Downloads · 30 days
56
6% of all-time downloads
allknowingroger_-_M7-8B-passthrough-gguf
RichardErkhov/allknowingroger_-_M7-8B-passthrough-gguf
allknowingroger_-_M7-8B-passthrough-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.
All-time downloads
936
Public
Repo size
122 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf141 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 19, 2024
- Updated
- Jul 20, 2024
- SHA
- 585840d4
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
M7-8B-passthrough - GGUF
- Model creator: https://huggingface.co/allknowingroger/
- Original model: https://huggingface.co/allknowingroger/M7-8B-passthrough/
| Name | Quant method | Size |
|---|---|---|
| M7-8B-passthrough.Q2_K.gguf | Q2_K | 3.73GB |
| M7-8B-passthrough.IQ3_XS.gguf | IQ3_XS | 4.14GB |
| M7-8B-passthrough.IQ3_S.gguf | IQ3_S | 4.37GB |
| M7-8B-passthrough.Q3_K_S.gguf | Q3_K_S | 4.34GB |
| M7-8B-passthrough.IQ3_M.gguf | IQ3_M | 4.51GB |
| M7-8B-passthrough.Q3_K.gguf | Q3_K | 4.84GB |
| M7-8B-passthrough.Q3_K_M.gguf | Q3_K_M | 4.84GB |
| M7-8B-passthrough.Q3_K_L.gguf | Q3_K_L | 5.26GB |
| M7-8B-passthrough.IQ4_XS.gguf | IQ4_XS | 5.43GB |
| M7-8B-passthrough.Q4_0.gguf | Q4_0 | 5.66GB |
| M7-8B-passthrough.IQ4_NL.gguf | IQ4_NL | 5.72GB |
| M7-8B-passthrough.Q4_K_S.gguf | Q4_K_S | 5.7GB |
| M7-8B-passthrough.Q4_K.gguf | Q4_K | 6.02GB |
| M7-8B-passthrough.Q4_K_M.gguf | Q4_K_M | 6.02GB |
| M7-8B-passthrough.Q4_1.gguf | Q4_1 | 6.27GB |
| M7-8B-passthrough.Q5_0.gguf | Q5_0 | 6.89GB |
| M7-8B-passthrough.Q5_K_S.gguf | Q5_K_S | 6.89GB |
| M7-8B-passthrough.Q5_K.gguf | Q5_K | 7.08GB |
| M7-8B-passthrough.Q5_K_M.gguf | Q5_K_M | 7.08GB |
| M7-8B-passthrough.Q5_1.gguf | Q5_1 | 7.51GB |
| M7-8B-passthrough.Q6_K.gguf | Q6_K | 8.2GB |
| M7-8B-passthrough.Q8_0.gguf | Q8_0 | 10.62GB |
Original model description:
tags:
- merge
- mergekit
- lazymergekit
- liminerity/M7-7b base_model:
- liminerity/M7-7b
- liminerity/M7-7b
- liminerity/M7-7b
- liminerity/M7-7b
- liminerity/M7-7b license: apache-2.0
M7-8B-passthrough
M7-8B-passthrough is a merge of the following models using LazyMergekit:
🧩 Configuration
dtype: float16
merge_method: passthrough
slices:
- sources:
- model: liminerity/M7-7b
layer_range: [0,9]
- sources:
- model: liminerity/M7-7b
layer_range: [5,14]
- sources:
- model: liminerity/M7-7b
layer_range: [10,19]
- sources:
- model: liminerity/M7-7b
layer_range: [15,24]
- sources:
- model: liminerity/M7-7b
layer_range: [20,32]
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "allknowingroger/M7-8B-passthrough"
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"])
- Created
- Jul 19, 2024
- Updated
- Jul 20, 2024