Upload folder using huggingface_hub

README.md

@@ -0,0 +1,39 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: tokyotech-llm/Llama-3-Swallow-8B-v0.1
+model-index:
+- name: shibajustfor/a560a2bc-0022-4e2c-8372-f1e202cd28eb
+  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. -->
+
+
+# shibajustfor/a560a2bc-0022-4e2c-8372-f1e202cd28eb
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4772
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+    "alpha_pattern": {},
+    "auto_mapping": null,
+    "base_model_name_or_path": "tokyotech-llm/Llama-3-Swallow-8B-v0.1",
+    "bias": "none",
+    "fan_in_fan_out": null,
+    "inference_mode": true,
+    "init_lora_weights": true,
+    "layer_replication": null,
+    "layers_pattern": null,
+    "layers_to_transform": null,
+    "loftq_config": {},
+    "lora_alpha": 64,
+    "lora_dropout": 0.05,
+    "megatron_config": null,
+    "megatron_core": "megatron.core",
+    "modules_to_save": null,
+    "peft_type": "LORA",
+    "r": 32,
+    "rank_pattern": {},
+    "revision": null,
+    "target_modules": [
+        "q_proj",
+        "up_proj",
+        "down_proj",
+        "k_proj",
+        "v_proj",
+        "gate_proj",
+        "o_proj"
+    ],
+    "task_type": "CAUSAL_LM",
+    "use_dora": false,
+    "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e2a4a41bb052070f83bd3d0e106419cc2c332f854dd15dcc25ed518e1b39c1
+size 335706186