m-polignano-uniba
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -25,7 +25,7 @@ license: llama3
|
|
25 |
<hr>
|
26 |
<!--<img src="https://i.ibb.co/6mHSRm3/llamantino53.jpg" width="200"/>-->
|
27 |
|
28 |
-
<p style="text-align:justify;"><b>LLaMAntino-3-ANITA-8B-
|
29 |
The model is an instruction-tuned version of <a href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct"><b>Meta-Llama-3-8b-instruct</b></a> (a fine-tuned <b>LLaMA 3 model</b>).
|
30 |
This model version aims to be the a <b>Multilingual Model</b> 🏁 -- EN 🇺🇸 + ITA🇮🇹 -- to further fine-tune for the Specific Italian Task</p>
|
31 |
|
@@ -88,7 +88,7 @@ For direct use with `transformers`, you can easily get started with the followin
|
|
88 |
AutoTokenizer,
|
89 |
)
|
90 |
|
91 |
-
base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-
|
92 |
model = AutoModelForCausalLM.from_pretrained(
|
93 |
base_model,
|
94 |
torch_dtype=torch.bfloat16,
|
@@ -141,7 +141,7 @@ For direct use with `transformers`, you can easily get started with the followin
|
|
141 |
BitsAndBytesConfig,
|
142 |
)
|
143 |
|
144 |
-
base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-
|
145 |
bnb_config = BitsAndBytesConfig(
|
146 |
load_in_4bit=True,
|
147 |
bnb_4bit_quant_type="nf4",
|
@@ -205,7 +205,7 @@ For direct use with `unsloth`, you can easily get started with the following ste
|
|
205 |
from unsloth import FastLanguageModel
|
206 |
import torch
|
207 |
|
208 |
-
base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-
|
209 |
model, tokenizer = FastLanguageModel.from_pretrained(
|
210 |
model_name = base_model,
|
211 |
max_seq_length = 8192,
|
|
|
25 |
<hr>
|
26 |
<!--<img src="https://i.ibb.co/6mHSRm3/llamantino53.jpg" width="200"/>-->
|
27 |
|
28 |
+
<p style="text-align:justify;"><b>LLaMAntino-3-ANITA-8B-Inst-DPO-ITA</b> is a model of the <a href="https://huggingface.co/swap-uniba"><b>LLaMAntino</b></a> - <i>Large Language Models family</i>.
|
29 |
The model is an instruction-tuned version of <a href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct"><b>Meta-Llama-3-8b-instruct</b></a> (a fine-tuned <b>LLaMA 3 model</b>).
|
30 |
This model version aims to be the a <b>Multilingual Model</b> 🏁 -- EN 🇺🇸 + ITA🇮🇹 -- to further fine-tune for the Specific Italian Task</p>
|
31 |
|
|
|
88 |
AutoTokenizer,
|
89 |
)
|
90 |
|
91 |
+
base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA"
|
92 |
model = AutoModelForCausalLM.from_pretrained(
|
93 |
base_model,
|
94 |
torch_dtype=torch.bfloat16,
|
|
|
141 |
BitsAndBytesConfig,
|
142 |
)
|
143 |
|
144 |
+
base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA"
|
145 |
bnb_config = BitsAndBytesConfig(
|
146 |
load_in_4bit=True,
|
147 |
bnb_4bit_quant_type="nf4",
|
|
|
205 |
from unsloth import FastLanguageModel
|
206 |
import torch
|
207 |
|
208 |
+
base_model = "m-polignano-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA"
|
209 |
model, tokenizer = FastLanguageModel.from_pretrained(
|
210 |
model_name = base_model,
|
211 |
max_seq_length = 8192,
|