Instructions to use v1olet/v1olet_marcoroni-go-bruins-merge-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use v1olet/v1olet_marcoroni-go-bruins-merge-7B with Transformers:

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

pipe = pipeline("text-generation", model="v1olet/v1olet_marcoroni-go-bruins-merge-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("v1olet/v1olet_marcoroni-go-bruins-merge-7B")
model = AutoModelForCausalLM.from_pretrained("v1olet/v1olet_marcoroni-go-bruins-merge-7B")

Inference
Local Apps Settings

vLLM

How to use v1olet/v1olet_marcoroni-go-bruins-merge-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "v1olet/v1olet_marcoroni-go-bruins-merge-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "v1olet/v1olet_marcoroni-go-bruins-merge-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/v1olet/v1olet_marcoroni-go-bruins-merge-7B

SGLang

How to use v1olet/v1olet_marcoroni-go-bruins-merge-7B 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 "v1olet/v1olet_marcoroni-go-bruins-merge-7B" \
    --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": "v1olet/v1olet_marcoroni-go-bruins-merge-7B",
		"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 "v1olet/v1olet_marcoroni-go-bruins-merge-7B" \
        --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": "v1olet/v1olet_marcoroni-go-bruins-merge-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use v1olet/v1olet_marcoroni-go-bruins-merge-7B with Docker Model Runner:
```
docker model run hf.co/v1olet/v1olet_marcoroni-go-bruins-merge-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

12th December 2023

We are ranked 6th on the overall leaderboard and 1st in the 7B leaderboard! 🔥🔥🔥

Merge AIDC-ai-business/Marcoroni-7B-v3 and rwitz/go-bruins-v2 using slerp merge from https://github.com/cg123/mergekit.

config.yaml

slices:
  - sources:
      - model: AIDC-ai-business/Marcoroni-7B-v3
        layer_range: [0, 32]
      - model: rwitz/go-bruins-v2
        layer_range: [0, 32]
merge_method: slerp
base_model: AIDC-ai-business/Marcoroni-7B-v3
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 
dtype: float16

You can use alpaca template.

template_format = """{system}
### Instruction:
{prompt}

### Response:
"""

Developed by: Trong-Hieu Nguyen-Mau

Downloads last month: 323

Model tree for v1olet/v1olet_marcoroni-go-bruins-merge-7B

Merges

1 model

Quantizations

3 models

v1olet
/

v1olet_marcoroni-go-bruins-merge-7B

12th December 2023

Model tree for v1olet/v1olet_marcoroni-go-bruins-merge-7B

Spaces using v1olet/v1olet_marcoroni-go-bruins-merge-7B 30