初始化项目，由ModelHub XC社区提供模型

Model: mradermacher/salamandra-2b-instruct-i1-GGUF Source: Original Platform
2026-05-05 18:29:52 +08:00
commit 78c82c4f9f
27 changed files with 268 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,133 @@
+---
+base_model: BSC-LT/salamandra-2b-instruct
+datasets:
+- oscar-corpus/colossal-oscar-1.0
+- HuggingFaceFW/fineweb-edu
+- joelniklaus/eurlex_resources
+- joelito/legal-mc4
+- projecte-aina/CATalog
+- UFRGS/brwac
+- community-datasets/hrwac
+- danish-foundation-models/danish-gigaword
+- HiTZ/euscrawl
+- PleIAs/French-PD-Newspapers
+- PleIAs/French-PD-Books
+- AI-team-UoA/greek_legal_code
+- HiTZ/latxa-corpus-v1.1
+- allenai/peS2o
+- pile-of-law/pile-of-law
+- PORTULAN/parlamento-pt
+- hoskinson-center/proof-pile
+- togethercomputer/RedPajama-Data-1T
+- bigcode/starcoderdata
+- bjoernp/tagesschau-2018-2023
+- EleutherAI/the_pile_deduplicated
+language:
+- bg
+- ca
+- code
+- cs
+- cy
+- da
+- de
+- el
+- en
+- es
+- et
+- eu
+- fi
+- fr
+- ga
+- gl
+- hr
+- hu
+- it
+- lt
+- lv
+- mt
+- nl
+- nn
+- \no
+- oc
+- pl
+- pt
+- ro
+- ru
+- sh
+- sk
+- sl
+- sr
+- sv
+- uk
+library_name: transformers
+license: apache-2.0
+quantized_by: mradermacher
+---
+## About
+
+<!-- ### quantize_version: 2 -->
+<!-- ### output_tensor_quantised: 1 -->
+<!-- ### convert_type: hf -->
+<!-- ### vocab_type:  -->
+<!-- ### tags: nicoboss -->
+weighted/imatrix quants of https://huggingface.co/BSC-LT/salamandra-2b-instruct
+
+<!-- provided-files -->
+static quants are available at https://huggingface.co/mradermacher/salamandra-2b-instruct-GGUF
+## Usage
+
+If you are unsure how to use GGUF files, refer to one of [TheBloke's
+READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
+more details, including on how to concatenate multi-part files.
+
+## Provided Quants
+
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+
+| Link | Type | Size/GB | Notes |
+|:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 1.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.2 | very low quality |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 1.2 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.2 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 1.3 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.3 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 1.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.4 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.4 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.5 | prefer IQ4_XS |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 1.5 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.5 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.6 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q4_1.gguf) | i1-Q4_1 | 1.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/salamandra-2b-instruct-i1-GGUF/resolve/main/salamandra-2b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 2.0 | practically like static Q6_K |
+
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
+
+And here are Artefact2's thoughts on the matter:
+https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
+
+## FAQ / Model Request
+
+See https://huggingface.co/mradermacher/model_requests for some answers to
+questions you might have and/or if you want some other model quantized.
+
+## Thanks
+
+I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
+me use its servers and providing upgrades to my workstation to enable
+this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
+
+<!-- end -->