初始化项目，由ModelHub XC社区提供模型

Model: mags0ft/SmolLM2-360m-German-Instruct Source: Original Platform
2026-05-13 18:57:49 +08:00
commit bed95392a2
16 changed files with 294153 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,41 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Q8_0/Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+q4_k_m/Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+f16/F16.gguf filter=lfs diff=lfs merge=lfs -text
+q8_0/Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Enhancing[[:space:]]Foreign[[:space:]]Language[[:space:]]Proficiency[[:space:]]in[[:space:]]SmolLM2-360M[[:space:]]via[[:space:]]Continued[[:space:]]Pretraining[[:space:]]and[[:space:]]Instruction[[:space:]]Fine-Tuning.pdf filter=lfs diff=lfs merge=lfs -text
+showcase-image.png filter=lfs diff=lfs merge=lfs -text
--- a/Fine-Tuning.pdf
+++ b/Fine-Tuning.pdf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534a2efc5186b448631d6f85c92a495bf0d7b9eb3466284bd773e58d66c77ea7
+size 247364
--- a/README.md
+++ b/README.md
@@ -0,0 +1,39 @@
+---
+base_model: HuggingFaceTB/SmolLM2-360M
+tags:
+- transformers
+- unsloth
+- llama
+license: apache-2.0
+language:
+- de
+datasets:
+- wikimedia/wikipedia
+- FreedomIntelligence/alpaca-gpt4-deutsch
+---
+# 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.
+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.
+
+# Links
+
+- [Ollama](https://ollama.com/jace-ai/SmolLM2-German-Instruct)
+- [Technical report paper](https://huggingface.co/mags0ft/SmolLM2-360m-German-Instruct/resolve/main/Enhancing%20Foreign%20Language%20Proficiency%20in%20SmolLM2-360M%20via%20Continued%20Pretraining%20and%20Instruction%20Fine-Tuning.pdf)
+
+# Cite as
+
+```bibtex
+@misc{smollm2germaninstruct,
+  author       = {Magnus Leonard Schlinsog},
+  title        = {Enhancing Foreign Language Proficiency in SmolLM2-360M via Continued Pretraining and Instruction Fine-Tuning},
+  year         = {2025},
+  url          = {https://huggingface.co/mags0ft/SmolLM2-360m-German-Instruct},
+}
+```
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user
+' + message['content'] + '<|im_end|>
+'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant
+' + message['content'] + '<|im_end|>
+' }}{% else %}{{ '<|im_start|>system
+' + message['content'] + '<|im_end|>
+' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.2",
+  "unsloth_version": "2025.7.4",
+  "use_cache": true,
+  "vocab_size": 49152
+}
--- a/f16/F16.gguf
+++ b/f16/F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed010060c32323c44e6248aaef94f4a4a5630a6dcfeacd8afc5c0c185826d5b9
+size 819925536
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "max_length": 8192,
+  "pad_token_id": 0,
+  "transformers_version": "4.53.2"
+}
--- a/merges.txt
+++ b/merges.txt
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e56c696d512be022033dacec04ad432384e1e9b7c4d3439c18bd452e42d306
+size 723674912
--- a/q4_k_m/Q4_K_M.gguf
+++ b/q4_k_m/Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5041c903e83c1864164de3f9f78e9e1286f6298cfe15d5e7822141aa4ea0f49
+size 303030816
--- a/q8_0/Q8_0.gguf
+++ b/q8_0/Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a931c76d445f1d6ab91c0687003070003d2c59fdc03d92086b108eeb487d94
+size 436539936
--- a/showcase-image.png
+++ b/showcase-image.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e70474f66335edacd1977498a0dc5351f8c201c8f28c15bcc9de5596acbff82
+size 1618360
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,149 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}
--- a/vocab.json
+++ b/vocab.json