Downloads · 30 days
5
1% of all-time downloads
winstcha_-_rewrite-7B-gguf
RichardErkhov/winstcha_-_rewrite-7B-gguf
winstcha_-_rewrite-7B-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
664
Public
Repo size
88.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf102 GB · 100%
At a glance
- Access
- Public
- Created
- Apr 21, 2025
- Updated
- Apr 21, 2025
- SHA
- 13fb9884
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
rewrite-7B - GGUF
- Model creator: https://huggingface.co/winstcha/
- Original model: https://huggingface.co/winstcha/rewrite-7B/
| Name | Quant method | Size |
|---|---|---|
| rewrite-7B.Q2_K.gguf | Q2_K | 2.81GB |
| rewrite-7B.IQ3_XS.gguf | IQ3_XS | 3.11GB |
| rewrite-7B.IQ3_S.gguf | IQ3_S | 3.26GB |
| rewrite-7B.Q3_K_S.gguf | Q3_K_S | 3.25GB |
| rewrite-7B.IQ3_M.gguf | IQ3_M | 3.33GB |
| rewrite-7B.Q3_K.gguf | Q3_K | 3.55GB |
| rewrite-7B.Q3_K_M.gguf | Q3_K_M | 3.55GB |
| rewrite-7B.Q3_K_L.gguf | Q3_K_L | 3.81GB |
| rewrite-7B.IQ4_XS.gguf | IQ4_XS | 3.96GB |
| rewrite-7B.Q4_0.gguf | Q4_0 | 4.13GB |
| rewrite-7B.IQ4_NL.gguf | IQ4_NL | 4.15GB |
| rewrite-7B.Q4_K_S.gguf | Q4_K_S | 4.15GB |
| rewrite-7B.Q4_K.gguf | Q4_K | 4.36GB |
| rewrite-7B.Q4_K_M.gguf | Q4_K_M | 4.36GB |
| rewrite-7B.Q4_1.gguf | Q4_1 | 4.54GB |
| rewrite-7B.Q5_0.gguf | Q5_0 | 4.95GB |
| rewrite-7B.Q5_K_S.gguf | Q5_K_S | 4.95GB |
| rewrite-7B.Q5_K.gguf | Q5_K | 5.07GB |
| rewrite-7B.Q5_K_M.gguf | Q5_K_M | 5.07GB |
| rewrite-7B.Q5_1.gguf | Q5_1 | 5.36GB |
| rewrite-7B.Q6_K.gguf | Q6_K | 5.82GB |
| rewrite-7B.Q8_0.gguf | Q8_0 | 7.54GB |
Original model description:
tags:
- autotrain
- text-generation-inference
- text-generation
- peft
library_name: transformers
base_model: Qwen/Qwen2.5-7B-Instruct
widget:
- messages:
- role: user content: What is your favorite condiment? license: other
- messages:
Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit AutoTrain.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
- Created
- Apr 21, 2025
- Updated
- Apr 21, 2025