You can deploy this model and start earning money today!

RichardErkhov/
Tremontaine_-_L3-Lunaris-v1-15B-gguf

Name: Tremontaine_-_L3-Lunaris-v1-15B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

L3-Lunaris-v1-15B - GGUF

Model creator: https://huggingface.co/Tremontaine/
Original model: https://huggingface.co/Tremontaine/L3-Lunaris-v1-15B/

Name	Quant method	Size
L3-Lunaris-v1-15B.Q2_K.gguf	Q2_K	5.35GB
L3-Lunaris-v1-15B.Q3_K_S.gguf	Q3_K_S	6.21GB
L3-Lunaris-v1-15B.Q3_K.gguf	Q3_K	3.32GB
L3-Lunaris-v1-15B.Q3_K_M.gguf	Q3_K_M	4.1GB
L3-Lunaris-v1-15B.Q3_K_L.gguf	Q3_K_L	2.57GB
L3-Lunaris-v1-15B.IQ4_XS.gguf	IQ4_XS	7.68GB
L3-Lunaris-v1-15B.Q4_0.gguf	Q4_0	8.0GB
L3-Lunaris-v1-15B.IQ4_NL.gguf	IQ4_NL	8.08GB
L3-Lunaris-v1-15B.Q4_K_S.gguf	Q4_K_S	8.05GB
L3-Lunaris-v1-15B.Q4_K.gguf	Q4_K	8.48GB
L3-Lunaris-v1-15B.Q4_K_M.gguf	Q4_K_M	8.48GB
L3-Lunaris-v1-15B.Q4_1.gguf	Q4_1	8.84GB
L3-Lunaris-v1-15B.Q5_0.gguf	Q5_0	9.68GB
L3-Lunaris-v1-15B.Q5_K_S.gguf	Q5_K_S	9.68GB
L3-Lunaris-v1-15B.Q5_K.gguf	Q5_K	9.93GB
L3-Lunaris-v1-15B.Q5_K_M.gguf	Q5_K_M	9.93GB
L3-Lunaris-v1-15B.Q5_1.gguf	Q5_1	10.53GB
L3-Lunaris-v1-15B.Q6_K.gguf	Q6_K	11.48GB
L3-Lunaris-v1-15B.Q8_0.gguf	Q8_0	14.86GB

Original model description:

base_model:

Sao10K/L3-8B-Lunaris-v1 tags:
merge
mergekit
lazymergekit
Sao10K/L3-8B-Lunaris-v1

L3-Lunaris-v1-15B

L3-Lunaris-v1-15B is a merge of the following model with itself using LazyMergekit:

Sao10K/L3-8B-Lunaris-v1

🧩 Configuration

yaml

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 24]
    model: Sao10K/L3-8B-Lunaris-v1
- sources:
  - layer_range: [8, 24]
    model: Sao10K/L3-8B-Lunaris-v1
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [8, 24]
    model: Sao10K/L3-8B-Lunaris-v1
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [24, 32]
    model: Sao10K/L3-8B-Lunaris-v1

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Tremontaine/L3-Lunaris-v1-15B"
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"])

RichardErkhov/Tremontaine_-_L3-Lunaris-v1-15B-gguf

Original model description:

L3-Lunaris-v1-15B

🧩 Configuration

💻 Usage

RichardErkhov/
Tremontaine_-_L3-Lunaris-v1-15B-gguf