Upload 9 files

README.md

@@ -0,0 +1,41 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-0.5B-Chat
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+widget:
+- text: "What is the sum of the first 10 positive integers?"
+---
+
+# Qwen1.5-0.5B-Chat with EPFL DPO fine-tuning
+
+Qwen1.5-0.5B-Chat DPO fine-tuned on open-ended and multiple choice questions from different EPFL courses and the Orca Math dataset that consists of ~200K grade school math word problems.
+
+## Model Details
+
+### Model Description
+
+The model was developed during the course Modern Natural Language Processing (CS-552). 
+Its aim is to fine-tune the base model (Qwen/Qwen1.5-0.5B-Chat) to accurately 
+answer open-ended and multiple-choice questions from various EPFL courses and Orca Math dataset.
+
+- **Developed by:** Emma Lise Boehly, Ahmed Aziz Ben Haj Hmida and Jan Kokla
+- **Finetuned from model:** Qwen/Qwen1.5-0.5B-Chat
+
+## Training Details
+
+### Training Data
+
+HuggingFace dataset : microsoft/orca-math-word-problems-200k
+The EPFL dataset is not publicly available.
+
+### Training Procedure
+
+#### Training Hyperparameters
+
+- **Training regime:** cDPO with bf16 mixed precision, $\beta=0.2$, $lr=3 \times 10^{-6}$, and $label_smoothing=0.2$
+
+- PEFT 0.10.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "gate_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:e69dfabff37b278f553cf89f84b9514e0fa85268eaf5d4837c9dbfa14e474c16
+size 15183400

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_end|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "return_tensors": "pt",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}