mindchain/qwen35-08b-fullft-kaggle-smoke

README.md

@@ -1,53 +1,59 @@
 ---
-library_name: transformers
-license: apache-2.0
 base_model: Qwen/Qwen3.5-0.8B
+library_name: transformers
+model_name: outputs
 tags:
 - generated_from_trainer
-model-index:
-- name: outputs
-  results: []
+- 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. -->
-
-# outputs
-
-This model is a fine-tuned version of [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) on the None dataset.
+# Model Card for outputs
 
-## Model description
+This model is a fine-tuned version of [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-More information needed
+## Quick start
 
-## Intended uses & limitations
+```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="mindchain/outputs", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-## 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: 2e-05
-- train_batch_size: 2
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- num_epochs: 1
+### Framework versions
 
-### Training results
+- TRL: 0.24.0
+- Transformers: 5.2.0
+- Pytorch: 2.10.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
 
+## Citations
 
 
-### Framework versions
 
-- Transformers 5.2.0
-- Pytorch 2.9.0+cu126
-- Datasets 4.0.0
-- Tokenizers 0.22.2
+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}}
+}
+```

config.json

@@ -1,75 +1,106 @@
 {
   "architectures": [
-    "Qwen3_5ForCausalLM"
+    "Qwen3_5ForConditionalGeneration"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "attn_output_gate": true,
-  "bos_token_id": null,
-  "dtype": "bfloat16",
-  "eos_token_id": 248044,
-  "full_attention_interval": 4,
-  "head_dim": 256,
-  "hidden_act": "silu",
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 3584,
-  "layer_types": [
-    "linear_attention",
-    "linear_attention",
-    "linear_attention",
-    "full_attention",
-    "linear_attention",
-    "linear_attention",
-    "linear_attention",
-    "full_attention",
-    "linear_attention",
-    "linear_attention",
-    "linear_attention",
-    "full_attention",
-    "linear_attention",
-    "linear_attention",
-    "linear_attention",
-    "full_attention",
-    "linear_attention",
-    "linear_attention",
-    "linear_attention",
-    "full_attention",
-    "linear_attention",
-    "linear_attention",
-    "linear_attention",
-    "full_attention"
-  ],
-  "linear_conv_kernel_dim": 4,
-  "linear_key_head_dim": 128,
-  "linear_num_key_heads": 16,
-  "linear_num_value_heads": 16,
-  "linear_value_head_dim": 128,
-  "mamba_ssm_dtype": "float32",
-  "max_position_embeddings": 262144,
-  "mlp_only_layers": [],
-  "model_type": "qwen3_5_text",
-  "mtp_num_hidden_layers": 1,
-  "mtp_use_dedicated_embeddings": false,
-  "num_attention_heads": 8,
-  "num_hidden_layers": 24,
-  "num_key_value_heads": 2,
-  "pad_token_id": null,
-  "partial_rotary_factor": 0.25,
-  "rms_norm_eps": 1e-06,
-  "rope_parameters": {
-    "mrope_interleaved": true,
-    "mrope_section": [
-      11,
-      11,
-      10
+  "dtype": "float16",
+  "eos_token_id": 248046,
+  "image_token_id": 248056,
+  "model_name": "Qwen/Qwen3.5-0.8B",
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "float16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 3584,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
     ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 16,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 8,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "pad_token_id": null,
     "partial_rotary_factor": 0.25,
-    "rope_theta": 10000000,
-    "rope_type": "default"
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 248320
   },
   "tie_word_embeddings": true,
   "transformers_version": "5.2.0",
+  "unsloth_version": "2026.3.4",
   "use_cache": false,
-  "vocab_size": 248320
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 12,
+    "dtype": "float16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "model_type": "qwen3_5",
+    "num_heads": 12,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 1024,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
 }

generation_config.json

@@ -1,6 +1,10 @@
 {
   "_from_model_config": true,
-  "eos_token_id": 248044,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
   "transformers_version": "5.2.0",
   "use_cache": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e59c71f60f117d3ef40a381b1aff3bb2bfbf63ff0c0ab0def4e875bb3571c00b
-size 1504827608
+oid sha256:3f87e433c1fe3113364134d74bdd4b4822fe17baf18415d658f9a1b902865a2d
+size 1706030056

processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16e71421c5d4e5b01c8be19a0ed8c9b91f9fd257ed0b17b39182561f48376ca9
-size 19989441
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -21,7 +21,9 @@
     "vision_eos_token": "<|vision_end|>"
   },
   "pad_token": "<|endoftext|>",
+  "padding_side": "right",
   "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "TokenizersBackend",
   "unk_token": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c7020c15dc8548fc47a78610f940668504546b180052b84b1d8c45f40c8e0c
-size 5137
+oid sha256:6e1228d543a1963a524818d62c1fcf58704f34e38c271cd9b5f53fd914ea81b3
+size 5713