Instructions to use keshav1354/CoderBuddy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use keshav1354/CoderBuddy with Transformers:

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

pipe = pipeline("text-generation", model="keshav1354/CoderBuddy")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("keshav1354/CoderBuddy")
model = AutoModelForCausalLM.from_pretrained("keshav1354/CoderBuddy", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use keshav1354/CoderBuddy with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "keshav1354/CoderBuddy"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keshav1354/CoderBuddy",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/keshav1354/CoderBuddy

SGLang

How to use keshav1354/CoderBuddy 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 "keshav1354/CoderBuddy" \
    --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": "keshav1354/CoderBuddy",
		"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 "keshav1354/CoderBuddy" \
        --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": "keshav1354/CoderBuddy",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use keshav1354/CoderBuddy with Docker Model Runner:
```
docker model run hf.co/keshav1354/CoderBuddy
```

keshav1354 commited on Oct 23, 2024

Commit

e4b8dff

verified ·

1 Parent(s): a922a71

update readme.md

Browse files

Files changed (1) hide show

README.md +16 -4

README.md CHANGED Viewed

@@ -1,15 +1,27 @@
 ---
 library_name: transformers
-tags: []
 ---
 # Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
 ## Model Details
 ### Model Description
@@ -17,13 +29,13 @@ tags: []
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
 - **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
 ### Model Sources [optional]

 ---
 library_name: transformers
+base_model:
+- bigcode/starcoder2-7b
 ---
 # Model Card for Model ID
+# StarCoder2 Fine-Tuned with LoRA
+This is a fine-tuned version of the StarCoder2 model using LoRA (Low-Rank Adaptation) on a specific dataset for code generation or a targeted task. The base model is `bigcode/starcoder2-7b`, and this model has been fine-tuned on the `CodeAlpaca_20K` python dataset.
 ## Model Details
+**Base Model:** `bigcode/starcoder2-7b`
+**Fine-Tuned With:** LoRA (Low-Rank Adaptation)
+**Quantization:** 4-bit precision using `bitsandbytes`
+**Fine-Tuning Framework:** Hugging Face `transformers` and `peft`
+**Dataset:** CodeAlpaca_20K (or other dataset)
+**Max Sequence Length:** 1024 tokens
+**Use Case:** Code generation or Q&A for programming-related tasks.
+**Model Size:** 7B parameters
 ### Model Description
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+- **Developed by:** Keshav Singh
 - **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
 - **License:** [More Information Needed]
+- **Finetuned from model [optional]:** Starcoder2-7b
 ### Model Sources [optional]