Compare commits

..

10 Commits

Author SHA1 Message Date
Magnus
e4095399dd correct wrong percentage of German Wikipedia pre-training info in README 2025-10-05 11:07:22 +00:00
Magnus
fa31b5a5d7 Upload f16/F16.gguf with huggingface_hub 2025-07-20 00:22:47 +00:00
Magnus
06d9b60a91 Upload q4_k_m/Q4_K_M.gguf with huggingface_hub 2025-07-20 00:17:12 +00:00
Magnus
c152e00e93 Upload q8_0/Q8_0.gguf with huggingface_hub 2025-07-20 00:14:55 +00:00
Magnus
4b18e5b9d6 again, restore README 2025-07-20 00:11:12 +00:00
Magnus
aa4c27b3a1 (Trained with Unsloth) 2025-07-20 00:09:36 +00:00
Magnus
5f284aa418 Unsloth Model Card 2025-07-20 00:04:47 +00:00
Magnus
c861aad2ef Upload showcase-image.png 2025-07-19 23:46:54 +00:00
Magnus
0e16271f54 Delete showcase-image.png 2025-07-19 23:46:46 +00:00
Magnus
2f38f7051e add showcase image to README 2025-07-19 23:45:22 +00:00
6 changed files with 11 additions and 8 deletions

View File

@@ -11,11 +11,14 @@ datasets:
- wikimedia/wikipedia - wikimedia/wikipedia
- FreedomIntelligence/alpaca-gpt4-deutsch - FreedomIntelligence/alpaca-gpt4-deutsch
--- ---
# SmolLM2-360m-German-Instruct # SmolLM2-360m-German-Instruct
<p align="center">
<img alt="Showcase image for SmolLM2-360m-German-Instruct" src="https://huggingface.co/mags0ft/SmolLM2-360m-German-Instruct/resolve/main/showcase-image.png" width="600" />
</p>
This is a continued pre-train as well as an instruct fine-tune done using Unsloth in order to make SmolLM2 360m capable of speaking German. This is a continued pre-train as well as an instruct fine-tune done using Unsloth in order to make SmolLM2 360m capable of speaking German.
It has been trained on 15% of the German Wikipedia as well as the full German version of the Alpaca-GPT4 dataset (translated version). It has been trained on 25% of the German Wikipedia as well as the full German version of the Alpaca-GPT4 dataset (translated version).
Even though a lot of training has been done, this is still a tiny model and is highly limited to its small size. Expect many hallucinations and do not use this in a demanding production workflow. Even though a lot of training has been done, this is still a tiny model and is highly limited to its small size. Expect many hallucinations and do not use this in a demanding production workflow.

View File

@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1 version https://git-lfs.github.com/spec/v1
oid sha256:1462d84557a08d69405309f3c16ada8d1c52fc6449ded0e0ae2d5dbe7373c816 oid sha256:ed010060c32323c44e6248aaef94f4a4a5630a6dcfeacd8afc5c0c185826d5b9
size 819925536 size 819925536

View File

@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1 version https://git-lfs.github.com/spec/v1
oid sha256:41222834cd1a584a897092dadad995f389839de5e24881530bd63e9c229b64c5 oid sha256:89e56c696d512be022033dacec04ad432384e1e9b7c4d3439c18bd452e42d306
size 723674912 size 723674912

View File

@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1 version https://git-lfs.github.com/spec/v1
oid sha256:8440cc3ea124948730bdcefff5b955064cd80cbe029cebb2b1b79d875b855dc1 oid sha256:b5041c903e83c1864164de3f9f78e9e1286f6298cfe15d5e7822141aa4ea0f49
size 303030816 size 303030816

View File

@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1 version https://git-lfs.github.com/spec/v1
oid sha256:8673622683be5beb60ca75993f01050c3ee6576564b21befac2a0f20b929039e oid sha256:59a931c76d445f1d6ab91c0687003070003d2c59fdc03d92086b108eeb487d94
size 436539936 size 436539936

View File

@@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1 version https://git-lfs.github.com/spec/v1
oid sha256:dc5c4ca40209ad8c39d456e20dada1e5a37ae356bb097646c0db2f934bc012c0 oid sha256:6e70474f66335edacd1977498a0dc5351f8c201c8f28c15bcc9de5596acbff82
size 1619494 size 1618360