Instructions to use oobabooga/CodeBooga-34B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oobabooga/CodeBooga-34B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="oobabooga/CodeBooga-34B-v0.1")

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

tokenizer = AutoTokenizer.from_pretrained("oobabooga/CodeBooga-34B-v0.1")
model = AutoModelForCausalLM.from_pretrained("oobabooga/CodeBooga-34B-v0.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use oobabooga/CodeBooga-34B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oobabooga/CodeBooga-34B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oobabooga/CodeBooga-34B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/oobabooga/CodeBooga-34B-v0.1

SGLang

How to use oobabooga/CodeBooga-34B-v0.1 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 "oobabooga/CodeBooga-34B-v0.1" \
    --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": "oobabooga/CodeBooga-34B-v0.1",
		"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 "oobabooga/CodeBooga-34B-v0.1" \
        --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": "oobabooga/CodeBooga-34B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use oobabooga/CodeBooga-34B-v0.1 with Docker Model Runner:
```
docker model run hf.co/oobabooga/CodeBooga-34B-v0.1
```

oobabooga commited on Jan 2, 2024

Commit

8a4e1e1

1 Parent(s): 3d2f1a2

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -11

README.md CHANGED Viewed

@@ -58,6 +58,8 @@ Bot reply
 ## Evaluation
 I made a quick experiment where I asked a set of 3 Python and 3 Javascript questions (real world, difficult questions with nuance) to the following models:
 1) This one
@@ -81,17 +83,6 @@ The resulting cumulative scores were:
 CodeBooga-34B-v0.1 performed very well, while its variant performed poorly, so I uploaded the former but not the latter.
-## Recommended settings
-I recommend the [Divine Intellect](https://github.com/oobabooga/text-generation-webui/blob/ae8cd449ae3e0236ecb3775892bb1eea23f9ed68/presets/Divine%20Intellect.yaml) preset for instruction-following models like this, as per the [Preset Arena experiment results](https://github.com/oobabooga/oobabooga.github.io/blob/main/arena/results.md):
-```yaml
-temperature: 1.31
-top_p: 0.14
-repetition_penalty: 1.17
-top_k: 49
-```
 ## Quantized versions
 ### GGUF

 ## Evaluation
+(This is not very scientific, so bear with me.)
 I made a quick experiment where I asked a set of 3 Python and 3 Javascript questions (real world, difficult questions with nuance) to the following models:
 1) This one
 CodeBooga-34B-v0.1 performed very well, while its variant performed poorly, so I uploaded the former but not the latter.
 ## Quantized versions
 ### GGUF