danielbyiringiro/lelapa_mtt

README.md

@@ -0,0 +1,54 @@
+---
+library_name: transformers
+license: cc-by-nc-4.0
+base_model: lelapa/InkubaLM-0.4B
+tags:
+- generated_from_trainer
+model-index:
+- name: mt_model
+  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. -->
+
+# mt_model
+
+This model is a fine-tuned version of [lelapa/InkubaLM-0.4B](https://huggingface.co/lelapa/InkubaLM-0.4B) on an unknown 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "lelapa/InkubaLM-0.4B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModelForCausalLM": "lelapa/InkubaLM-0.4B--vulavulaslm.VulavulaLlamaForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 61788
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7307a38f1a1d6a84756ad9090868015b1c7210030bdaeb44386d9da1cfb572
+size 2656649584

runs/Feb06_12-40-08_aa12006afdb4/events.out.tfevents.1738845808.aa12006afdb4.947.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee88fece68814bb8d48d7815af20b2fa6b7c8e1baf5683a9c57fabef611a080
+size 10348

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f1d51d586f847c2404ea8087f875b1f5179e1185e2232d6d22d470b3aa9a5c
+size 5240