Model save

README.md

@@ -1,23 +1,57 @@
 ---
 base_model: unsloth/llama-2-7b-chat-bnb-4bit
-language:
-- en
+library_name: peft
 license: apache-2.0
 tags:
-- text-generation-inference
-- transformers
 - unsloth
-- llama
 - trl
 - sft
+- generated_from_trainer
+model-index:
+- name: Llama-2-7b-chat-hf-hotel-booking-assistant
+  results: []
 ---
 
-# Uploaded  model
+<!-- 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. -->
 
-- **Developed by:** M-A-E
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/llama-2-7b-chat-bnb-4bit
+# Llama-2-7b-chat-hf-hotel-booking-assistant
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+This model is a fine-tuned version of [unsloth/llama-2-7b-chat-bnb-4bit](https://huggingface.co/unsloth/llama-2-7b-chat-bnb-4bit) on an unknown dataset.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+## 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: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- training_steps: 60
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/llama-2-7b-chat-bnb-4bit",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:047fe78e1e3f21ab4e0595a19bc7e25780602d8305792ba322d7df902abce0a5
+size 159967880

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 2048,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -32,15 +32,11 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
-  "max_length": 2048,
   "model_max_length": 4096,
   "pad_token": "<unk>",
-  "padding_side": "left",
+  "padding_side": "right",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4df80b8e13ea13cda04c01234baa8cd80e5966c0a0bd1ded5e38597b8b967ff3
+size 5176