YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
Wernicke-7B-v8 - GGUF
- Model creator: https://huggingface.co/CultriX/
- Original model: https://huggingface.co/CultriX/Wernicke-7B-v8/
Name | Quant method | Size |
---|---|---|
Wernicke-7B-v8.Q2_K.gguf | Q2_K | 2.53GB |
Wernicke-7B-v8.IQ3_XS.gguf | IQ3_XS | 2.81GB |
Wernicke-7B-v8.IQ3_S.gguf | IQ3_S | 2.96GB |
Wernicke-7B-v8.Q3_K_S.gguf | Q3_K_S | 2.95GB |
Wernicke-7B-v8.IQ3_M.gguf | IQ3_M | 3.06GB |
Wernicke-7B-v8.Q3_K.gguf | Q3_K | 3.28GB |
Wernicke-7B-v8.Q3_K_M.gguf | Q3_K_M | 3.28GB |
Wernicke-7B-v8.Q3_K_L.gguf | Q3_K_L | 3.56GB |
Wernicke-7B-v8.IQ4_XS.gguf | IQ4_XS | 3.67GB |
Wernicke-7B-v8.Q4_0.gguf | Q4_0 | 3.83GB |
Wernicke-7B-v8.IQ4_NL.gguf | IQ4_NL | 3.87GB |
Wernicke-7B-v8.Q4_K_S.gguf | Q4_K_S | 3.86GB |
Wernicke-7B-v8.Q4_K.gguf | Q4_K | 4.07GB |
Wernicke-7B-v8.Q4_K_M.gguf | Q4_K_M | 4.07GB |
Wernicke-7B-v8.Q4_1.gguf | Q4_1 | 4.24GB |
Wernicke-7B-v8.Q5_0.gguf | Q5_0 | 4.65GB |
Wernicke-7B-v8.Q5_K_S.gguf | Q5_K_S | 4.65GB |
Wernicke-7B-v8.Q5_K.gguf | Q5_K | 4.78GB |
Wernicke-7B-v8.Q5_K_M.gguf | Q5_K_M | 4.78GB |
Wernicke-7B-v8.Q5_1.gguf | Q5_1 | 5.07GB |
Wernicke-7B-v8.Q6_K.gguf | Q6_K | 5.53GB |
Wernicke-7B-v8.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
tags: - merge - mergekit - lazymergekit - kaitchup/Mayonnaise-4in1-022 - macadeliccc/WestLake-7B-v2-laser-truthy-dpo - vanillaOVO/supermario_v2 - FelixChao/WestSeverus-7B-DPO-v2 base_model: - kaitchup/Mayonnaise-4in1-022 - macadeliccc/WestLake-7B-v2-laser-truthy-dpo - vanillaOVO/supermario_v2 - FelixChao/WestSeverus-7B-DPO-v2 license: apache-2.0
Wernicke-7B-v8
Wernicke-7B-v8 is a merge of the following models using LazyMergekit:
- kaitchup/Mayonnaise-4in1-022
- macadeliccc/WestLake-7B-v2-laser-truthy-dpo
- vanillaOVO/supermario_v2
- FelixChao/WestSeverus-7B-DPO-v2
𧩠Configuration
models:
- model: CultriX/Wernicke-7B-v1
# No parameters necessary for base model
- model: kaitchup/Mayonnaise-4in1-022
parameters:
density: 0.53
weight: 0.40
- model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
parameters:
density: 0.53
weight: 0.25
- model: vanillaOVO/supermario_v2
parameters:
density: 0.53
weight: 0.25
- model: FelixChao/WestSeverus-7B-DPO-v2
parameters:
density: 0.53
weight: 0.20
merge_method: dare_ties
base_model: CultriX/Wernicke-7B-v1
parameters:
int8_mask: true
dtype: float16
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "CultriX/Wernicke-7B-v8"
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"])
- Downloads last month
- 43