Instructions to use Edens-Gate/ministral-tor-r1-e2212 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Edens-Gate/ministral-tor-r1-e2212 with Transformers:

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

pipe = pipeline("text-generation", model="Edens-Gate/ministral-tor-r1-e2212")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Edens-Gate/ministral-tor-r1-e2212")
model = AutoModelForCausalLM.from_pretrained("Edens-Gate/ministral-tor-r1-e2212")
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 Edens-Gate/ministral-tor-r1-e2212 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Edens-Gate/ministral-tor-r1-e2212"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Edens-Gate/ministral-tor-r1-e2212",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Edens-Gate/ministral-tor-r1-e2212

SGLang

How to use Edens-Gate/ministral-tor-r1-e2212 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 "Edens-Gate/ministral-tor-r1-e2212" \
    --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": "Edens-Gate/ministral-tor-r1-e2212",
		"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 "Edens-Gate/ministral-tor-r1-e2212" \
        --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": "Edens-Gate/ministral-tor-r1-e2212",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Edens-Gate/ministral-tor-r1-e2212 with Docker Model Runner:
```
docker model run hf.co/Edens-Gate/ministral-tor-r1-e2212
```

See axolotl config

axolotl version: 0.4.1

base_model: ./prince-canuma_Ministral-8B-Instruct-2410-HF
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Story-writing-Alt-Data-sharegpt
    type: sharegpt
    conversation: chatml
  - path: NewEden/Misc-Phase-Sharegpt
    type: sharegpt
    conversation: chatml
  - path: NewEden/Synth-RP-Phase-sharegpt
    type: sharegpt
    conversation: chatml
  - path: NewEden/Claude-instruct-Merged-Sharegpt
    type: sharegpt
    conversation: chatml
  - path: NewEden/Intelligence-Phase-Sharegpt
    type: sharegpt
    conversation: chatml
chat_template: chatml

output_dir: ./ministral_outputs

  #adapter: lora
  #lora_r: 128
  #lora_alpha: 16
  #lora_dropout:  0.05
  #lora_target_linear: true
  #peft_use_rslora: true
  #lora_modules_to_save:
  #- embed_tokens
  #- lm_head

sequence_len: 16384
  #sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true


wandb_project: Ministral-Tor
wandb_entity:
wandb_watch:
wandb_name: run-1
wandb_log_model:


plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-5

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

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
#auto_resume_from_checkpoints: true
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 30
eval_table_size:
saves_per_epoch: 1
weight_decay: 0.1
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
  #deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
  #deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<pad>"

ministral_outputs

This model was trained from scratch on the None 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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 16
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 30
num_epochs: 2

Training results

Framework versions

Transformers 4.45.2
Pytorch 2.3.1+cu121
Datasets 3.0.1
Tokenizers 0.20.1

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

BF16