Instructions to use allura-forge/g3.3-sft-adpts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allura-forge/g3.3-sft-adpts with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-3.3-8b-instruct")
model = PeftModel.from_pretrained(base_model, "allura-forge/g3.3-sft-adpts")

Transformers

How to use allura-forge/g3.3-sft-adpts with Transformers:

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

pipe = pipeline("text-generation", model="allura-forge/g3.3-sft-adpts")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allura-forge/g3.3-sft-adpts")
model = AutoModelForCausalLM.from_pretrained("allura-forge/g3.3-sft-adpts")
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 allura-forge/g3.3-sft-adpts with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allura-forge/g3.3-sft-adpts"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allura-forge/g3.3-sft-adpts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allura-forge/g3.3-sft-adpts

SGLang

How to use allura-forge/g3.3-sft-adpts 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 "allura-forge/g3.3-sft-adpts" \
    --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": "allura-forge/g3.3-sft-adpts",
		"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 "allura-forge/g3.3-sft-adpts" \
        --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": "allura-forge/g3.3-sft-adpts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allura-forge/g3.3-sft-adpts with Docker Model Runner:
```
docker model run hf.co/allura-forge/g3.3-sft-adpts
```

See axolotl config

axolotl version: 0.12.0.dev0

# === Model Configuration ===
base_model: ibm-granite/granite-3.3-8b-instruct
load_in_8bit: false
load_in_4bit: false

# === Training Setup ===
num_epochs: 2
micro_batch_size: 4
gradient_accumulation_steps: 4
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

# === LoRA Configuration ===
adapter: lora
lora_r: 128
lora_alpha: 16
lora_dropout: 0.35
lora_target_modules:
lora_target_linear: true
peft_use_rslora: true
max_grad_norm: 0.1

chunked_cross_entropy: true

# === Hyperparameter Configuration ===
optimizer: adamw_torch_fused
learning_rate: 2e-6
lr_scheduler: rex
weight_decay: 0.01
warmup_ratio: 0.05
cosine_min_lr_ratio: 0.1

# === Data Configuration ===
datasets:
  - path: allura-forge/fuckedup-inkmix
    type: chat_template
    split: train
    field_messages: conversations
    message_field_role: from
    message_field_content: value
chat_template: jinja
chat_template_jinja: |
  {%- for message in messages -%}
    {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
  ' -}}
    {%- if loop.last and add_generation_prompt -%}
        {{- '<|start_of_role|>assistant<|end_of_role|>' -}}
    {%- endif -%}
  {%- endfor -%}
  
  

dataset_prepared_path: last_run_prepared

# === Hardware Optimization ===
gradient_checkpointing: true

# === Wandb Tracking ===
wandb_project: frizzite-fuckedup-inkmix

# === Checkpointing ===
saves_per_epoch: 2
save_only_model: true

# === Advanced Settings ===
output_dir: ./frizzite-small-ckpts
bf16: auto
flash_attention: true
train_on_inputs: false
group_by_length: false
logging_steps: 1
trust_remote_code: true

frizzite-small-ckpts

This model is a fine-tuned version of ibm-granite/granite-3.3-8b-instruct on the allura-forge/fuckedup-inkmix 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-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
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
lr_scheduler_warmup_steps: 46
training_steps: 926

Training results

Framework versions

PEFT 0.16.0
Transformers 4.53.2
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.21.2

Downloads last month: -

Model tree for allura-forge/g3.3-sft-adpts

Base model

ibm-granite/granite-3.3-8b-base

Finetuned

ibm-granite/granite-3.3-8b-instruct

Adapter

(6)

this model