Instructions to use Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat with Transformers:

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

pipe = pipeline("text-generation", model="Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat")
model = AutoModelForCausalLM.from_pretrained("Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat

SGLang

How to use Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat 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 "Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat" \
    --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": "Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat",
		"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 "Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat" \
        --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": "Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat with Docker Model Runner:
```
docker model run hf.co/Nexesenex/Llama_3.x_70b_SmarTricks_v1.30_flat
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

about

Successor of SmartTricks 1.30.

Flat means a single level merge, not a 3 stages merges.
This, to avoid models being "averaged over and over" until it becomes too "soupy", even if benching right.
In other words, limiting the number of consecutive merges to preserve as much as possible the features of each model.

benchs

PPL much better than Smartricks v1.30.

IK_LLama.CPP Benchs in IQ6_K:

PPL-512 WikiEng Text 564 : 3.33
ARC-C 299 : 60.20
ARC-E 570 : 82.28
Hellaswag 200 : 88
Winogrande 1263 : 81.53
MMLU : 46.64

MMLU results are much lower than they should be on LlamaCPP. This is a constant quirk since 2024.

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using huihui-ai/Llama-3.3-70B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
models:
  - model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
    parameters:
      weight: 1.0
  - model: huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
    parameters:
      weight: 1.0
  - model: huihui-ai/Llama-3.1-Tulu-3-70B-abliterated
    parameters:
      weight: 1.0
  - model: hitachi-nlp/Llama-3.1-70B-FLDx2
    parameters:
      weight: 1.0
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: false
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union