HugoVoxx/llama-3.2-1b-it-ag

README.md

@@ -1,57 +1,59 @@
 ---
 base_model: unsloth/Llama-3.2-1B-Instruct
-library_name: transformers
-model_name: llama-3.2-1b-it-ag
+library_name: peft
+license: llama3.2
 tags:
-- generated_from_trainer
 - trl
 - sft
-licence: license
+- generated_from_trainer
+model-index:
+- name: llama-3.2-1b-it-ag
+  results: []
 ---
 
-# Model Card for llama-3.2-1b-it-ag
+<!-- 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. -->
 
-This model is a fine-tuned version of [unsloth/Llama-3.2-1B-Instruct](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+# llama-3.2-1b-it-ag
 
-## Quick start
+This model is a fine-tuned version of [unsloth/Llama-3.2-1B-Instruct](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct) on an unknown dataset.
 
-```python
-from transformers import pipeline
+## Model description
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="HugoVoxx/llama-3.2-1b-it-ag", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+More information needed
 
-## Training procedure
+## Intended uses & limitations
 
+More information needed
 
+## Training and evaluation data
 
-This model was trained with SFT.
+More information needed
 
-### Framework versions
+## Training procedure
+
+### Training hyperparameters
 
-- TRL: 0.12.0.dev0
-- Transformers: 4.45.2
-- Pytorch: 2.6.0.dev20240922+cu124
-- Datasets: 3.0.1
-- Tokenizers: 0.20.0
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 5
 
-## Citations
+### Training results
 
 
 
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.45.2
+- Pytorch 2.4.0
+- Datasets 3.0.2
+- Tokenizers 0.20.0

adapter_config.json

@@ -1,34 +1,34 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.01,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "q_proj",
-    "up_proj",
-    "gate_proj",
-    "down_proj",
-    "o_proj",
-    "v_proj",
-    "k_proj"
-  ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb3d946af99b14f14080212461b54ccdd4dde9e871839e64b28d9dc1f78f811
-size 1073263472
+oid sha256:db8a91ccfcd440c96c1304447baba0ddc73541baaa4f6d0346bc9c2d18e5e291
+size 1411430208

runs/Oct23_01-44-10_0df87f83d07d/events.out.tfevents.1729647852.0df87f83d07d.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a21509782e4b600ef0e00098404fecf9b794e050512d81f7651c1a0991d362
+size 6364

special_tokens_map.json

@@ -1,21 +1,21 @@
-{
-  "additional_special_tokens": [
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
-  "bos_token": "<|im_start|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|im_end|>"
-}
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:510d12ec255f4cb0304aa5428d699c354c1a49696b427a2748a7b03bb7bbb575
-size 17210296
+oid sha256:a5183f5ff3c6a5bb58733e2d242ef948580948862f5c16473564707ff1e5b48e
+size 17210395

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47cf5c33e0553608bd82b8d6cf0d0e5abae883131af6b0a85ecd6a370683779b
-size 5432
+oid sha256:f0ecc28b9d61250a22a4f59bc20e8e210efab66c53df03e3cb30011c8e909453
+size 5496