Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


Halu-L3-Stheno-BlackOasis-8B - GGUF
- Model creator: https://huggingface.co/Casual-Autopsy/
- Original model: https://huggingface.co/Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Halu-L3-Stheno-BlackOasis-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q2_K.gguf) | Q2_K | 2.96GB |
| [Halu-L3-Stheno-BlackOasis-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
| [Halu-L3-Stheno-BlackOasis-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_S.gguf) | IQ3_S | 3.43GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
| [Halu-L3-Stheno-BlackOasis-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_M.gguf) | IQ3_M | 3.52GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K.gguf) | Q3_K | 3.74GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
| [Halu-L3-Stheno-BlackOasis-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q4_0.gguf) | Q4_0 | 4.34GB |
| [Halu-L3-Stheno-BlackOasis-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q4_K.gguf) | Q4_K | 4.58GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q4_1.gguf) | Q4_1 | 4.78GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q5_0.gguf) | Q5_0 | 5.21GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q5_K.gguf) | Q5_K | 5.34GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q5_1.gguf) | Q5_1 | 5.65GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q6_K.gguf) | Q6_K | 6.14GB |
| [Halu-L3-Stheno-BlackOasis-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q8_0.gguf) | Q8_0 | 7.95GB |




Original model description:
---
tags:
- merge
- mergekit
- lazymergekit
- not-for-all-audiences
license: llama3
language:
- en
library_name: transformers
pipeline_tag: text-generation
base_model:
- grimjim/Llama-3-Oasis-v1-OAS-8B
- Hastagaras/Halu-8B-Llama3-Blackroot
- Sao10K/L3-8B-Stheno-v3.2
---

# Halu-L3-Stheno-BlackOasis-8B

Halu-L3-Stheno-BlackOasis-8B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2)
    * [grimjim/Llama-3-Oasis-v1-OAS-8B](https://huggingface.co/grimjim/Llama-3-Oasis-v1-OAS-8B)
    * [Hastagaras/Halu-8B-Llama3-Blackroot](https://huggingface.co/Hastagaras/Halu-8B-Llama3-Blackroot)
    * [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2)

## 🧩 Configuration

```yaml
models:
  - model: grimjim/Llama-3-Oasis-v1-OAS-8B
  - model: Hastagaras/Halu-8B-Llama3-Blackroot
  - model: Sao10K/L3-8B-Stheno-v3.2
merge_method: model_stock
base_model: Sao10K/L3-8B-Stheno-v3.2
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```