @@ TBD
 ### Acknowledgements
 We gain a lot of knowledge and resources from the open-source community:
-- [DeepSeekCoder](https://huggingface.co/deepseek-ai): impressive performance and insightful tech reports
-- [WizardCoder](https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder): Evol Instruct method and datasets
   - We used a ([Leon-Leee/wizardlm_evol_instruct_v2_196K_backuped](https://huggingface.co/datasets/Leon-Leee/wizardlm_evol_instruct_v2_196K_backuped)) since this original has been deleted.
-- [Magicoder](https://github.com/ise-uiuc/magicoder/): OSS-Instruct method and datasets, [Magicoder-Evol-Instruct-110K](https://huggingface.co/datasets/ise-uiuc/Magicoder-Evol-Instruct-110K) from theblackcat102/evol-codealpaca-v1(https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)
-- [Eurus](https://github.com/OpenBMB/Eurus): creative methods and datasets for reasoning, [openbmb/UltraInteract_sft](https://huggingface.co/datasets/openbmb/UltraInteract_sft)
-- [OpenCoderInterpreter](https://opencodeinterpreter.github.io/): well-designed experiments and [m-a-p/Code-Feedback](https://huggingface.co/datasets/m-a-p/Code-Feedback)

 ## AIGCodeGeek-DS-6.7B
 ### Introduction
+AIGCodeGeek-DS-6.7B is the first released version of our Code-LLM family with competitive performance on public and private benchmarks.
 ### Model Details
 #### Model Description
 - Fine-tuned from [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) with full parameters
 ### Training data
+A mixture of samples from high-quality open-source (read *Acknowledgements*) and our private datasets.
+We have made contamination detection as Magicoder/Bigcode did.
 ### Evaluation
+results to be added.
 ### Requirements
 It should work with the same requirements as DeepSeek-Coder-6.7B or the following packages:
 ### QuickStart
 ```
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("aigcode/AIGCodeGeek-DS-6.7B", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("aigcode/AIGCodeGeek-DS-6.7B", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
+messages=[
+    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
+]
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+# tokenizer.eos_token_id is the id of <|EOT|> token
+outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
 ```
 ### Limits
 ### Acknowledgements
 We gain a lot of knowledge and resources from the open-source community:
+- [DeepSeekCoder](https://huggingface.co/deepseek-ai): impressive model series and insightful tech reports
+- [WizardCoder](https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder): Evol Instruct and public datasets
   - We used a ([Leon-Leee/wizardlm_evol_instruct_v2_196K_backuped](https://huggingface.co/datasets/Leon-Leee/wizardlm_evol_instruct_v2_196K_backuped)) since this original has been deleted.
+- [Magicoder](https://github.com/ise-uiuc/magicoder/): OSS-Instruct, [Magicoder-Evol-Instruct-110K](https://huggingface.co/datasets/ise-uiuc/Magicoder-Evol-Instruct-110K) from theblackcat102/evol-codealpaca-v1(https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1)
+- [Eurus](https://github.com/OpenBMB/Eurus): creative datasets for reasoning, [openbmb/UltraInteract_sft](https://huggingface.co/datasets/openbmb/UltraInteract_sft)
+- [OpenCoderInterpreter](https://opencodeinterpreter.github.io/): well-designed system and datasets [m-a-p/Code-Feedback](https://huggingface.co/datasets/m-a-p/Code-Feedback)
+- [flytech/python-codes-25k](https://huggingface.co/datasets/flytech/python-codes-25k): diversity
+- [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory): easily used to finetune base models