9542215901
Model: RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf Source: Original Platform
89 lines
6.2 KiB
Markdown
89 lines
6.2 KiB
Markdown
Quantization made by Richard Erkhov.
|
|
|
|
[Github](https://github.com/RichardErkhov)
|
|
|
|
[Discord](https://discord.gg/pvy7H8DZMG)
|
|
|
|
[Request more models](https://github.com/RichardErkhov/quant_request)
|
|
|
|
|
|
gpt2-autotrain-text-HrPolicy-aug-v2 - GGUF
|
|
- Model creator: https://huggingface.co/ishmanish/
|
|
- Original model: https://huggingface.co/ishmanish/gpt2-autotrain-text-HrPolicy-aug-v2/
|
|
|
|
|
|
| Name | Quant method | Size |
|
|
| ---- | ---- | ---- |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q2_K.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q2_K.gguf) | Q2_K | 0.08GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.IQ3_XS.gguf) | IQ3_XS | 0.08GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.IQ3_S.gguf) | IQ3_S | 0.08GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q3_K_S.gguf) | Q3_K_S | 0.08GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.IQ3_M.gguf) | IQ3_M | 0.09GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q3_K.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q3_K.gguf) | Q3_K | 0.09GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q3_K_M.gguf) | Q3_K_M | 0.09GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q3_K_L.gguf) | Q3_K_L | 0.1GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.IQ4_XS.gguf) | IQ4_XS | 0.1GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q4_0.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q4_0.gguf) | Q4_0 | 0.1GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.IQ4_NL.gguf) | IQ4_NL | 0.1GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q4_K_S.gguf) | Q4_K_S | 0.1GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q4_K.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q4_K.gguf) | Q4_K | 0.11GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q4_K_M.gguf) | Q4_K_M | 0.11GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q4_1.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q4_1.gguf) | Q4_1 | 0.11GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q5_0.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q5_0.gguf) | Q5_0 | 0.11GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q5_K_S.gguf) | Q5_K_S | 0.11GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q5_K.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q5_K.gguf) | Q5_K | 0.12GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q5_K_M.gguf) | Q5_K_M | 0.12GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q5_1.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q5_1.gguf) | Q5_1 | 0.12GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q6_K.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q6_K.gguf) | Q6_K | 0.13GB |
|
|
| [gpt2-autotrain-text-HrPolicy-aug-v2.Q8_0.gguf](https://huggingface.co/RichardErkhov/ishmanish_-_gpt2-autotrain-text-HrPolicy-aug-v2-gguf/blob/main/gpt2-autotrain-text-HrPolicy-aug-v2.Q8_0.gguf) | Q8_0 | 0.17GB |
|
|
|
|
|
|
|
|
|
|
Original model description:
|
|
---
|
|
tags:
|
|
- autotrain
|
|
- text-generation-inference
|
|
- text-generation
|
|
library_name: transformers
|
|
widget:
|
|
- messages:
|
|
- role: user
|
|
content: What is your favorite condiment?
|
|
license: other
|
|
---
|
|
|
|
# Model Trained Using AutoTrain
|
|
|
|
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
|
|
|
# Usage
|
|
|
|
```python
|
|
|
|
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)
|
|
```
|
|
|