Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,17 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+llamantino-2-chat-13b-hf-ita.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,84 @@
+---
+title: "LLaMAntino-2-chat-13b-hf-ITA Quantized in GGUF"
+tags:
+  - GGUF
+language: en
+---
+![Image description](https://i.postimg.cc/MGwhtFfF/tsune-fixed.png)
+
+# Tsunemoto GGUF's of LLaMAntino-2-chat-13b-hf-ITA
+
+This is a GGUF quantization of LLaMAntino-2-chat-13b-hf-ITA.
+
+## Original Repo Link:
+[Original Repository](https://huggingface.co/swap-uniba/LLaMAntino-2-chat-13b-hf-ITA)
+
+## Original Model Card:
+---
+# Model Card for LLaMAntino-2-chat-13b-ITA
+
+## Model description
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+**LLaMAntino-2-chat-13b** is a *Large Language Model (LLM)* that is an italian-adapted **LLaMA 2 chat**. 
+This model aims to provide Italian NLP researchers with a base model for italian dialogue use cases.
+
+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). 
+If you are interested in more details regarding the training procedure, you can find the code we used at the following link:
+- **Repository:** https://github.com/swapUniba/LLaMAntino
+
+**NOTICE**: the code has not been released yet, we apologize for the delay, it will be available asap!
+
+- **Developed by:** Pierpaolo Basile, Elio Musacchio, Marco Polignano, Lucia Siciliani, Giuseppe Fiameni, Giovanni Semeraro
+- **Funded by:** PNRR project FAIR - Future AI Research
+- **Compute infrastructure:** [Leonardo](https://www.hpc.cineca.it/systems/hardware/leonardo/) supercomputer
+- **Model type:** LLaMA 2 chat
+- **Language(s) (NLP):** Italian
+- **License:** Llama 2 Community License 
+- **Finetuned from model:** [NousResearch/Llama-2-13b-chat-hf](https://huggingface.co/NousResearch/Llama-2-13b-chat-hf)
+
+## How to Get Started with the Model
+
+Below you can find an example of model usage:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "swap-uniba/LLaMAntino-2-chat-13b-hf-ITA"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+prompt = "Scrivi qui un possibile prompt"
+
+input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+outputs = model.generate(input_ids=input_ids)
+
+print(tokenizer.batch_decode(outputs.detach().cpu().numpy()[:, input_ids.shape[1]:], skip_special_tokens=True)[0])
+```
+
+If you are facing issues when loading the model, you can try to load it quantized:
+
+```python
+model = AutoModelForCausalLM.from_pretrained(model_id, load_in_8bit=True)
+```
+
+*Note*: The model loading strategy above requires the [*bitsandbytes*](https://pypi.org/project/bitsandbytes/) and [*accelerate*](https://pypi.org/project/accelerate/) libraries
+
+## Citation
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+If you use this model in your research, please cite the following:
+
+```bibtex
+@misc{basile2023llamantino,
+      title={LLaMAntino: LLaMA 2 Models for Effective Text Generation in Italian Language}, 
+      author={Pierpaolo Basile and Elio Musacchio and Marco Polignano and Lucia Siciliani and Giuseppe Fiameni and Giovanni Semeraro},
+      year={2023},
+      eprint={2312.09993},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

llamantino-2-chat-13b-hf-ita.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdee2b4fcb568d53b449b802630ac9e7539c6bdf3a8df35eaff1aed0d147578b
+size 5429348352

llamantino-2-chat-13b-hf-ita.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a28151b370ad1416c946a02861e2ed33d0b2f905da1545556e44ae26e45f38
+size 6929559552

llamantino-2-chat-13b-hf-ita.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2449600464cb566936888831fdfcfad6f2f471d46c722045e5aaa1eaa72a59a6
+size 6337769472

llamantino-2-chat-13b-hf-ita.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2327eb52ae85116773cc86209ce0ebe22ab458fff54ce11a6e7ea6ab5dc14bd
+size 5658980352

llamantino-2-chat-13b-hf-ita.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ffab0c7399396d26c1264cf83a3cf8d093296a7592d0d8f7f6f984623bed11
+size 7365834752

llamantino-2-chat-13b-hf-ita.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1d7e4f2614bb16d126f61359cc6c1f0caebeb092cac314f57a8b9965d6224e
+size 8169060352

llamantino-2-chat-13b-hf-ita.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181b1cd5f419fe8cf40b60a6017b25ee30e712f436fa5e7b69002bb67e622505
+size 7865956352

llamantino-2-chat-13b-hf-ita.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0022af42c01e2a385a968ffddbb16142b6f0e6584ddae20fed90a44742acbcf7
+size 7414331392

llamantino-2-chat-13b-hf-ita.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810f2161edd64550bcd3d15b3753b8aab15e8e2960c15222e7924f6b671cbcd3
+size 8972285952

llamantino-2-chat-13b-hf-ita.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf9056e400cac26588788f6fd414b2a91a6033046725f252ce85f9a381ff4bb
+size 9775511552

llamantino-2-chat-13b-hf-ita.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247dcc92236e498654f1db0c88e1133ff35afb337ed37da8948331888cc8de96
+size 9229924352

llamantino-2-chat-13b-hf-ita.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37abf2e1caf3c09e4cc032e3a3207a6fb810848344d3f6fd66efb8cb3aa05939
+size 8972285952

llamantino-2-chat-13b-hf-ita.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3380c11cd7f8f26c5f172a0316c90fa7af79aea12927da3dc51ed32f430cf48b
+size 10679140352

llamantino-2-chat-13b-hf-ita.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf3b54be6629da89838b15ce1237c2af89bb9a7db9e40ea38777db229331856
+size 13831319552