batouln/gemma3_adapters

README.md

@@ -1,60 +1,59 @@
 ---
-library_name: peft
-license: gemma
-base_model: silma-ai/SILMA-9B-Instruct-v1.0
+base_model: unsloth/gemma-3-27b-it-unsloth-bnb-4bit
+library_name: transformers
+model_name: outputs
 tags:
-- base_model:adapter:silma-ai/SILMA-9B-Instruct-v1.0
-- lora
-- transformers
-pipeline_tag: text-generation
-model-index:
-- name: outputs
-  results: []
+- generated_from_trainer
+- sft
+- unsloth
+- trl
+licence: license
 ---
 
-<!-- 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. -->
+# Model Card for outputs
 
-# outputs
+This model is a fine-tuned version of [unsloth/gemma-3-27b-it-unsloth-bnb-4bit](https://huggingface.co/unsloth/gemma-3-27b-it-unsloth-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-This model is a fine-tuned version of [silma-ai/SILMA-9B-Instruct-v1.0](https://huggingface.co/silma-ai/SILMA-9B-Instruct-v1.0) on the None dataset.
+## Quick start
 
-## Model description
+```python
+from transformers import pipeline
 
-More information needed
+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="batoulnn/outputs", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
+## Training procedure
 
-More information needed
+ 
 
-## Training procedure
 
-### Training hyperparameters
+This model was trained with SFT.
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 2
-- eval_batch_size: 8
-- seed: 3407
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 8
-- optimizer: Use adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 5
-- training_steps: 700
+### Framework versions
 
-### Training results
+- TRL: 0.19.1
+- Transformers: 4.53.2
+- Pytorch: 2.7.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
 
+## Citations
 
 
-### Framework versions
 
-- PEFT 0.16.0
-- Transformers 4.53.2
-- Pytorch 2.7.1+cu126
-- Datasets 4.0.0
-- Tokenizers 0.21.2
+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

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "silma-ai/SILMA-9B-Instruct-v1.0",
+  "base_model_name_or_path": "unsloth/gemma-3-27b-it-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -13,24 +13,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 64,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "down_proj",
-    "k_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj",
     "up_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50dd0ad1ae7af5f1a942de10ab0417433c49b711a87a5f9ed2edc77716d669e
-size 864368280
+oid sha256:11a6572ca8f3f5696035a087b09db1a4f20baaa5103b1f3bb2b0ab4a0e2af2fe
+size 932178320

added_tokens.json

@@ -1,28 +1,3 @@
 {
-  "</think>": 151668,
-  "</tool_call>": 151658,
-  "</tool_response>": 151666,
-  "<think>": 151667,
-  "<tool_call>": 151657,
-  "<tool_response>": 151665,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
+  "<image_soft_token>": 262144
 }

chat_template.jinja

@@ -1,5 +1,47 @@
-{{ '<bos>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<start_of_turn>user
-' + content + '<end_of_turn>
-<start_of_turn>model
-' }}{% elif message['role'] == 'assistant' %}{{ content + '<end_of_turn>
-' }}{% endif %}{% endfor %}
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- 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" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

special_tokens_map.json

@@ -1,8 +1,5 @@
 {
-  "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
-  ],
+  "boi_token": "<start_of_image>",
   "bos_token": {
     "content": "<bos>",
     "lstrip": false,
@@ -10,13 +7,15 @@
     "rstrip": false,
     "single_word": false
   },
+  "eoi_token": "<end_of_image>",
   "eos_token": {
-    "content": "<eos>",
+    "content": "<end_of_turn>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "image_token": "<image_soft_token>",
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c023eeb0d48ed0c7dd6a9696accb31e725946039229bdb3bd2ef4fb381ea1b8
-size 34363139
+oid sha256:a872e3bb510a751b26bd65f61aad05f948c9cf78fe4f787aebd197b393cc4081
+size 33384667

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a3d91e846b1286eba30a7b3c08ce17616b56ac77c240a444e35daf77903841
-size 5713
+oid sha256:37f032582a3365e34790b296b49ea6eeb3ab720d82783d279345a9fa1faf47e3
+size 6097