Instructions to use OpenAssistant/codellama-13b-oasst-sft-v10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenAssistant/codellama-13b-oasst-sft-v10 with Transformers:

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

pipe = pipeline("text-generation", model="OpenAssistant/codellama-13b-oasst-sft-v10", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenAssistant/codellama-13b-oasst-sft-v10", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OpenAssistant/codellama-13b-oasst-sft-v10", trust_remote_code=True)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenAssistant/codellama-13b-oasst-sft-v10 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenAssistant/codellama-13b-oasst-sft-v10"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenAssistant/codellama-13b-oasst-sft-v10",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenAssistant/codellama-13b-oasst-sft-v10

SGLang

How to use OpenAssistant/codellama-13b-oasst-sft-v10 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 "OpenAssistant/codellama-13b-oasst-sft-v10" \
    --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": "OpenAssistant/codellama-13b-oasst-sft-v10",
		"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 "OpenAssistant/codellama-13b-oasst-sft-v10" \
        --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": "OpenAssistant/codellama-13b-oasst-sft-v10",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenAssistant/codellama-13b-oasst-sft-v10 with Docker Model Runner:
```
docker model run hf.co/OpenAssistant/codellama-13b-oasst-sft-v10
```

andreaskoepf commited on Aug 27, 2023

Commit

8bd6622

1 Parent(s): ca83664

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -10,12 +10,14 @@ language:
 This model is an Open-Assistant fine-tuning of Meta's CodeLlama 13B LLM.
 ## Model Details
-- **Finetuned from:** [codellama](https://github.com/facebookresearch/codellama) via [epfLLM/Megatron-LLM](https://github.com/epfLLM/Megatron-LLM)
 - **Model type:** Causal decoder-only transformer language model
 - **Language:** English
-- **Weights & Biases training logs:** 6123 steps [run56_oa_llamacode](https://wandb.ai/open-assistant/public-sft/runs/run56_oa_llamacode)
 - **Demo:** [Continuations for 250 random prompts (without system message)](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-08-26_OpenAssistant_codellama-13b-oasst-sft-v10_sampling_noprefix2.json)
 - **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
 - **Contact:** [Open-Assistant Discord](https://ykilcher.com/open-assistant-discord)

 This model is an Open-Assistant fine-tuning of Meta's CodeLlama 13B LLM.
+**Note**: Due to the new RoPE Theta value (1e6 instead of 1e4), for correct results you must load this model with `trust_remote_code=True` or use the latest main branch of Huggingface transformers (until version 4.33 is released).
 ## Model Details
+- **Finetuned from:** [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) via [epfLLM/Megatron-LLM](https://github.com/epfLLM/Megatron-LLM)
 - **Model type:** Causal decoder-only transformer language model
 - **Language:** English
+- **Weights & Biases training logs:** 6123 steps, BS 64 [run56_oa_llamacode](https://wandb.ai/open-assistant/public-sft/runs/run56_oa_llamacode)
 - **Demo:** [Continuations for 250 random prompts (without system message)](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-08-26_OpenAssistant_codellama-13b-oasst-sft-v10_sampling_noprefix2.json)
 - **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
 - **Contact:** [Open-Assistant Discord](https://ykilcher.com/open-assistant-discord)