Instructions to use KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees with Transformers:

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

pipe = pipeline("text-generation", model="KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees")
model = AutoModelForCausalLM.from_pretrained("KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees

SGLang

How to use KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees 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 "KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees" \
    --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": "KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees",
		"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 "KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees" \
        --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": "KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees with Docker Model Runner:
```
docker model run hf.co/KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Good Evening.

New model mix because I got frustrated of dealing with wrangling with parameters and I chalked it up to a "Seems like a model issue".

Going back to merge stock since i dont feel like experimenting and want to try something that vibes well out of the box.

Prompt Format

ChatML works. Same goes for L3 chat.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Llama-3.3-70B-Instruct 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:
  - model: Blackroot/Mirai-3.0-70B
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
  - model: TheDrummer/Anubis-70B-v1
  - model: Sao10K/L3.3-70B-Euryale-v2.3
  - model: Sao10K/70B-L3.3-Cirrus-x1
  - model: nitky/Llama-3.3-SuperSwallowX-70B-Instruct-v0.1
  - model: KaraKaraWitch/Llama-MiraiFanfare-2-3.3-70B
  - model: Undi95/Sushi-v1.4
  - model: Nohobby/L3.3-Prikol-70B-v0.2

merge_method: model_stock
base_model: Llama-3.3-70B-Instruct
parameters:
  normalize: true
dtype: bfloat16