llammchen_1b

README.md

@@ -0,0 +1,28 @@
+---
+datasets:
+- togethercomputer/RedPajama-Data-V2
+language:
+- de
+---
+
+# LLäMMchen 1B
+
+This is a German Tinyllama 1B language model trained from scratch using the 
+the [Tinyllama](https://github.com/jzhang38/TinyLlama) codebase on the German portion of [RedPajama V2](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2). 
+
+
+### Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("LSX-UniWue/llammchen_1b")
+
+tokenizer = AutoTokenizer.from_pretrained("LSX-UniWue/llammchen_1b")
+```
+
+
+### Evaluation 
+We evaluated our results on the [Superkleber](https://lsx-uniwue.github.io/SuperGLEBer-site/) benchmark. 
+
+

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/data/42-julia-hpc-rz-lsx/s386162/models/formatted/iter-1430512-ckpt",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9234c5205711b2ffa94f4701f2310df312147d4af843054eaf97a4ecf4ae9df2
+size 4400216536

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}