Upload folder using huggingface_hub

README.md

@@ -0,0 +1,82 @@
+---
+base_model:
+- jekunz/smollm-360m-cpt-fineweb-icelandic
+- jekunz/smollm-360m-cpt-fineweb-swedish
+- jekunz/smollm-360m-cpt-fineweb-danish
+- jekunz/smollm-360m-cpt-fineweb-norwegian-bokmaal
+- jekunz/smollm-360m-cpt-fineweb-norwegian-nynorsk
+tags:
+- merge
+- mergekit
+- lazymergekit
+- jekunz/smollm-360m-cpt-fineweb-icelandic
+- jekunz/smollm-360m-cpt-fineweb-swedish
+- jekunz/smollm-360m-cpt-fineweb-danish
+- jekunz/smollm-360m-cpt-fineweb-norwegian-bokmaal
+- jekunz/smollm-360m-cpt-fineweb-norwegian-nynorsk
+---
+
+# smollm360m-da1-is1-nno1-nob1-sv1-ties
+
+smollm360m-da1-is1-nno1-nob1-sv1-ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [jekunz/smollm-360m-cpt-fineweb-icelandic](https://huggingface.co/jekunz/smollm-360m-cpt-fineweb-icelandic)
+* [jekunz/smollm-360m-cpt-fineweb-swedish](https://huggingface.co/jekunz/smollm-360m-cpt-fineweb-swedish)
+* [jekunz/smollm-360m-cpt-fineweb-danish](https://huggingface.co/jekunz/smollm-360m-cpt-fineweb-danish)
+* [jekunz/smollm-360m-cpt-fineweb-norwegian-bokmaal](https://huggingface.co/jekunz/smollm-360m-cpt-fineweb-norwegian-bokmaal)
+* [jekunz/smollm-360m-cpt-fineweb-norwegian-nynorsk](https://huggingface.co/jekunz/smollm-360m-cpt-fineweb-norwegian-nynorsk)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: jekunz/smollm-360m-cpt-fineweb-icelandic
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: jekunz/smollm-360m-cpt-fineweb-swedish
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: jekunz/smollm-360m-cpt-fineweb-danish
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: jekunz/smollm-360m-cpt-fineweb-norwegian-bokmaal
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: jekunz/smollm-360m-cpt-fineweb-norwegian-nynorsk
+    parameters:
+      density: 0.5
+      weight: 1.0
+merge_method: ties
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
+parameters:
+  normalize: true
+dtype: float16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "jekunz/smollm360m-da1-is1-nno1-nob1-sv1-ties"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.51.1",
+  "use_cache": true,
+  "vocab_size": 49152
+}

mergekit_config.yml

@@ -0,0 +1,27 @@
+
+models:
+  - model: jekunz/smollm-360m-cpt-fineweb-icelandic
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: jekunz/smollm-360m-cpt-fineweb-swedish
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: jekunz/smollm-360m-cpt-fineweb-danish
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: jekunz/smollm-360m-cpt-fineweb-norwegian-bokmaal
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: jekunz/smollm-360m-cpt-fineweb-norwegian-nynorsk
+    parameters:
+      density: 0.5
+      weight: 1.0
+merge_method: ties
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
+parameters:
+  normalize: true
+dtype: float16

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d08c8e640c1515aecc73a08cf283d3924c5da5d2b2cd9dde85c5b3f85be477
+size 723674624

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "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": "<|im_end|>",
+      "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}