Le modèle de langage le plus petit, entraîné sur 'Clem' et 'Creatrice'

README.md

@@ -0,0 +1,51 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: the-smallest-llm-real-words
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# the-smallest-llm-real-words
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 1,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 2,
+  "n_head": 1,
+  "n_inner": null,
+  "n_layer": 1,
+  "n_positions": 13,
+  "pad_token_id": 2,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 4
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 1,
+  "pad_token_id": 2,
+  "transformers_version": "4.57.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1acb67f7772192dcb0dd47a64ffef578d3c25cb26dbebbf28a37e1e8123dafc
+size 1840

runs/Nov16_09-41-06_338386517b02/events.out.tfevents.1763286145.338386517b02.822.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e40ffd95d75e4764049d5c7b380589567d1c7ccf1f71e55c0e7c97f6fee43d3
+size 5669

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a127e0120f55a35e71e82effe4e813f11bb9c68fa007bf2e2506bd276f6669
+size 5905