Question Answering
Transformers
Safetensors
PEFT
Spanish
llama
text-generation
resident-evil
qlora
llama-cpp
instruct
gaming
text-generation-inference
Instructions to use DavidCaraballoBulnes/ResidentEvil-QA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DavidCaraballoBulnes/ResidentEvil-QA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="DavidCaraballoBulnes/ResidentEvil-QA")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DavidCaraballoBulnes/ResidentEvil-QA") model = AutoModelForCausalLM.from_pretrained("DavidCaraballoBulnes/ResidentEvil-QA", device_map="auto") - PEFT
How to use DavidCaraballoBulnes/ResidentEvil-QA with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,8 @@ tags:
|
|
| 19 |
|
| 20 |
# Salamandra 7B Instruct - Resident Evil Edition 🧟♂️🌿
|
| 21 |
|
|
|
|
|
|
|
| 22 |
This model is a Fine-Tuned version of the [BSC-LT/salamandra-7b-instruct](https://huggingface.co/BSC-LT/salamandra-7b-instruct) foundational model, specifically trained to master the lore, characters, and events of the **Resident Evil** universe.
|
| 23 |
|
| 24 |
The training process was conducted using **QLoRA** (Quantized Low-Rank Adaptation) techniques to achieve high performance. The resulting adapter has already been merged with the base model, making it ready for plug-and-play use.
|
|
@@ -27,6 +29,7 @@ The training process was conducted using **QLoRA** (Quantized Low-Rank Adaptatio
|
|
| 27 |
|
| 28 |
* **Base Model:** `BSC-LT/salamandra-7b-instruct`
|
| 29 |
* **Training Dataset:** [DavidCaraballoBulnes/ResidentEvil-Data-Instruct](https://huggingface.co/datasets/DavidCaraballoBulnes/ResidentEvil-Data-Instruct)
|
|
|
|
| 30 |
* **Architecture:** Causal Language Modeling (Causal LM)
|
| 31 |
* **Final Precision:** `bfloat16`
|
| 32 |
* **Primary Language:** Spanish (ES)
|
|
|
|
| 19 |
|
| 20 |
# Salamandra 7B Instruct - Resident Evil Edition 🧟♂️🌿
|
| 21 |
|
| 22 |
+
[](https://github.com/DavidCaraballoBulnes/salamandra-7b-resident-evil-sft)
|
| 23 |
+
|
| 24 |
This model is a Fine-Tuned version of the [BSC-LT/salamandra-7b-instruct](https://huggingface.co/BSC-LT/salamandra-7b-instruct) foundational model, specifically trained to master the lore, characters, and events of the **Resident Evil** universe.
|
| 25 |
|
| 26 |
The training process was conducted using **QLoRA** (Quantized Low-Rank Adaptation) techniques to achieve high performance. The resulting adapter has already been merged with the base model, making it ready for plug-and-play use.
|
|
|
|
| 29 |
|
| 30 |
* **Base Model:** `BSC-LT/salamandra-7b-instruct`
|
| 31 |
* **Training Dataset:** [DavidCaraballoBulnes/ResidentEvil-Data-Instruct](https://huggingface.co/datasets/DavidCaraballoBulnes/ResidentEvil-Data-Instruct)
|
| 32 |
+
* **Source Code:** [salamandra-7b-resident-evil-sft (GitHub)](https://github.com/DavidCaraballoBulnes/salamandra-7b-resident-evil-sft)
|
| 33 |
* **Architecture:** Causal Language Modeling (Causal LM)
|
| 34 |
* **Final Precision:** `bfloat16`
|
| 35 |
* **Primary Language:** Spanish (ES)
|