Downloads · 30 days
71
3% of all-time downloads
RichardErkhov/luqmanxyz_-_FrankenVillain-7B-v1-gguf
luqmanxyz_-_FrankenVillain-7B-v1-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
71
3% of all-time downloads
All-time downloads
2.7K
Public
Repo size
122 GB
Likes
0
Public
Click a slice to open those files.
.gguf141 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
FrankenVillain-7B-v1 - GGUF
| Name | Quant method | Size |
|---|---|---|
| FrankenVillain-7B-v1.Q2_K.gguf | Q2_K | 3.73GB |
| FrankenVillain-7B-v1.IQ3_XS.gguf | IQ3_XS | 4.14GB |
| FrankenVillain-7B-v1.IQ3_S.gguf | IQ3_S | 4.37GB |
| FrankenVillain-7B-v1.Q3_K_S.gguf | Q3_K_S | 4.34GB |
| FrankenVillain-7B-v1.IQ3_M.gguf | IQ3_M | 4.51GB |
| FrankenVillain-7B-v1.Q3_K.gguf | Q3_K | 4.84GB |
| FrankenVillain-7B-v1.Q3_K_M.gguf | Q3_K_M | 4.84GB |
| FrankenVillain-7B-v1.Q3_K_L.gguf | Q3_K_L | 5.26GB |
| FrankenVillain-7B-v1.IQ4_XS.gguf | IQ4_XS | 5.43GB |
| FrankenVillain-7B-v1.Q4_0.gguf | Q4_0 | 5.66GB |
| FrankenVillain-7B-v1.IQ4_NL.gguf | IQ4_NL | 5.72GB |
| FrankenVillain-7B-v1.Q4_K_S.gguf | Q4_K_S | 5.7GB |
| FrankenVillain-7B-v1.Q4_K.gguf | Q4_K | 6.02GB |
| FrankenVillain-7B-v1.Q4_K_M.gguf | Q4_K_M | 6.02GB |
| FrankenVillain-7B-v1.Q4_1.gguf | Q4_1 | 6.27GB |
| FrankenVillain-7B-v1.Q5_0.gguf | Q5_0 | 6.89GB |
| FrankenVillain-7B-v1.Q5_K_S.gguf | Q5_K_S | 6.89GB |
| FrankenVillain-7B-v1.Q5_K.gguf | Q5_K | 7.08GB |
| FrankenVillain-7B-v1.Q5_K_M.gguf | Q5_K_M | 7.08GB |
| FrankenVillain-7B-v1.Q5_1.gguf | Q5_1 | 7.51GB |
| FrankenVillain-7B-v1.Q6_K.gguf | Q6_K | 8.2GB |
| FrankenVillain-7B-v1.Q8_0.gguf | Q8_0 | 10.62GB |
license: apache-2.0 tags:
FrankenVillain-7B-v1 is a Franken merge of the following models using [mergekit](https://github.com/cg123/mergekit
slices:
- sources:
- model: jeonsworld/CarbonVillain-en-10.7B-v1
layer_range: [0, 24]
- sources:
- model: jeonsworld/CarbonVillain-en-10.7B-v1
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "luqmanxyz/FrankenVillain-7B-v1"
messages = [{"role": "user", "content": "What are the 3 planets closest to the sun"}]
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"])
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 45.34 |
| AI2 Reasoning Challenge (25-Shot) | 42.75 |
| HellaSwag (10-Shot) | 51.52 |
| MMLU (5-Shot) | 48.60 |
| TruthfulQA (0-shot) | 56.19 |
| Winogrande (5-shot) | 73.01 |
| GSM8k (5-shot) | 0.00 |