Instructions to use RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits", device_map="auto")
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 Settings

vLLM

How to use RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits

SGLang

How to use RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits 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 "RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits" \
    --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": "RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits",
		"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 "RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits" \
        --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": "RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

sixtyoneeighty-7b - bnb 8bits

Model creator: https://huggingface.co/jambroz/
Original model: https://huggingface.co/jambroz/sixtyoneeighty-7b/

Original model description:

base_model: - Intel/neural-chat-7b-v3-1 - mlabonne/AlphaMonarch-7B - HuggingFaceH4/zephyr-7b-beta - mlabonne/NeuralBeagle14-7B library_name: transformers tags: - mergekit - merge license: apache-2.0

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using mlabonne/NeuralBeagle14-7B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: mlabonne/NeuralBeagle14-7B
dtype: bfloat16
merge_method: dare_ties
models:
- model: mlabonne/NeuralBeagle14-7B
- model: mlabonne/AlphaMonarch-7B
  parameters:
    density: '0.53'
    weight: '0.4'
- model: Intel/neural-chat-7b-v3-1
  parameters:
    density: '0.53'
    weight: '0.3'
- model: HuggingFaceH4/zephyr-7b-beta
  parameters:
    density: '0.53'
    weight: '0.3'
parameters:
  int8_mask: true

Downloads last month: 5

Safetensors

Model size

7B params

Tensor type

F32

F16

Papers for RichardErkhov/jambroz_-_sixtyoneeighty-7b-8bits

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 36

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19