ChaoticNeutrals
/

Prima-LelantaclesV6-7b

Text Generation

Eval Results (legacy)

text-generation-inference

Model card Files Files and versions

Instructions to use ChaoticNeutrals/Prima-LelantaclesV6-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChaoticNeutrals/Prima-LelantaclesV6-7b with Transformers:

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

pipe = pipeline("text-generation", model="ChaoticNeutrals/Prima-LelantaclesV6-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChaoticNeutrals/Prima-LelantaclesV6-7b")
model = AutoModelForCausalLM.from_pretrained("ChaoticNeutrals/Prima-LelantaclesV6-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ChaoticNeutrals/Prima-LelantaclesV6-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChaoticNeutrals/Prima-LelantaclesV6-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChaoticNeutrals/Prima-LelantaclesV6-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ChaoticNeutrals/Prima-LelantaclesV6-7b

How to use ChaoticNeutrals/Prima-LelantaclesV6-7b 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 "ChaoticNeutrals/Prima-LelantaclesV6-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChaoticNeutrals/Prima-LelantaclesV6-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ChaoticNeutrals/Prima-LelantaclesV6-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChaoticNeutrals/Prima-LelantaclesV6-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ChaoticNeutrals/Prima-LelantaclesV6-7b with Docker Model Runner:
```
docker model run hf.co/ChaoticNeutrals/Prima-LelantaclesV6-7b
```

General discussion.

#1

by Lewdiculous - opened Mar 1, 2024

👀

The Chaotic Neutrals org Mar 1, 2024

•

edited Mar 1, 2024

@Lewdiculous lmao its in the que for the leaderboard, but ive been testing locally and it cooks so far. Waiting to stretch the context after a few more ideas i want to get inside the model.

Curious for leaderboard results 👀

The Chaotic Neutrals org Mar 1, 2024

improvement but not much:

•

edited Mar 1, 2024 by

Hey, it's an improvement nonetheless! 👏

•

edited Mar 1, 2024

Prima-LelantaclesV6-7b-Q4_K_M-imatrix.gguf
Prima-LelantaclesV6-7b-Q4_K_S-imatrix.gguf
Prima-LelantaclesV6-7b-IQ4_NL-imatrix.gguf
Prima-LelantaclesV6-7b-IQ4_XS-imatrix.gguf (only supported in koboldcpp 1.60 or higher)
Prima-LelantaclesV6-7b-Q5_K_M-imatrix.gguf
Prima-LelantaclesV6-7b-Q5_K_S-imatrix.gguf
Prima-LelantaclesV6-7b-Q6_K-imatrix.gguf
Prima-LelantaclesV6-7b-Q8_0-imatrix.gguf
Prima-LelantaclesV6-7b-IQ3_M-imatrix.gguf
Prima-LelantaclesV6-7b-IQ3_S-imatrix.gguf
Prima-LelantaclesV6-7b-IQ3_XS-imatrix.gguf
Prima-LelantaclesV6-7b-IQ3_XXS-imatrix.gguf

The GGUF situation is getting intense XD

I think things are sort of getting re-unified again soon, maybe? Hopefully.

Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix

Fixed: Link

The Chaotic Neutrals org Mar 1, 2024

Appreciated as always! i went kind of nuts tonight and did a bunch of stuff. Will update with more information towards the weekend and as i have more time.

•

edited Mar 1, 2024

@Lewdiculous Is support coming in the next koboldcpp release or are you referring to 1.59.1? I cant find it in lostruins' releases

•

edited Mar 1, 2024

@saishf - Yes, I meant in the next release of KCPP, for the IQ4_XS support to be merged, this is the PR that needs to be merged downstream.

Okay, thank you!

The Chaotic Neutrals org Mar 2, 2024

•

edited Mar 2, 2024

The Chaotic Neutrals have cooked up a merge using the two front runner models from the org: Eris-7b coming soon. (LelantaclesV6 x Prodigy) from both jeiku and myself. https://huggingface.co/ChaoticNeutrals/Eris_7B

Great news. 🎉

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment