Instructions to use giux78/zagreus-test-202000-sft-11 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use giux78/zagreus-test-202000-sft-11 with Transformers:

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

pipe = pipeline("text-generation", model="giux78/zagreus-test-202000-sft-11")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("giux78/zagreus-test-202000-sft-11")
model = AutoModelForCausalLM.from_pretrained("giux78/zagreus-test-202000-sft-11")
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 giux78/zagreus-test-202000-sft-11 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "giux78/zagreus-test-202000-sft-11"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "giux78/zagreus-test-202000-sft-11",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/giux78/zagreus-test-202000-sft-11

SGLang

How to use giux78/zagreus-test-202000-sft-11 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 "giux78/zagreus-test-202000-sft-11" \
    --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": "giux78/zagreus-test-202000-sft-11",
		"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 "giux78/zagreus-test-202000-sft-11" \
        --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": "giux78/zagreus-test-202000-sft-11",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use giux78/zagreus-test-202000-sft-11 with Docker Model Runner:
```
docker model run hf.co/giux78/zagreus-test-202000-sft-11
```

See axolotl config

axolotl version: 0.9.2

   # ============= SFT DEBUG (~1M conv) =============
base_model: giux78/zagreus-test-202000
strict: false
output_dir: ./ale_outputs/opendata-sft-debug
seed: 42

datasets:
  - path: /leonardo_work/EUHPC_A04_045/training/opendata-1000000
    type: chat_template
    field_messages: conversation
    roles_to_train: ["assistant"]
    train_on_eos: turn

dataset_prepared_path: ./ale_outputs/dataset_cache/opendata-sft
#default_system_message: "Sei un assistente utile."
chat_template: llama3

sequence_len: 4096
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

optimizer: adamw_torch_fused
lr_scheduler: constant_with_warmup   # <-- per isolare il comportamento
learning_rate: 1.5e-5
warmup_ratio: 0.05                   # un po’ più lungo in debug
weight_decay: 0.01
max_grad_norm: 1.0

micro_batch_size: 1
gradient_accumulation_steps: 8
# Usa max_steps per “più step” indipendentemente dalla lunghezza effettiva del dataset
max_steps: 2000                      # ≈ 4x gli step attuali
#num_epochs: null                     # ignora epoche quando max_steps è settato

bf16: auto
flash_attention: true
gradient_checkpointing: true

logging_steps: 10
eval_strategy: steps
eval_steps: 100
save_strategy: steps
save_steps: 200
save_total_limit: 2
val_set_size: 10000

fsdp_config:
  fsdp_sharding_strategy: FULL_SHARD
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
  fsdp_backward_prefetch_policy: BACKWARD_PRE
  fsdp_state_dict_type: FULL_STATE_DICT

special_tokens:
  pad_token: <|end_of_text|>
  eos_token: <|end_of_text|>

ale_outputs/opendata-sft-debug

This model is a fine-tuned version of giux78/zagreus-test-202000 on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.4891

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: 1.5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 32
gradient_accumulation_steps: 8
total_train_batch_size: 256
total_eval_batch_size: 32
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: constant_with_warmup
lr_scheduler_warmup_steps: 24
training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0020	1	3.7876
3.7673	0.2011	100	3.7540
3.7566	0.4022	200	3.7122
3.6861	0.6033	300	3.6780
3.6558	0.8044	400	3.6379
3.6057	1.0040	500	3.6005
3.5706	1.2051	600	3.5714
3.5991	1.4062	700	3.5497
3.561	1.6073	800	3.5329
3.5464	1.8084	900	3.5206
3.4594	2.0080	1000	3.5112
3.4559	2.2092	1100	3.5053
3.4955	2.4103	1200	3.5016
3.5145	2.6114	1300	3.4984
3.5199	2.8125	1400	3.4964
3.3811	3.0121	1500	3.4948
3.381	3.2132	1600	3.4935
3.4175	3.4143	1700	3.4922
3.4663	3.6154	1800	3.4911
3.447	3.8165	1900	3.4897
3.314	4.0161	2000	3.4891

Framework versions

Transformers 4.56.2
Pytorch 2.5.1+cu121
Datasets 3.5.1
Tokenizers 0.22.1

Downloads last month: 4

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for giux78/zagreus-test-202000-sft-11

Base model

giux78/zagreus-test-202000

Finetuned

(12)

this model