Instructions to use paulml/TW3_FR_7B_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use paulml/TW3_FR_7B_v1 with Transformers:

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

pipe = pipeline("text-generation", model="paulml/TW3_FR_7B_v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("paulml/TW3_FR_7B_v1")
model = AutoModelForCausalLM.from_pretrained("paulml/TW3_FR_7B_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 paulml/TW3_FR_7B_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "paulml/TW3_FR_7B_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": "paulml/TW3_FR_7B_v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/paulml/TW3_FR_7B_v1

SGLang

How to use paulml/TW3_FR_7B_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 "paulml/TW3_FR_7B_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": "paulml/TW3_FR_7B_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 "paulml/TW3_FR_7B_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": "paulml/TW3_FR_7B_v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use paulml/TW3_FR_7B_v1 with Docker Model Runner:
```
docker model run hf.co/paulml/TW3_FR_7B_v1
```

TW3 French 8B v1

This model is a finetuned version of https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO using the https://huggingface.co/datasets/tbboukhari/Alpaca_french_instruct dataset.

Prompt Format

Nous Hermes 2 uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.

System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.

This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.

This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.

Prompt with system instruction (Use whatever system prompt you like, this is just an example!):

<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>

Inference Code

Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)

# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers import LlamaTokenizer, MixtralForCausalLM
import bitsandbytes, flash_attn

tokenizer = LlamaTokenizer.from_pretrained('paulml/TW3_FR_7B_v1', trust_remote_code=True)
model = MixtralForCausalLM.from_pretrained(
    "paulml/TW3_FR_7B_v1",
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_8bit=False,
    load_in_4bit=True,
    use_flash_attention_2=True
)

prompts = [
    """<|im_start|>system
Tu es un modèle d'IA, tu dois répondre aux requêtes avec les réponses les plus pertinentes.<|im_end|>
<|im_start|>user
Explique moi ce qu'est un LLM.<|im_end|>
<|im_start|>assistant""",
    ]

for chat in prompts:
    print(chat)
    input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
    generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
    response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
    print(f"Response: {response}")

Downloads last month: 7

paulml
/

TW3_FR_7B_v1

Dataset used to train paulml/TW3_FR_7B_v1