Instructions to use rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("aeon37/Llama-3.3-8B-Instruct-128K-heretic")
model = PeftModel.from_pretrained(base_model, "rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora")

Transformers

How to use rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora with Transformers:

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

pipe = pipeline("text-generation", model="rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora")
model = AutoModelForCausalLM.from_pretrained("rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora", device_map="auto")
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 rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora

SGLang

How to use rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora 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 "rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora" \
    --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": "rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora",
		"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 "rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora" \
        --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": "rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora with Docker Model Runner:
```
docker model run hf.co/rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora
```

See axolotl config

axolotl version: 0.15.0.dev0

base_model: aeon37/Llama-3.3-8B-Instruct-128K-heretic
#deepspeed: zero1_torch_compile.json # deepspeed_configs/zero1.json

# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

  #plugins:
  # - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

load_in_8bit: false
load_in_4bit: true 


datasets:
  - path: ramendik/kimify-ifeval-like
    type: chat_template
    # drop_system_message: true
    field_messages: messages
    # roles_to_train: ["assistant", "user"]
  - path: ramendik/kimify-20251115
    type: chat_template
    # drop_system_message: true
    field_messages: messages
  - path: ramendik/kimify-short-20260131
    type: chat_template
    # drop_system_message: true
    field_messages: messages


dataset_prepared_path: last_run_prepared_kimi
val_set_size: 0.1
output_dir: ./outputs/llama3.3-miki-lora-out
special_tokens:
 pad_token: <|end_of_text|>

adapter: qlora
lora_model_dir:

sequence_len: 2048
sample_packing: true

lora_r: 16
lora_alpha: 8
lora_dropout: 0.05
lora_target_linear: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

use_wandb: true
wandb_project: Llama-3.3-8B-Instruct-128k-heretic-Kimi-miki
wandb_entity: 
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs: 
    use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch: 0
saves_per_epoch: 5 

save_first_step: true  # uncomment this to validate checkpoint saving works with your config

outputs/llama3.3-miki-lora-out

This model is a fine-tuned version of aeon37/Llama-3.3-8B-Instruct-128K-heretic on the ramendik/kimify-ifeval-like, the ramendik/kimify-20251115 and the ramendik/kimify-short-20260131 datasets.

Model description

Without system prompts. Provided Lora so you can check what strenght to merge it with the model for best results. Untested !!

Intended uses & limitations

More information needed

llama-server -hf noctrex/Llama-3.3-8B-Instruct-128k-abliterated-GGUF:Q8_0 --lora-scaled rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora 0.5 --lora-scaled rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora 0.7 --lora-scaled rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora 1.0 --port 8111 --host 0.0.0.0 -n 128000

Training and evaluation data

More information needed

paged_adamw_8bit can raise the batch size a bit more for quicker training, but results in some spikes.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 16
total_eval_batch_size: 4
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: cosine
lr_scheduler_warmup_steps: 103
training_steps: 1032

Training results

Could have trained for 2.4 epoch, seems a bit overfill.

Framework versions

PEFT 0.18.1
Transformers 5.0.0
Pytorch 2.9.1+cu128
Datasets 4.5.0
Tokenizers 0.22.2

Downloads last month: 5

Model tree for rekrek/Llama-3.3-8B-Instruct-128K-heretic-kimified-lora

Base model

aeon37/Llama-3.3-8B-Instruct-128K-heretic

Adapter

(1)

this model

rekrek
/

Llama-3.3-8B-Instruct-128K-heretic-kimified-lora