Instructions to use Guilherme34/secretmodel-indevelopment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Guilherme34/secretmodel-indevelopment with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("MuXodious/GLM-4.7-Flash-impotent-heresy")
model = PeftModel.from_pretrained(base_model, "Guilherme34/secretmodel-indevelopment")

Transformers

How to use Guilherme34/secretmodel-indevelopment with Transformers:

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

pipe = pipeline("text-generation", model="Guilherme34/secretmodel-indevelopment")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Guilherme34/secretmodel-indevelopment")
model = AutoModelForCausalLM.from_pretrained("Guilherme34/secretmodel-indevelopment")
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 Guilherme34/secretmodel-indevelopment with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Guilherme34/secretmodel-indevelopment"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Guilherme34/secretmodel-indevelopment",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Guilherme34/secretmodel-indevelopment

SGLang

How to use Guilherme34/secretmodel-indevelopment 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 "Guilherme34/secretmodel-indevelopment" \
    --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": "Guilherme34/secretmodel-indevelopment",
		"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 "Guilherme34/secretmodel-indevelopment" \
        --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": "Guilherme34/secretmodel-indevelopment",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Guilherme34/secretmodel-indevelopment with Docker Model Runner:
```
docker model run hf.co/Guilherme34/secretmodel-indevelopment
```

See axolotl config

axolotl version: 0.13.1

base_model: MuXodious/GLM-4.7-Flash-impotent-heresy # Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

#load_in_4bit: true

pretraining_dataset:
  - path: Guilherme34/Dataset-for-updating-llm-to-be-aware-of-the-situation
    type: pretrain
    text_column: text
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./outputs/qlora-out
save_steps: 45
adapter: lora
lora_model_dir:

sequence_len: 1024
sample_packing: true
eval_sample_packing: true


lora_r: 24
lora_alpha: 48
lora_dropout: 0.05
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
#num_epochs: 2
max_steps: 496
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.0002

bf16: true
tf32: false

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_ratio: 0.1
evals_per_epoch: 1
#saves_per_epoch: 1
weight_decay: 0.0

weight_decay: 0.0
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: true
  fsdp_use_orig_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: Glm4MoeLiteDecoderLayer
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
special_tokens:
  pad_token: <|endoftext|>

outputs/qlora-out

This model is a fine-tuned version of MuXodious/GLM-4.7-Flash-impotent-heresy on an unknown 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: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 2
total_eval_batch_size: 2
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: cosine
training_steps: 496

Training results

Framework versions

PEFT 0.18.1
Transformers 5.0.0rc3
Pytorch 2.10.0+cu130
Datasets 4.5.0
Tokenizers 0.22.2

Downloads last month: -

Model tree for Guilherme34/secretmodel-indevelopment

Base model

zai-org/GLM-4.7-Flash

Finetuned

MuXodious/GLM-4.7-Flash-impotent-heresy

Adapter

(1)

this model