RichardErkhov
commited on
Commit
•
9c1c9d8
1
Parent(s):
735ac5b
uploaded readme
Browse files
README.md
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Quantization made by Richard Erkhov.
|
2 |
+
|
3 |
+
[Github](https://github.com/RichardErkhov)
|
4 |
+
|
5 |
+
[Discord](https://discord.gg/pvy7H8DZMG)
|
6 |
+
|
7 |
+
[Request more models](https://github.com/RichardErkhov/quant_request)
|
8 |
+
|
9 |
+
|
10 |
+
LLaMAntino-2-7b-hf-ITA - GGUF
|
11 |
+
- Model creator: https://huggingface.co/swap-uniba/
|
12 |
+
- Original model: https://huggingface.co/swap-uniba/LLaMAntino-2-7b-hf-ITA/
|
13 |
+
|
14 |
+
|
15 |
+
| Name | Quant method | Size |
|
16 |
+
| ---- | ---- | ---- |
|
17 |
+
| [LLaMAntino-2-7b-hf-ITA.Q2_K.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q2_K.gguf) | Q2_K | 2.36GB |
|
18 |
+
| [LLaMAntino-2-7b-hf-ITA.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.IQ3_XS.gguf) | IQ3_XS | 2.6GB |
|
19 |
+
| [LLaMAntino-2-7b-hf-ITA.IQ3_S.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.IQ3_S.gguf) | IQ3_S | 2.75GB |
|
20 |
+
| [LLaMAntino-2-7b-hf-ITA.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
|
21 |
+
| [LLaMAntino-2-7b-hf-ITA.IQ3_M.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.IQ3_M.gguf) | IQ3_M | 2.9GB |
|
22 |
+
| [LLaMAntino-2-7b-hf-ITA.Q3_K.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q3_K.gguf) | Q3_K | 3.07GB |
|
23 |
+
| [LLaMAntino-2-7b-hf-ITA.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
|
24 |
+
| [LLaMAntino-2-7b-hf-ITA.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
|
25 |
+
| [LLaMAntino-2-7b-hf-ITA.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
|
26 |
+
| [LLaMAntino-2-7b-hf-ITA.Q4_0.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q4_0.gguf) | Q4_0 | 3.56GB |
|
27 |
+
| [LLaMAntino-2-7b-hf-ITA.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.IQ4_NL.gguf) | IQ4_NL | 3.58GB |
|
28 |
+
| [LLaMAntino-2-7b-hf-ITA.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
|
29 |
+
| [LLaMAntino-2-7b-hf-ITA.Q4_K.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q4_K.gguf) | Q4_K | 3.8GB |
|
30 |
+
| [LLaMAntino-2-7b-hf-ITA.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
|
31 |
+
| [LLaMAntino-2-7b-hf-ITA.Q4_1.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q4_1.gguf) | Q4_1 | 3.95GB |
|
32 |
+
| [LLaMAntino-2-7b-hf-ITA.Q5_0.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q5_0.gguf) | Q5_0 | 4.33GB |
|
33 |
+
| [LLaMAntino-2-7b-hf-ITA.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
|
34 |
+
| [LLaMAntino-2-7b-hf-ITA.Q5_K.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q5_K.gguf) | Q5_K | 4.45GB |
|
35 |
+
| [LLaMAntino-2-7b-hf-ITA.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q5_K_M.gguf) | Q5_K_M | 4.45GB |
|
36 |
+
| [LLaMAntino-2-7b-hf-ITA.Q5_1.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q5_1.gguf) | Q5_1 | 4.72GB |
|
37 |
+
| [LLaMAntino-2-7b-hf-ITA.Q6_K.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q6_K.gguf) | Q6_K | 5.15GB |
|
38 |
+
| [LLaMAntino-2-7b-hf-ITA.Q8_0.gguf](https://huggingface.co/RichardErkhov/swap-uniba_-_LLaMAntino-2-7b-hf-ITA-gguf/blob/main/LLaMAntino-2-7b-hf-ITA.Q8_0.gguf) | Q8_0 | 6.67GB |
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
Original model description:
|
44 |
+
---
|
45 |
+
license: llama2
|
46 |
+
language:
|
47 |
+
- it
|
48 |
+
tags:
|
49 |
+
- text-generation-inference
|
50 |
+
---
|
51 |
+
# Model Card for LLaMAntino-2-7b-ITA
|
52 |
+
*Last Update: 22/01/2024*<br>
|
53 |
+
|
54 |
+
## Model description
|
55 |
+
|
56 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
57 |
+
|
58 |
+
**LLaMAntino-2-7b** is a *Large Language Model (LLM)* that is an italian-adapted **LLaMA 2**.
|
59 |
+
This model aims to provide Italian NLP researchers with a base model for natural language generation tasks.
|
60 |
+
|
61 |
+
The model was trained using *QLora* and using as training data [clean_mc4_it medium](https://huggingface.co/datasets/gsarti/clean_mc4_it/viewer/medium).
|
62 |
+
If you are interested in more details regarding the training procedure, you can find the code we used at the following link:
|
63 |
+
- **Repository:** https://github.com/swapUniba/LLaMAntino
|
64 |
+
|
65 |
+
**NOTICE**: the code has not been released yet, we apologize for the delay, it will be available asap!
|
66 |
+
|
67 |
+
- **Developed by:** Pierpaolo Basile, Elio Musacchio, Marco Polignano, Lucia Siciliani, Giuseppe Fiameni, Giovanni Semeraro
|
68 |
+
- **Funded by:** PNRR project FAIR - Future AI Research
|
69 |
+
- **Compute infrastructure:** [Leonardo](https://www.hpc.cineca.it/systems/hardware/leonardo/) supercomputer
|
70 |
+
- **Model type:** LLaMA 2
|
71 |
+
- **Language(s) (NLP):** Italian
|
72 |
+
- **License:** Llama 2 Community License
|
73 |
+
- **Finetuned from model:** [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf)
|
74 |
+
|
75 |
+
## How to Get Started with the Model
|
76 |
+
|
77 |
+
Below you can find an example of model usage:
|
78 |
+
|
79 |
+
```python
|
80 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
81 |
+
|
82 |
+
model_id = "swap-uniba/LLaMAntino-2-7b-hf-ITA"
|
83 |
+
|
84 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
85 |
+
model = AutoModelForCausalLM.from_pretrained(model_id)
|
86 |
+
|
87 |
+
prompt = "Scrivi qui un possibile prompt"
|
88 |
+
|
89 |
+
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
|
90 |
+
outputs = model.generate(input_ids=input_ids)
|
91 |
+
|
92 |
+
print(tokenizer.batch_decode(outputs.detach().cpu().numpy()[:, input_ids.shape[1]:], skip_special_tokens=True)[0])
|
93 |
+
```
|
94 |
+
|
95 |
+
If you are facing issues when loading the model, you can try to load it quantized:
|
96 |
+
|
97 |
+
```python
|
98 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, load_in_8bit=True)
|
99 |
+
```
|
100 |
+
|
101 |
+
*Note*: The model loading strategy above requires the [*bitsandbytes*](https://pypi.org/project/bitsandbytes/) and [*accelerate*](https://pypi.org/project/accelerate/) libraries
|
102 |
+
|
103 |
+
## Citation
|
104 |
+
|
105 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
106 |
+
|
107 |
+
If you use this model in your research, please cite the following:
|
108 |
+
|
109 |
+
```bibtex
|
110 |
+
@misc{basile2023llamantino,
|
111 |
+
title={LLaMAntino: LLaMA 2 Models for Effective Text Generation in Italian Language},
|
112 |
+
author={Pierpaolo Basile and Elio Musacchio and Marco Polignano and Lucia Siciliani and Giuseppe Fiameni and Giovanni Semeraro},
|
113 |
+
year={2023},
|
114 |
+
eprint={2312.09993},
|
115 |
+
archivePrefix={arXiv},
|
116 |
+
primaryClass={cs.CL}
|
117 |
+
}
|
118 |
+
```
|
119 |
+
|
120 |
+
*Notice:* Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. [*License*](https://ai.meta.com/llama/license/)
|
121 |
+
|