Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
language:
|
| 6 |
+
- bg
|
| 7 |
+
- ca
|
| 8 |
+
- code
|
| 9 |
+
- cs
|
| 10 |
+
- cy
|
| 11 |
+
- da
|
| 12 |
+
- de
|
| 13 |
+
- el
|
| 14 |
+
- en
|
| 15 |
+
- es
|
| 16 |
+
- et
|
| 17 |
+
- eu
|
| 18 |
+
- fi
|
| 19 |
+
- fr
|
| 20 |
+
- ga
|
| 21 |
+
- gl
|
| 22 |
+
- hr
|
| 23 |
+
- hu
|
| 24 |
+
- it
|
| 25 |
+
- lt
|
| 26 |
+
- lv
|
| 27 |
+
- mt
|
| 28 |
+
- nl
|
| 29 |
+
- nn
|
| 30 |
+
- no
|
| 31 |
+
- oc
|
| 32 |
+
- pl
|
| 33 |
+
- pt
|
| 34 |
+
- ro
|
| 35 |
+
- ru
|
| 36 |
+
- sh
|
| 37 |
+
- sk
|
| 38 |
+
- sl
|
| 39 |
+
- sr
|
| 40 |
+
- sv
|
| 41 |
+
- uk
|
| 42 |
+
---
|
| 43 |
+
|
| 44 |
+
# GGUF quants
|
| 45 |
+
|
| 46 |
+
Experimental GGUF quantization of [BSC-LT/salamandra-7b-instruct](https://huggingface.co/BSC-LT/salamandra-7b-instruct/) from llama.cpp (older version b2750).
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
# Salamandra Model Card
|
| 51 |
+
|
| 52 |
+
Salamandra comes in three different sizes — 2B, 7B and 40B parameters — with their respective base and instruction-tuned variants.
|
| 53 |
+
This model card corresponds to the 7B instructed version.
|
| 54 |
+
|
| 55 |
+
To visit the model cards of other Salamandra versions, please refer to the [Model Index](#model-index).
|
| 56 |
+
|
| 57 |
+
The entire Salamandra family is released under a permissive [Apache 2.0 license]((https://www.apache.org/licenses/LICENSE-2.0)).
|
| 58 |
+
Along with the open weights, all training scripts and configuration files are made publicly available in [this GitHub repository](https://github.com/langtech-bsc/salamandra).
|
| 59 |
+
|
| 60 |
+
> [!WARNING]
|
| 61 |
+
> **DISCLAIMER:** This model is a first proof-of-concept designed to demonstrate the instruction-following capabilities of recently released base models.
|
| 62 |
+
> It has been optimized to engage in conversation but has *NOT* been aligned through RLHF to filter or avoid sensitive topics.
|
| 63 |
+
> As a result, it may generate harmful or inappropriate content.
|
| 64 |
+
> The team is actively working to enhance its performance through further instruction and alignment with RL techniques.
|