Instructions to use DewEfresh/Neo_7b-merge10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DewEfresh/Neo_7b-merge10 with Transformers:

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

pipe = pipeline("text-generation", model="DewEfresh/Neo_7b-merge10")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DewEfresh/Neo_7b-merge10")
model = AutoModelForCausalLM.from_pretrained("DewEfresh/Neo_7b-merge10")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DewEfresh/Neo_7b-merge10 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DewEfresh/Neo_7b-merge10"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DewEfresh/Neo_7b-merge10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DewEfresh/Neo_7b-merge10

SGLang

How to use DewEfresh/Neo_7b-merge10 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 "DewEfresh/Neo_7b-merge10" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DewEfresh/Neo_7b-merge10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "DewEfresh/Neo_7b-merge10" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DewEfresh/Neo_7b-merge10",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DewEfresh/Neo_7b-merge10 with Docker Model Runner:
```
docker model run hf.co/DewEfresh/Neo_7b-merge10
```

Neo_7b-merge10

Neo_7b-merge10 is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [0, 0]
      - model: DewEfresh/neo_7b
        layer_range: [3, 3]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [1, 1]
      - model: DewEfresh/neo_7b
        layer_range: [3, 3]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [2, 2]
      - model: DewEfresh/neo_7b
        layer_range: [3, 3]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [4, 4]
      - model: DewEfresh/neo_7b
        layer_range: [7, 7]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [5, 5]
      - model: DewEfresh/neo_7b
        layer_range: [7, 7]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [6, 6]
      - model: DewEfresh/neo_7b
        layer_range: [7, 7]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [8, 8]
      - model: DewEfresh/neo_7b
        layer_range: [11, 11]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [9, 9]
      - model: DewEfresh/neo_7b
        layer_range: [11, 11]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [10, 10]
      - model: DewEfresh/neo_7b
        layer_range: [11, 11]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [12, 12]
      - model: DewEfresh/neo_7b
        layer_range: [15, 15]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [13, 13]
      - model: DewEfresh/neo_7b
        layer_range: [15, 15]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [14, 14]
      - model: DewEfresh/neo_7b
        layer_range: [15, 15]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [16, 16]
      - model: DewEfresh/neo_7b
        layer_range: [19, 19]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [17, 17]
      - model: DewEfresh/neo_7b
        layer_range: [19, 19]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [18, 18]
      - model: DewEfresh/neo_7b
        layer_range: [19, 19]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [20, 20]
      - model: DewEfresh/neo_7b
        layer_range: [23, 23]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [21, 21]
      - model: DewEfresh/neo_7b
        layer_range: [23, 23]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [22, 22]
      - model: DewEfresh/neo_7b
        layer_range: [23, 23]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [24, 24]
      - model: DewEfresh/neo_7b
        layer_range: [27, 27]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [25, 25]
      - model: DewEfresh/neo_7b
        layer_range: [27, 27]
  - sources:
      - model: DewEfresh/neo_7b
        layer_range: [26, 26]
      - model: DewEfresh/neo_7b
        layer_range: [27, 27]
merge_method: slerp
base_model: DewEfresh/neo_7b
parameters:
  t: 0.5
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "DewEfresh/Neo_7b-merge10"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for DewEfresh/Neo_7b-merge10

Base model

DewEfresh/neo_7b

Finetuned

(7)

this model