Instructions to use yibinlei/effir-mistral-drop-16-mlp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yibinlei/effir-mistral-drop-16-mlp with Transformers:

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

pipe = pipeline("text-generation", model="yibinlei/effir-mistral-drop-16-mlp", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yibinlei/effir-mistral-drop-16-mlp", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("yibinlei/effir-mistral-drop-16-mlp", trust_remote_code=True, 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]:]))

PEFT
How to use yibinlei/effir-mistral-drop-16-mlp with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yibinlei/effir-mistral-drop-16-mlp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yibinlei/effir-mistral-drop-16-mlp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yibinlei/effir-mistral-drop-16-mlp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yibinlei/effir-mistral-drop-16-mlp

SGLang

How to use yibinlei/effir-mistral-drop-16-mlp 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 "yibinlei/effir-mistral-drop-16-mlp" \
    --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": "yibinlei/effir-mistral-drop-16-mlp",
		"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 "yibinlei/effir-mistral-drop-16-mlp" \
        --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": "yibinlei/effir-mistral-drop-16-mlp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yibinlei/effir-mistral-drop-16-mlp with Docker Model Runner:
```
docker model run hf.co/yibinlei/effir-mistral-drop-16-mlp
```

EffiR Mistral Drop 16 MLP

EffiR Mistral dense retriever with direct layer dropping.

Use trust_remote_code=True.

from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
from huggingface_hub import hf_hub_download
import torch

repo = "yibinlei/effir-mistral-drop-16-mlp"

tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
config = AutoConfig.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    config=config,
    trust_remote_code=True,
    attn_implementation="eager",
    torch_dtype=torch.bfloat16,
)

input_emb_path = hf_hub_download(repo, "embedding/input_emb.pth")
model.set_input_embeddings(torch.load(input_emb_path, map_location="cpu"))
model = PeftModel.from_pretrained(model, repo)
model = model.merge_and_unload()

Downloads last month: 359

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for yibinlei/effir-mistral-drop-16-mlp

Base model

mistralai/Mistral-7B-v0.1

Adapter

(2463)

this model