Instructions to use JetBrains/CodeLlama-7B-Kexer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JetBrains/CodeLlama-7B-Kexer with Transformers:

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

pipe = pipeline("text-generation", model="JetBrains/CodeLlama-7B-Kexer")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JetBrains/CodeLlama-7B-Kexer")
model = AutoModelForCausalLM.from_pretrained("JetBrains/CodeLlama-7B-Kexer")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use JetBrains/CodeLlama-7B-Kexer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JetBrains/CodeLlama-7B-Kexer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JetBrains/CodeLlama-7B-Kexer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/JetBrains/CodeLlama-7B-Kexer

SGLang

How to use JetBrains/CodeLlama-7B-Kexer 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/CodeLlama-7B-Kexer" \
    --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/CodeLlama-7B-Kexer",
		"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/CodeLlama-7B-Kexer" \
        --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/CodeLlama-7B-Kexer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use JetBrains/CodeLlama-7B-Kexer with Docker Model Runner:
```
docker model run hf.co/JetBrains/CodeLlama-7B-Kexer
```

jdev8 commited on May 16, 2024

Commit

c5bf7d6

verified ·

1 Parent(s): 2ba7b66

Update README.md

Browse files

Files changed (1) hide show

README.md +23 -4

README.md CHANGED Viewed

@@ -1,5 +1,19 @@
 ---
 license: apache-2.0
 ---
 # Kexer models
@@ -37,6 +51,11 @@ generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
 print(generated_text)
 ```
 # Training setup
 The model was trained on one A100 GPU with following hyperparameters:
@@ -62,10 +81,10 @@ To evaluate we used Kotlin Humaneval (more infromation here)
 Fine-tuned model:
-|         **Model name**           |             **Kotlin HumanEval Pass Rate**              |             **Kotlin Completion**              |
-|:---------------------------:|:----------------------------------------:|:----------------------------------------:|
-|           `base model`            |           26.89            |           0.388            |
-|        `fine-tuned model`        |          42.24         |          0.344          |
 # Ethical Considerations and Limitations

 ---
 license: apache-2.0
+datasets:
+- JetBrains/KExercises
+results:
+  - task:
+      type: text-generation
+    dataset:
+      name: MultiPL-HumanEval (Kotlin)
+      type: openai_humaneval
+    metrics:
+      - name: pass@1
+        type: pass@1
+        value: 42.24
+tags:
+- code
 ---
 # Kexer models
 print(generated_text)
 ```
+As with the base model, we can use FIM. To do this, the following format must be used:
+```
+'<PRE> ' + prefix + ' <SUF> ' + suffix + ' <MID>'
+```
 # Training setup
 The model was trained on one A100 GPU with following hyperparameters:
 Fine-tuned model:
+|         **Model name**           |             **Kotlin HumanEval Pass Rate**              |
+|:---------------------------:|:----------------------------------------:|
+|           `base model`            |           26.89            |
+|        `fine-tuned model`        |          42.24         |
 # Ethical Considerations and Limitations