Instructions to use brucethemoose/Yi-34B-200K-DARE-megamerge-v8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brucethemoose/Yi-34B-200K-DARE-megamerge-v8 with Transformers:

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

pipe = pipeline("text-generation", model="brucethemoose/Yi-34B-200K-DARE-megamerge-v8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("brucethemoose/Yi-34B-200K-DARE-megamerge-v8")
model = AutoModelForMultimodalLM.from_pretrained("brucethemoose/Yi-34B-200K-DARE-megamerge-v8")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use brucethemoose/Yi-34B-200K-DARE-megamerge-v8 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-DARE-megamerge-v8"
# 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-DARE-megamerge-v8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/brucethemoose/Yi-34B-200K-DARE-megamerge-v8

SGLang

How to use brucethemoose/Yi-34B-200K-DARE-megamerge-v8 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-DARE-megamerge-v8" \
    --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-DARE-megamerge-v8",
		"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-DARE-megamerge-v8" \
        --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-DARE-megamerge-v8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use brucethemoose/Yi-34B-200K-DARE-megamerge-v8 with Docker Model Runner:
```
docker model run hf.co/brucethemoose/Yi-34B-200K-DARE-megamerge-v8
```

brucethemoose commited on Jan 15, 2024

Commit

2750ab8

verified ·

1 Parent(s): 63eba31

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -32,6 +32,8 @@ Being a Yi model, run a lower temperature with 0.05 or higher MinP, a little rep
 I recommend exl2 quantizations profiled on data similar to the desired task. It is especially sensitive to the quantization data at low bpw. I've upload my own fiction-oriented quantizations here: https://huggingface.co/collections/brucethemoose/most-recent-merge-65742644ca03b6c514afa204
 To load/train this in full-context backends like transformers, you *must* change `max_position_embeddings` in config.json to a lower value than 200,000, otherwise you will OOM! I do not recommend running high context without context-efficient backends like exllamav2, litellm or unsloth.

 I recommend exl2 quantizations profiled on data similar to the desired task. It is especially sensitive to the quantization data at low bpw. I've upload my own fiction-oriented quantizations here: https://huggingface.co/collections/brucethemoose/most-recent-merge-65742644ca03b6c514afa204
+Lonestriker has also uploaded more general purpose quantizations here: https://huggingface.co/models?sort=trending&search=LoneStriker+Yi-34B-200K-DARE-megamerge-v8
 To load/train this in full-context backends like transformers, you *must* change `max_position_embeddings` in config.json to a lower value than 200,000, otherwise you will OOM! I do not recommend running high context without context-efficient backends like exllamav2, litellm or unsloth.