Instructions to use schonsense/70B_FT_BC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use schonsense/70B_FT_BC with Transformers:

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

pipe = pipeline("text-generation", model="schonsense/70B_FT_BC")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("schonsense/70B_FT_BC")
model = AutoModelForCausalLM.from_pretrained("schonsense/70B_FT_BC")
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 schonsense/70B_FT_BC with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "schonsense/70B_FT_BC"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schonsense/70B_FT_BC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/schonsense/70B_FT_BC

SGLang

How to use schonsense/70B_FT_BC 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 "schonsense/70B_FT_BC" \
    --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": "schonsense/70B_FT_BC",
		"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 "schonsense/70B_FT_BC" \
        --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": "schonsense/70B_FT_BC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use schonsense/70B_FT_BC with Docker Model Runner:
```
docker model run hf.co/schonsense/70B_FT_BC
```

FT_BC

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

Merge Details

Merge Method

This model was merged using the Model Breadcrumbs merge method using meta-llama/Llama-3.3-70B-Instruct as a base.

Models Merged

The following models were included in the merge:

schonsense/70B_Chunky_stock
D:\mergekit\LORAs\applied\70B_ERA2_sun_r256
D:\mergekit_My_YAMLS\ERA2_stock
schonsense/VAR_stock
D:\mergekit_My_YAMLS\Book_stock

Configuration

The following YAML configuration was used to produce this model:

merge_method: breadcrumbs

models:
   
  - model: "D:\\mergekit\\_My_YAMLS\\ERA2_stock"
    parameters:
      gamma: 0.01
      density: .4
      weight: 0.2  

  - model: "D:\\mergekit\\_My_YAMLS\\Book_stock"
    parameters:
      gamma: 0.0
      density: .6
      weight: 0.3  

  - model: schonsense/70B_Chunky_stock
    parameters:
      gamma: 0.01
      density: .3
      weight: 0.2  

  - model: "D:\\mergekit\\LORAs\\applied\\70B_ERA2_sun_r256"
    parameters:
      gamma: 0.02
      density: .3
      weight: 0.2  

  - model: schonsense/VAR_stock
    parameters:
      gamma: 0.02
      density: .5
      weight: 0.1  
 
  - model: meta-llama/Llama-3.3-70B-Instruct

base_model: meta-llama/Llama-3.3-70B-Instruct

parameters:
  normalize: true
  int8_mask: true
  lambda: 1

dtype: float32
out_dtype: bfloat16

tokenizer:
  source: union
  pad_to_multiple_of: 8

Downloads last month: 1

Model tree for schonsense/70B_FT_BC

meta-llama/Llama-3.3-70B-Instruct

schonsense/70B_Chunky_stock

schonsense/VAR_stock

Merge model

this model

Paper for schonsense/70B_FT_BC

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

Paper • 2312.06795 • Published Dec 11, 2023 • 2