Instructions to use TareksGraveyard/Thalassic-Delta-LLaMa-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TareksGraveyard/Thalassic-Delta-LLaMa-70B with Transformers:

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

pipe = pipeline("text-generation", model="TareksGraveyard/Thalassic-Delta-LLaMa-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TareksGraveyard/Thalassic-Delta-LLaMa-70B")
model = AutoModelForCausalLM.from_pretrained("TareksGraveyard/Thalassic-Delta-LLaMa-70B", 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 TareksGraveyard/Thalassic-Delta-LLaMa-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TareksGraveyard/Thalassic-Delta-LLaMa-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TareksGraveyard/Thalassic-Delta-LLaMa-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TareksGraveyard/Thalassic-Delta-LLaMa-70B

SGLang

How to use TareksGraveyard/Thalassic-Delta-LLaMa-70B 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 "TareksGraveyard/Thalassic-Delta-LLaMa-70B" \
    --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": "TareksGraveyard/Thalassic-Delta-LLaMa-70B",
		"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 "TareksGraveyard/Thalassic-Delta-LLaMa-70B" \
        --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": "TareksGraveyard/Thalassic-Delta-LLaMa-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TareksGraveyard/Thalassic-Delta-LLaMa-70B with Docker Model Runner:
```
docker model run hf.co/TareksGraveyard/Thalassic-Delta-LLaMa-70B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

I messed around with the the ingredients in the Thalassic series, essentially testing how much of an effect the base and pivot models had on the merge. In my opinion, this is the best of the Thalassic models.

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using SicariusSicariiStuff/Negative_LLAMA_70B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  # Pivot model
  - model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
  # Target models
  - model: Sao10K/70B-L3.3-Cirrus-x1
  - model: Sao10K/L3.1-70B-Hanami-x1
  - model: TheDrummer/Anubis-70B-v1
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
merge_method: sce
base_model: SicariusSicariiStuff/Negative_LLAMA_70B
parameters:
  select_topk: 1.0
dtype: bfloat16