Instructions to use speechlessai/speechless-codellama-airoboros-orca-platypus-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use speechlessai/speechless-codellama-airoboros-orca-platypus-13b with Transformers:

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

pipe = pipeline("text-generation", model="speechlessai/speechless-codellama-airoboros-orca-platypus-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("speechlessai/speechless-codellama-airoboros-orca-platypus-13b")
model = AutoModelForCausalLM.from_pretrained("speechlessai/speechless-codellama-airoboros-orca-platypus-13b")

Inference
Local Apps Settings

vLLM

How to use speechlessai/speechless-codellama-airoboros-orca-platypus-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "speechlessai/speechless-codellama-airoboros-orca-platypus-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "speechlessai/speechless-codellama-airoboros-orca-platypus-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/speechlessai/speechless-codellama-airoboros-orca-platypus-13b

SGLang

How to use speechlessai/speechless-codellama-airoboros-orca-platypus-13b 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 "speechlessai/speechless-codellama-airoboros-orca-platypus-13b" \
    --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": "speechlessai/speechless-codellama-airoboros-orca-platypus-13b",
		"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 "speechlessai/speechless-codellama-airoboros-orca-platypus-13b" \
        --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": "speechlessai/speechless-codellama-airoboros-orca-platypus-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use speechlessai/speechless-codellama-airoboros-orca-platypus-13b with Docker Model Runner:
```
docker model run hf.co/speechlessai/speechless-codellama-airoboros-orca-platypus-13b
```

uukuguy commited on Sep 22, 2023

Commit

907f228

1 Parent(s): f01d3ab

Update README.md

Browse files

Files changed (1) hide show

README.md +26 -6

README.md CHANGED Viewed

@@ -18,15 +18,35 @@ Use the following dataset to fine-tune codellama/CodeLlama-13B in order to impro
 - jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning.
 - Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset.
-- garage-bAInd/Open-Platypus: 100%
 | Metric | Value |
 | --- | --- |
-| ARC | |
-| HellaSwag | |
-| MMLU | |
-| TruthfulQA | |
-| Average | |
 # **Code Llama**

 - jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning.
 - Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset.
+- garage-bAInd/Open-Platypus: 100%
+| Metric | Value |
+| --- | --- |
+| humaneval-python | 49.39 |
+[Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
+CodeLlama-34B-Python: 53.29
+CodeLlama-34B-Instruct: 50.79
+CodeLlama-13B-Instruct: 50.6
+CodeLlama-34B: 45.11
+CodeLlama-13B-Python: 42.89
+CodeLlama-13B: 35.07
+[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
 | Metric | Value |
 | --- | --- |
+| ARC | 44.88 |
+| HellaSwag | 67.7 |
+| MMLU | 43.16 |
+| TruthfulQA | 40.88 |
+| Average | 49.15 |
 # **Code Llama**