Model save

README.md

@@ -0,0 +1,52 @@
+---
+license: llama3.2
+base_model: meta-llama/Llama-3.2-1B-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: llama32
+  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. -->
+
+# llama32
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.43.4
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

llama23-1b-prefix-is/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "config": {
+    "architecture": "prefix_tuning",
+    "bottleneck_size": 512,
+    "cross_prefix": true,
+    "dropout": 0.0,
+    "encoder_prefix": true,
+    "flat": false,
+    "leave_out": [],
+    "non_linearity": "tanh",
+    "prefix_length": 30,
+    "shared_gating": true,
+    "use_gating": false
+  },
+  "config_id": "648bf22f5afeaaa6",
+  "hidden_size": 2048,
+  "model_class": "LlamaForCausalLM",
+  "model_name": "meta-llama/Llama-3.2-1B-Instruct",
+  "model_type": "llama",
+  "name": "llama23-1b-prefix-is",
+  "version": "adapters.1.0.0"
+}

llama23-1b-prefix-is/head_config.json

@@ -0,0 +1,14 @@
+{
+  "config": null,
+  "hidden_size": 2048,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_class": "LlamaForCausalLM",
+  "model_name": "meta-llama/Llama-3.2-1B-Instruct",
+  "model_type": "llama",
+  "name": null,
+  "num_labels": 2,
+  "version": "adapters.1.0.0"
+}

llama23-1b-prefix-is/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8681c6c849549a11ac7d5af148de721d59e3f2dad12b3a92dd694e5d5b94fffd
+size 138940436

llama23-1b-prefix-is/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0ce01b605263d49872370f631813ee6b0f168b772bd8d50b1d2176aea1f7e6
+size 1050674451