Instructions to use Tarek07/Alkahest-V4-LLaMa-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tarek07/Alkahest-V4-LLaMa-70B with Transformers:

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

pipe = pipeline("text-generation", model="Tarek07/Alkahest-V4-LLaMa-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Tarek07/Alkahest-V4-LLaMa-70B")
model = AutoModelForMultimodalLM.from_pretrained("Tarek07/Alkahest-V4-LLaMa-70B")
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 Tarek07/Alkahest-V4-LLaMa-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tarek07/Alkahest-V4-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": "Tarek07/Alkahest-V4-LLaMa-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tarek07/Alkahest-V4-LLaMa-70B

SGLang

How to use Tarek07/Alkahest-V4-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 "Tarek07/Alkahest-V4-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": "Tarek07/Alkahest-V4-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 "Tarek07/Alkahest-V4-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": "Tarek07/Alkahest-V4-LLaMa-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tarek07/Alkahest-V4-LLaMa-70B with Docker Model Runner:
```
docker model run hf.co/Tarek07/Alkahest-V4-LLaMa-70B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Alkahest is part of my ongoing experiments with merging specialized curated models. It has a few occasional logic hiccups, but it's creativity more than makes up for it. Might just require a swipe here and there.

As for samplers, the model is very creative at 0.02 min P and 1 temp but increasing the min P might be necessary to help cull some minor coherency issues.

Because of the nature of this sort of 'Hyper Multi Model Merge', my recommendation is not to run this on anything lower than a Q5 quant.

If you enjoy my work, please consider supporting me, It helps me make more models like this! Support on KO-FI <3

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using TareksLab/Stylizer-V2-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:
  - model: TareksLab/Wordsmith-V9-LLaMa-70B
    parameters:
      weight: 0.25
      density: 0.5
  - model: TareksLab/Malediction-V2-LLaMa-70B
    parameters:
      weight: 0.25
      density: 0.5
  - model: TareksLab/Dungeons-and-Dragons-V1.2-LLaMa-70B
    parameters:
      weight: 0.25
      density: 0.5
  - model: TareksLab/Stylizer-V2-LLaMa-70B
    parameters:
      weight: 0.25
      density: 0.5
merge_method: dare_ties
base_model: TareksLab/Stylizer-V2-LLaMa-70B
parameters:
  normalize: false
out_dtype: bfloat16
chat_template: llama3
tokenizer:
 source: base