Downloads · 30 days
20
1% of all-time downloads
RichardErkhov/Tremontaine_-_L3-Lunaris-v1-15B-gguf
Tremontaine_-_L3-Lunaris-v1-15B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
20
1% of all-time downloads
All-time downloads
1.5K
Public
Repo size
147 GB
Likes
0
Public
Click a slice to open those files.
.gguf167 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
L3-Lunaris-v1-15B - GGUF
| 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 |
base_model:
L3-Lunaris-v1-15B is a merge of the following model with itself using LazyMergekit:
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
!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"])