Instructions to use brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw with Transformers:

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

pipe = pipeline("text-generation", model="brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw")
model = AutoModelForCausalLM.from_pretrained("brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw

SGLang

How to use brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw 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 "brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw" \
    --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": "brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw",
		"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 "brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw" \
        --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": "brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw with Docker Model Runner:
```
docker model run hf.co/brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw
```

tokenizer.model failing to load

by tylerdev - opened Feb 13, 2024

Discussion

tylerdev

Feb 13, 2024

Hi, I see you just updated this to include a tokenizer model.

It seems to be causing some issues with sentencepiece when trying to load the model. My error is below:

2024-02-13T00:16:16.475613939Z     self.tokenizer = ExLlamaV2Tokenizer(config)
2024-02-13T00:16:16.475615049Z   File "/usr/local/lib/python3.10/dist-packages/exllamav2/tokenizer.py", line 65, in __init__
2024-02-13T00:16:16.475616229Z     if os.path.exists(path_spm) and not force_json: self.tokenizer = ExLlamaV2TokenizerSPM(path_spm)
2024-02-13T00:16:16.475617419Z   File "/usr/local/lib/python3.10/dist-packages/exllamav2/tokenizers/spm.py", line 9, in __init__
2024-02-13T00:16:16.475618739Z     self.spm = SentencePieceProcessor(model_file = tokenizer_model)
2024-02-13T00:16:16.475619839Z   File "/usr/local/lib/python3.10/dist-packages/sentencepiece/__init__.py", line 447, in Init
2024-02-13T00:16:16.475620919Z     self.Load(model_file=model_file, model_proto=model_proto)
2024-02-13T00:16:16.475622029Z   File "/usr/local/lib/python3.10/dist-packages/sentencepiece/__init__.py", line 905, in Load
2024-02-13T00:16:16.475623039Z     return self.LoadFromFile(model_file)
2024-02-13T00:16:16.475624149Z   File "/usr/local/lib/python3.10/dist-packages/sentencepiece/__init__.py", line 310, in LoadFromFile
2024-02-13T00:16:16.475625379Z     return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg)
2024-02-13T00:16:16.475626769Z RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

Any ideas on what might be causing this? I confirmed that the tokenizer model downloaded so not sure what to try.

Anyway, great model!! Thanks for publishing this.

brucethemoose

Owner Feb 13, 2024

That is because I failed to upload the right one.

Should be fixed now, let me know if it isn't!

tylerdev

Feb 14, 2024

That worked, thanks!

tylerdev changed discussion status to closed Feb 14, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment