Instructions to use Raitocan/8BitsMastermind_go with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Raitocan/8BitsMastermind_go with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-chat-hf")
model = PeftModel.from_pretrained(base_model, "Raitocan/8BitsMastermind_go")

Transformers

How to use Raitocan/8BitsMastermind_go with Transformers:

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

pipe = pipeline("text-generation", model="Raitocan/8BitsMastermind_go")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Raitocan/8BitsMastermind_go", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Raitocan/8BitsMastermind_go with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Raitocan/8BitsMastermind_go"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Raitocan/8BitsMastermind_go",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Raitocan/8BitsMastermind_go

SGLang

How to use Raitocan/8BitsMastermind_go 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 "Raitocan/8BitsMastermind_go" \
    --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": "Raitocan/8BitsMastermind_go",
		"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 "Raitocan/8BitsMastermind_go" \
        --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": "Raitocan/8BitsMastermind_go",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Raitocan/8BitsMastermind_go with Docker Model Runner:
```
docker model run hf.co/Raitocan/8BitsMastermind_go
```

8BitsMastermind_go

This model is a fine-tuned version of NousResearch/Llama-2-7b-chat-hf on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 7.9128
Scoremae: 10.0
Winratemae: 1.0
Rouge-l: 0.3841

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 5
eval_batch_size: 10
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 3000
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Scoremae	Winratemae	Rouge-l
No log	0.0110	1	8.4443	10.0	1.0	0.3821
No log	1.0	91	7.9128	10.0	1.0	0.3841

Framework versions

PEFT 0.20.0
Transformers 5.15.1
Pytorch 2.11.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: 19

Model tree for Raitocan/8BitsMastermind_go

Base model

NousResearch/Llama-2-7b-chat-hf

Adapter

(464)

this model