Instructions to use allura-forge/q3527rpslopadptep1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allura-forge/q3527rpslopadptep1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-27B")
model = PeftModel.from_pretrained(base_model, "allura-forge/q3527rpslopadptep1")

Transformers

How to use allura-forge/q3527rpslopadptep1 with Transformers:

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

pipe = pipeline("text-generation", model="allura-forge/q3527rpslopadptep1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("allura-forge/q3527rpslopadptep1")
model = AutoModelForImageTextToText.from_pretrained("allura-forge/q3527rpslopadptep1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use allura-forge/q3527rpslopadptep1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allura-forge/q3527rpslopadptep1"
# 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/q3527rpslopadptep1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allura-forge/q3527rpslopadptep1

SGLang

How to use allura-forge/q3527rpslopadptep1 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/q3527rpslopadptep1" \
    --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/q3527rpslopadptep1",
		"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/q3527rpslopadptep1" \
        --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/q3527rpslopadptep1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allura-forge/q3527rpslopadptep1 with Docker Model Runner:
```
docker model run hf.co/allura-forge/q3527rpslopadptep1
```

See axolotl config

axolotl version: 0.16.0.dev0

# === Model Configuration ===
base_model: Qwen/Qwen3.5-27B
load_in_8bit: false
load_in_4bit: false

# === Training Setup ===
num_epochs: 1
micro_batch_size: 4
gradient_accumulation_steps: 8
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_r: 64
lora_alpha: 512
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - down_proj
  - up_proj
  - linear_attn.in_proj_qkv
  - linear_attn.in_proj_z
  - linear_attn.out_proj

# === Hyperparameter Configuration ===
optimizer: adamw_torch_8bit
learning_rate: 1e-5
lr_scheduler: constant
weight_decay: 0.001
max_grad_norm: 0.1
warmup_ratio: 0.05
cosine_min_lr_ratio: 0.1

# === Data Configuration ===
datasets:
  - path: doubao-seed2.0-claude-distill-hs3-nothink.parquet
    ds_type: parquet
    type: 
  - path: doubao-seed2.0-claude-distill-hs3.parquet
    ds_type: parquet
    type: 
  - path: doubao-seed2.0-claude-distill-hs3-nothink.parquet
    ds_type: parquet
    type: 
  - path: doubao-seed2.0-claude-distill-hs3.parquet
    ds_type: parquet
    type: 
  - path: expr-rp-sft-mix.parquet
    ds_type: parquet
    type: 

chat_template: tokenizer_default

dataset_prepared_path: last_run_prepared

# === Hardware Optimization ===
gradient_checkpointing: offload

# === Wandb Tracking ===
wandb_project: qwen-27b-rpslop

# === Checkpointing ===
saves_per_epoch: 1

# === Advanced Settings ===
output_dir: ./model-output
bf16: auto
flash_attention: true
train_on_inputs: false
group_by_length: false
logging_steps: 1
trust_remote_code: false

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

model-output

This model is a fine-tuned version of Qwen/Qwen3.5-27B on the doubao-seed2.0-claude-distill-hs3-nothink.parquet, the doubao-seed2.0-claude-distill-hs3.parquet, the doubao-seed2.0-claude-distill-hs3-nothink.parquet, the doubao-seed2.0-claude-distill-hs3.parquet and the expr-rp-sft-mix.parquet datasets.

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 10
training_steps: 211

Training results

Framework versions

PEFT 0.18.1
Transformers 5.3.0
Pytorch 2.8.0+cu128
Datasets 4.5.0
Tokenizers 0.22.2

Downloads last month: 1

Model tree for allura-forge/q3527rpslopadptep1

Base model

Qwen/Qwen3.5-27B

Adapter

(77)

this model