Instructions to use waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2")
model = AutoModelForCausalLM.from_pretrained("waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2")
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 waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2

SGLang

How to use waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2 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 "waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2" \
    --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": "waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2",
		"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 "waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2" \
        --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": "waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2 with Docker Model Runner:
```
docker model run hf.co/waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2
```

Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

Creator: SteelSkull

About Evayale-70B:

Name Legend:
L3.3 = Llama 3.3
MS = Model Stock
Evayale = mix of EVA-LLAMA-0.0 and EURYALE-v2.3
70B = its 70B

This model was created as I liked the storytelling of EVA but the prose and details of scenes from EURYALE, my goal is to merge the robust storytelling of both models while attempting to maintain the positives of both models.

My recommended Templates / System prompts: (List of Prompt-Gremlins)

LLam@ception <<< Template / System prompt [Made by @.konnect]

DWK-SP0.02 <<< System prompt [Made by @daimonwk]

Quants: (List of badasses) [will add once created]

GGUF Quant:

- bartowski: Combined-GGUF

- mradermacher: GGUF // Imat-GGUF

Config:

MODEL_NAME = "L3.3-MS-Evayale-70B"
base_model: unsloth/Llama-3.3-70B-Instruct
merge_method: model_stock
dtype: bfloat16
models:
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0
  - model: Sao10K/L3.3-70B-Euryale-v2.3

If you wish to support:

Downloads last month: 4

Model tree for waldie/L3.3-MS-Evayale-70B-2.25bpw-h6-exl2

Base model

SteelStorage/L3.3-MS-Evayale-70B

Quantized

(4)

this model