Upload Phi-4-mini N2 schema retrieval adapter model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+base_model: unsloth/Phi-4-mini-instruct-bnb-4bit
+library_name: peft
+model_name: n2_schema_retrieval_model
+tags:
+- base_model:adapter:unsloth/Phi-4-mini-instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for n2_schema_retrieval_model
+
+This model is a fine-tuned version of [unsloth/Phi-4-mini-instruct-bnb-4bit](https://huggingface.co/unsloth/Phi-4-mini-instruct-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+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="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yepster/n2-schema-retrieval-unsloth/runs/5pwqqkrw) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.16.0
+- TRL: 0.19.1
+- Transformers: 4.53.1
+- Pytorch: 2.7.1
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2
+
+## Citations
+
+
+
+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 Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Phi-4-mini-instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 1024,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 512,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51db3afe4bf926a12de3a30609209f673fa74d6d0b32fa9d5d814c8c3071b0f3
+size 402662000

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021,
+  "<｜PAD▁TOKEN｜>": 200029
+}

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}

config.json

@@ -0,0 +1,145 @@
+{
+    "architectures": [
+        "Phi3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_phi3.Phi3Config",
+        "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
+        "AutoTokenizer": "Xenova/gpt-4o"
+    },
+    "bos_token_id": 199999,
+    "embd_pdrop": 0.0,
+    "eos_token_id": 200020,
+    "full_attn_mod": 1,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "interpolate_factor": 1,
+    "lm_head_bias": false,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_type": "phi3",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "original_max_position_embeddings": 4096,
+    "pad_token_id": 200029,
+    "partial_rotary_factor": 0.75,
+    "resid_pdrop": 0.0,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "long_factor": [
+            1,
+            1.118320672,
+            1.250641126,
+            1.398617824,
+            1.564103225,
+            1.74916897,
+            1.956131817,
+            2.187582649,
+            2.446418898,
+            2.735880826,
+            3.059592084,
+            3.421605075,
+            3.826451687,
+            4.279200023,
+            4.785517845,
+            5.351743533,
+            5.984965424,
+            6.693110555,
+            7.485043894,
+            8.370679318,
+            9.36110372,
+            10.4687158,
+            11.70738129,
+            13.09260651,
+            14.64173252,
+            16.37415215,
+            18.31155283,
+            20.47818807,
+            22.90118105,
+            25.61086418,
+            28.64115884,
+            32.03,
+            32.1,
+            32.13,
+            32.23,
+            32.6,
+            32.61,
+            32.64,
+            32.66,
+            32.7,
+            32.71,
+            32.93,
+            32.97,
+            33.28,
+            33.49,
+            33.5,
+            44.16,
+            47.77
+        ],
+        "short_factor": [
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0
+        ],
+        "type": "longrope"
+    },
+    "rope_theta": 10000.0,
+    "sliding_window": 262144,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.53.1",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.7.2",
+    "use_cache": true,
+    "vocab_size": 200064
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 199999,
+  "eos_token_id": 200020,
+  "max_length": 131072,
+  "pad_token_id": 200029,
+  "transformers_version": "4.53.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1865c38a88cffd468a9b2fad5d08b720af7ca2c921a6697df9de69223810870c
+size 2891584764

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜PAD▁TOKEN｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "�",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b10016a39382ff2d24acc20a291ed83243a26c4549ab01f6240e72c6291d56
+size 15524472

tokenizer_config.json

@@ -0,0 +1,128 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "3251": {
+      "content": "�",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200029": {
+      "content": "<｜PAD▁TOKEN｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<｜PAD▁TOKEN｜>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "�"
+}

training_args.json

@@ -0,0 +1,35 @@
+{
+  "model": "phi4-mini",
+  "use_unsloth_model": true,
+  "dataset": "UWV/wim-instruct-wiki-to-jsonld-agent-steps",
+  "max_samples": null,
+  "filter_n2_only": true,
+  "max_seq_length": 8192,
+  "batch_size": 32,
+  "gradient_accumulation_steps": 1,
+  "max_steps": 5000,
+  "learning_rate": 2e-05,
+  "warmup_steps": 100,
+  "max_grad_norm": 1.0,
+  "lora_r": 512,
+  "lora_alpha": 1024,
+  "lora_dropout": 0.05,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "load_in_4bit": true,
+  "use_gradient_checkpointing": false,
+  "rope_scaling": null,
+  "output_dir": "/data/model_outputs/n2_schema_retrieval_model",
+  "assistant_only_loss": true,
+  "no_eval": false,
+  "num_workers": 8,
+  "full_finetune": false,
+  "wandb": true,
+  "seed": 42,
+  "push_to_hub": false,
+  "hub_model_id": null
+}