Instructions to use paloalma/ECE-TW3-JRGL-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use paloalma/ECE-TW3-JRGL-V1 with Transformers:

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

pipe = pipeline("text-generation", model="paloalma/ECE-TW3-JRGL-V1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("paloalma/ECE-TW3-JRGL-V1")
model = AutoModelForCausalLM.from_pretrained("paloalma/ECE-TW3-JRGL-V1")
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 paloalma/ECE-TW3-JRGL-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "paloalma/ECE-TW3-JRGL-V1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "paloalma/ECE-TW3-JRGL-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/paloalma/ECE-TW3-JRGL-V1

SGLang

How to use paloalma/ECE-TW3-JRGL-V1 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 "paloalma/ECE-TW3-JRGL-V1" \
    --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": "paloalma/ECE-TW3-JRGL-V1",
		"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 "paloalma/ECE-TW3-JRGL-V1" \
        --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": "paloalma/ECE-TW3-JRGL-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use paloalma/ECE-TW3-JRGL-V1 with Docker Model Runner:
```
docker model run hf.co/paloalma/ECE-TW3-JRGL-V1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

ECE-TW3-JRGL-V1

This model has been produced by :

Louis Garcia, engineering student at French Engineering School ECE
Matthieu Jollard, engineering student at French Engineering School ECE

Under the supervision of :

Andre-Louis Rochet, Lecturer at ECE & Co-Founder of TW3 Partners
Paul Lemaistre, CTO of TW3 Partners

With the contribution of :

ECE engineering school as sponsor and financial contributor
RunPod as financial contributor

About ECE

ECE, a multi-program, multi-campus, and multi-sector engineering school specializing in digital engineering, trains engineers and technology experts for the 21st century, capable of meeting the challenges of the dual digital and sustainable development revolutions. French Engineering School ECE

Description

ECE-TW3-JRGL-V1 is a merge of the following models using mergekit:

slices:
  - sources:
      - model: ShinojiResearch/Senku-70B-Full
        layer_range: [0, 80]
      - model: 152334H/miqu-1-70b-sf
        layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
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

Results

ECE-TW3-JRGL-v1 scores 83.07 on EQ-Bench V2

@misc{paech2023eqbench, title={EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models}, author={Samuel J. Paech}, year={2023}, eprint={2312.06281}, archivePrefix={arXiv}, primaryClass={cs.CL} }

Downloads last month: 8,403

Safetensors

Model size

69B params

Tensor type

F16

Model tree for paloalma/ECE-TW3-JRGL-V1

Quantizations

2 models

Paper for paloalma/ECE-TW3-JRGL-V1

EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models

Paper • 2312.06281 • Published Dec 11, 2023 • 2