Instructions to use NeuralNovel/Senzu-7B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeuralNovel/Senzu-7B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="NeuralNovel/Senzu-7B-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("NeuralNovel/Senzu-7B-v0.1")
model = AutoModelForMultimodalLM.from_pretrained("NeuralNovel/Senzu-7B-v0.1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NeuralNovel/Senzu-7B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeuralNovel/Senzu-7B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeuralNovel/Senzu-7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NeuralNovel/Senzu-7B-v0.1

SGLang

How to use NeuralNovel/Senzu-7B-v0.1 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 "NeuralNovel/Senzu-7B-v0.1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeuralNovel/Senzu-7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "NeuralNovel/Senzu-7B-v0.1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeuralNovel/Senzu-7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NeuralNovel/Senzu-7B-v0.1 with Docker Model Runner:
```
docker model run hf.co/NeuralNovel/Senzu-7B-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

NeuralNovel/Senzu-7B-v0.1

Embracing a quiet storm ..

Model Details

This model is a full parameter fine-tuned version of mistralai/Mistral-7B-v0.1

Trained on the Neural-DPO, metamath_gsm8k and RPGPT_PublicDomain-alpaca dataset.

This model excels at character roleplay, also with the ability of responding accurately to a wide variety of complex questions.

base_model: mistralai/Mistral-7B-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets: 
  - path: practical-dreamer/RPGPT_PublicDomain-alpaca
    type: alpaca
    format: "[INST] {instruction} [/INST]"
    no_input_format: "[INST] {instruction} [/INST]"

datasets: 
  - path: shuyuej/metamath_gsm8k
    type: jeopardy
    format: "[INST] {instruction} [/INST]"
    no_input_format: "[INST] {instruction} [/INST]"

datasets:
  - path: NeuralNovel/Neural-DPO
    type:
      system_prompt: ""
      field_system: system
      field_instruction: chosen
      field_output: chosen
      format: "[INST] {instruction} [/INST]"
      no_input_format: "[INST] {instruction} [/INST]"
      
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out

sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true
eval_sample_packing: false

wandb_project:
wandb_entity:
wandb_watch:
wandb_name: 
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 0
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.2061	0.01	1	0.3139
0.0	0.25	32	0.0000
0.0	0.5	64	0.0010
0.0	0.76	96	0.0000

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.2.0+cu121
Datasets 2.17.1
Tokenizers 0.15.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	56.40
AI2 Reasoning Challenge (25-Shot)	58.19
HellaSwag (10-Shot)	81.98
MMLU (5-Shot)	63.20
TruthfulQA (0-shot)	40.20
Winogrande (5-shot)	76.64
GSM8k (5-shot)	18.20

Downloads last month: 11

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for NeuralNovel/Senzu-7B-v0.1

Base model

mistralai/Mistral-7B-v0.1

Finetuned

(928)

this model

Quantizations

4 models

NeuralNovel
/

Senzu-7B-v0.1