Instructions to use Novocoders/Mistral-NeuralDPO-v0.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Novocoders/Mistral-NeuralDPO-v0.4 with Transformers:

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

pipe = pipeline("text-generation", model="Novocoders/Mistral-NeuralDPO-v0.4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Novocoders/Mistral-NeuralDPO-v0.4")
model = AutoModelForCausalLM.from_pretrained("Novocoders/Mistral-NeuralDPO-v0.4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Novocoders/Mistral-NeuralDPO-v0.4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Novocoders/Mistral-NeuralDPO-v0.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Novocoders/Mistral-NeuralDPO-v0.4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Novocoders/Mistral-NeuralDPO-v0.4

SGLang

How to use Novocoders/Mistral-NeuralDPO-v0.4 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 "Novocoders/Mistral-NeuralDPO-v0.4" \
    --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": "Novocoders/Mistral-NeuralDPO-v0.4",
		"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 "Novocoders/Mistral-NeuralDPO-v0.4" \
        --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": "Novocoders/Mistral-NeuralDPO-v0.4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Novocoders/Mistral-NeuralDPO-v0.4 with Docker Model Runner:
```
docker model run hf.co/Novocoders/Mistral-NeuralDPO-v0.4
```

NovoCode commited on Mar 19, 2024

Commit

31c2816

verified ·

1 Parent(s): 76a02dd

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -7

README.md CHANGED Viewed

@@ -1,6 +1,7 @@
 ---
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
 - generated_from_trainer
 model-index:
@@ -31,7 +32,8 @@ datasets:
     split: train
     type: chatml.intel
     format: "[INST] {instruction} [/INST]"
-    no_input_format: "[INST] {instruction} [/INST]"
 dataset_prepared_path:
 val_set_size: 0.05
 output_dir: ./out
@@ -44,12 +46,12 @@ eval_sample_packing: false
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name: Neural-DPO
 wandb_log_model:
 gradient_accumulation_steps: 4
 micro_batch_size: 2
-num_epochs: 6
 optimizer: adamw_bnb_8bit
 lr_scheduler: cosine
 learning_rate: 0.000005
@@ -72,7 +74,7 @@ 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
@@ -89,7 +91,7 @@ special_tokens:
 # out
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
 ## Model description
@@ -117,7 +119,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- training_steps: 801
 ### Training results
@@ -127,5 +129,5 @@ The following hyperparameters were used during training:
 - Transformers 4.38.0.dev0
 - Pytorch 2.2.0+cu121
-- Datasets 2.17.1
 - Tokenizers 0.15.0

 ---
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
+datasets: NeuralNovel/Neural-DPO
 tags:
 - generated_from_trainer
 model-index:
     split: train
     type: chatml.intel
     format: "[INST] {instruction} [/INST]"
+    no_input_format: "[INST] {instruction} [/INST]"
 dataset_prepared_path:
 val_set_size: 0.05
 output_dir: ./out
 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
 evals_per_epoch: 4
 eval_table_size:
 eval_max_new_tokens: 128
+saves_per_epoch: 1
 debug:
 deepspeed:
 weight_decay: 0.0
 # out
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the Neural-DPO dataset with laserRMT applied.
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
+- training_steps: 134
 ### Training results
 - Transformers 4.38.0.dev0
 - Pytorch 2.2.0+cu121
+- Datasets 2.17.0
 - Tokenizers 0.15.0