Add files using upload-large-folder tool

.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 +1,57 @@
+---
+library_name: transformers
+model_name: user_gemma_3_270m_it
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for user_gemma_3_270m_it
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.25.1
+- Transformers: 4.57.3
+- Pytorch: 2.9.0
+- Datasets: 4.2.0
+- Tokenizers: 0.22.1
+
+## 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/README.md

@@ -0,0 +1,209 @@
+---
+base_model: /leonardo_scratch/large/userexternal/apetruzz/ale_priv/base_models/gemma-3-270m-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/leonardo_scratch/large/userexternal/apetruzz/ale_priv/base_models/gemma-3-270m-it
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

adapter/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/leonardo_scratch/large/userexternal/apetruzz/ale_priv/base_models/gemma-3-270m-it",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3aba267f8e22bc208cc54917f79cb43158c2c27fa2fe68738a89883d44be08d
+size 121537408

chat_template.jinja

@@ -0,0 +1,73 @@
+{{ bos_token }}
+{%- set system_prompt = "You are an advanced user simulator. Your objective is to generate realistic and coherent user responses in a dialogue with a recommendation system based on the user persona, interaction history and target item provided.
+Use the following guidelines:
+1. Adhere to the user persona: The user's behavior, tone, and responses must align with the specified persona.
+2. Use the tone inferred from the user's past reviews in the interaction history.
+3. Ensure that the user's responses are contextually relevant to the ongoing conversation and the target item.
+4. Maintain coherence and natural flow in the dialogue." -%}
+
+{%- set first_user_prefix = system_prompt + '
+
+' -%}
+{%- set loop_messages = messages -%}
+
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- elif (message['role'] == 'system') -%}
+        {{ raise_exception("This template is hardcoded and does not accept 'system' messages.") }}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message.content is string -%}
+        {# This handles regular assistant/model responses #}
+{{ message.content | trim }}
+    {%- elif message.content is mapping -%}
+# Category
+{{ message.content.category | trim }}{{ "\n\n" }}
+# User Persona
+{{ message.content.user_persona | trim }}{{ "\n" }}
+{%- if message.content.interacted_items | length > 0 -%}
+{{ "\n\n" }}# Interaction history
+    {%- for item in message.content.interacted_items -%}
+{{ "\n" }}## Item Name: {{ item.item_name | trim }}
+## Description: {{ item.description | trim }}
+## Visual Description: {{ item.visual_description | trim }}
+## Review: {{ item.review |  trim }}{{ "\n" }}
+    {%- endfor -%}
+{%- endif -%}
+{{ "\n" }}
+# Target item
+## Item Name: {{ message.content.target_item.item_name | trim }}
+## Description: {{ message.content.target_item.description | trim }}
+## Visual Description: {{ message.content.target_item.visual_description | trim }}
+## Review: {{ message.content.target_item.review |  trim }}{{ "\n" }}
+    {%- if message.content.messages | length > 0 -%}
+{{ "\n\n" }}# Conversation so far
+        {%- for turn in message.content.messages[-2:] -%}
+            {%- if turn['role'] == 'assistant' -%}
+{{ "\n" }}CRS: "{{turn['content'] | trim}}"
+            {%- else -%}
+{{ "\n" }}USR: "{{turn['content'] | trim}}"
+            {%- endif -%}
+        {%- endfor -%}
+        {{ "\n" }}
+{{ "Generate the next user response based on the above information." }}
+    {%- else -%}
+        {{ "\nGenerate the first user message based on the above information." }}
+    {%- endif -%}
+{%- else -%}
+    {{ raise_exception("Invalid content type: must be string, mapping (dict), or iterable (list).") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -0,0 +1,54 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 512,
+  "transformers_version": "4.57.3",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59744119fbd5bfda1f364d348ebeda7dc2903e2cc9ab0893675b1f6529a103e3
+size 1072419256

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

training_config.yaml

@@ -0,0 +1,54 @@
+# config.yaml
+
+# General settings for the training run
+general:
+  output_dir: "/leonardo_scratch/large/userexternal/apetruzz/ale_priv/SpecialIssue/results/v3/user_gemma_3_270m_it" # Directory to save the final model adapters
+
+# Model configuration
+model:
+  name: "/leonardo_scratch/large/userexternal/apetruzz/ale_priv/base_models/gemma-3-270m-it" # Base model from Hugging Face Hub
+  max_seq_length: 2048 # Maximum sequence length for the tokenizer and model
+  trust_remote_code: true
+  chat_template_file: "/leonardo_work/IscrC_SYMBREC/ale/UserSimTraining/data/chat_template.jinja"
+
+# Dataset configuration
+dataset:
+  name: "/leonardo_work/IscrC_SYMBREC/ale/UserSimTraining/data/all_processed_prompts_new.jsonl" # Dataset from Hugging Face Hub or local path
+  text_field: "prompt" # The name of the column in the dataset that contains the text
+
+# PEFT (LoRA) configuration
+peft_config:
+  lora_alpha: 32
+  lora_dropout: 0.1
+  r: 128
+  bias: "none"
+  task_type: "CAUSAL_LM"
+  target_modules: "all-linear"
+
+# SFTTrainer-specific arguments
+trainer_args:
+  packing: false
+
+# Logging configuration
+logging:
+  use_wandb: false # Set to true to enable Weights & Biases logging
+
+# Hugging Face TrainingArguments
+# See https://huggingface.co/docs/transformers/main_classes/trainer#transformers.TrainingArguments
+training_args:
+  num_train_epochs: 5
+  per_device_train_batch_size: 8
+  gradient_accumulation_steps: 1
+  optim: "adamw_torch"
+  logging_steps: 25
+  learning_rate: 0.0002 # 2e-4
+  weight_decay: 0.001
+  fp16: false
+  bf16: true
+  max_grad_norm: 1.0
+  max_steps: -1
+  warmup_ratio: 0.05
+  lr_scheduler_type: "constant"
+  #evaluation_strategy: "epoch"
+  save_strategy: "epoch"
+