Instructions to use hardlyworking/MS32-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hardlyworking/MS32-2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("model")
model = PeftModel.from_pretrained(base_model, "hardlyworking/MS32-2")

Transformers

How to use hardlyworking/MS32-2 with Transformers:

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

pipe = pipeline("text-generation", model="hardlyworking/MS32-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hardlyworking/MS32-2")
model = AutoModelForCausalLM.from_pretrained("hardlyworking/MS32-2")
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 hardlyworking/MS32-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hardlyworking/MS32-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hardlyworking/MS32-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hardlyworking/MS32-2

SGLang

How to use hardlyworking/MS32-2 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 "hardlyworking/MS32-2" \
    --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": "hardlyworking/MS32-2",
		"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 "hardlyworking/MS32-2" \
        --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": "hardlyworking/MS32-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hardlyworking/MS32-2 with Docker Model Runner:
```
docker model run hf.co/hardlyworking/MS32-2
```

See axolotl config

axolotl version: 0.12.0.dev0

base_model: model

hub_model_id: hardlyworking/MS32-2
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

load_in_8bit: false
load_in_4bit: true

chat_template: mistral_v7_tekken
datasets:
  - path: hardlyworking/HardlyRPv2-10k
    type: chat_template
    split: train
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value
      user: human
      assistant: gpt

val_set_size: 0.0
output_dir: ./outputs/out

adapter: qlora
lora_r: 32
lora_alpha: 16
lora_dropout: 0.0
lora_target_linear: true
peft_use_rslora: true


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

wandb_project: MS32-2
wandb_entity:
wandb_watch:
wandb_name: MS32-2
wandb_log_model:

gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

bf16: auto
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
  unsloth: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch:
saves_per_epoch: 4
weight_decay: 0.0025
special_tokens:

MS32-2

This model was trained from scratch on the hardlyworking/HardlyRPv2-10k dataset.

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: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 6
training_steps: 67

Training results

Framework versions

PEFT 0.17.0
Transformers 4.55.0
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 2

Model tree for hardlyworking/MS32-2

Merges

1 model

hardlyworking
/

MS32-2

MS32-2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for hardlyworking/MS32-2

Dataset used to train hardlyworking/MS32-2