Instructions to use Jboadu/test-model-2-pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jboadu/test-model-2-pretrain with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jboadu/test-model-2-pretrain")
model = AutoModelForCausalLM.from_pretrained("Jboadu/test-model-2-pretrain")
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 Settings

vLLM

How to use Jboadu/test-model-2-pretrain with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Jboadu/test-model-2-pretrain

SGLang

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

Docker Model Runner
How to use Jboadu/test-model-2-pretrain with Docker Model Runner:
```
docker model run hf.co/Jboadu/test-model-2-pretrain
```

test-model-2-pretrain / README.md

Jboadu

End of training

76c5a60 verified 11 months ago

preview code

Raw

History Blame Contribute Delete

4.41 kB

metadata

library_name: transformers
license: apache-2.0
base_model: Jboadu/test-model-1-pretrain
tags:
  - axolotl
  - generated_from_trainer
datasets:
  - representation_variation_GAIA_Raw_Training_Data.jsonl
  - text_chunks_GAIA_Raw_Training_Data.jsonl
  - inferred_facts_GAIA_Raw_Training_Data.jsonl
model-index:
  - name: test-model-2-pretrain
    results: []

See axolotl config

axolotl version: 0.12.0

base_model: Jboadu/test-model-1-pretrain
tokenizer_type: AutoTokenizer
model_type: AutoModelForCausalLM
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: representation_variation_GAIA_Raw_Training_Data.jsonl
  type: completion
- path: text_chunks_GAIA_Raw_Training_Data.jsonl
  type: completion
- path: inferred_facts_GAIA_Raw_Training_Data.jsonl
  type: completion
dataset_prepared_path: last_run_prepared
output_dir: ./model-output
seed: 1337
sequence_len: 5000
sample_packing: true
pad_to_sequence_len: false
shuffle_merged_datasets: true
gradient_accumulation_steps: 75
micro_batch_size: 2
eval_batch_size: 4
num_epochs: 4
optimizer: paged_adamw_8bit
lr_scheduler: constant
learning_rate: 2.0e-05
noisy_embedding_alpha: 5
weight_decay: 0
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
logging_steps: 1
xformers_attention: false
flash_attention: true
chat_template: chatml
auto_resume_from_checkpoints: false
warmup_ratio: 0.1
evals_per_epoch: 1
val_set_size: 0.04
saves_per_epoch: 1
eval_sample_packing: false
save_total_limit: 2
special_tokens:
  pad_token: <unk>
use_liger_kernel: true
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_layer_norm: true
liger_fused_linear_cross_entropy: true
sequence_length: 10000
wandb_project: test-project
wandb_entity: ''
wandb_watch: ''
wandb_run_id: ''
wandb_log_model: ''
hub_model_id: Jboadu/test-model-2-pretrain
hub_strategy: all_checkpoints

test-model-2-pretrain

This model is a fine-tuned version of Jboadu/test-model-1-pretrain on the representation_variation_GAIA_Raw_Training_Data.jsonl, the text_chunks_GAIA_Raw_Training_Data.jsonl and the inferred_facts_GAIA_Raw_Training_Data.jsonl datasets. It achieves the following results on the evaluation set:

Loss: 0.9761
Memory/max Mem Active(gib): 31.49
Memory/max Mem Allocated(gib): 31.49
Memory/device Mem Reserved(gib): 33.08

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: 2
eval_batch_size: 4
seed: 1337
gradient_accumulation_steps: 75
total_train_batch_size: 150
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
training_steps: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Mem Active(gib)	Mem Allocated(gib)	Mem Reserved(gib)
No log	0	0	1.6467	19.79	19.79	24.59
3.0113	0.8021	2	1.8388	31.49	31.49	33.08
1.5032	1.4011	4	1.4474	31.49	31.49	33.08
1.1777	2.0	6	1.1725	31.49	31.49	33.08
0.9505	2.8021	8	0.9761	31.49	31.49	33.08

Framework versions

Transformers 4.55.0
Pytorch 2.7.1+cu128
Datasets 4.0.0
Tokenizers 0.21.4