Upload folder using huggingface_hub

.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 +1,130 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-1b/0
+  results: []
+---
+
+<!-- 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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.12.2`
+```yaml
+base_model: /lustre/fswork/projects/rech/qwv/udv55np/Gemma/base/gemma-3-1b
+
+datasets:
+- path: /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking
+  ds_type: json
+  type: chat_template
+  field_messages: conversations
+  data_files:
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0007.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0009.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0005.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0006.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0014.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0010.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0012.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0008.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0001.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0002.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0013.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0015.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0004.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0011.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0000.jsonl
+  - /lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0003.jsonl
+
+dataset_prepared_path: /lustre/fswork/projects/rech/dgo/udv55np/dataset_gemma/Nemotron-Super-49B-v1_5/split_0
+tokenizer_config: "/lustre/fswork/projects/rech/qwv/udv55np/Gemma/base/gemma-3-27b"
+chat_template: gemma3
+eot_tokens:
+  - "<end_of_turn>"
+
+shuffle_merged_datasets: true
+output_dir: /lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-1b/0
+
+sequence_len: 16384
+sample_packing: true
+
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+num_epochs: 0.6
+auto_resume_from_checkpoints: true
+
+optimizer: adamw_torch_fused
+lr_scheduler: warmup_stable_decay
+learning_rate: 2e-5
+lr_scheduler_kwargs:
+  num_decay_steps: 200
+  min_lr_ratio: 0.1
+warmup_steps: 100
+
+bf16: true
+tf32: false
+
+gradient_checkpointing: true
+logging_steps: 10
+flash_attention: true
+
+evals_per_epoch: 0
+saves_per_epoch: 1
+save_total_limit: 20
+save_only_model: true
+
+use_tensorboard: true
+deepspeed: /lustre/fswork/projects/rech/qwv/udv55np/axolotl/zero3.json
+
+```
+
+</details><br>
+
+# lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-1b/0
+
+This model was trained from scratch on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- 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: warmup_stable_decay
+- lr_scheduler_warmup_steps: 100
+- training_steps: 711
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.55.2
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ 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 -%}

config.json

@@ -0,0 +1,62 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "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",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 512,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "use_cache": false,
+  "vocab_size": 262145
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.55.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb8cff1740667520b79e4224e30dd72d4a336ace27a244066d8a2e6fefb78bf
+size 1999813512

runs/Nov24_00-08-13_jzxh067/events.out.tfevents.1763939397.jzxh067.4127210.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359cb51f53bb81206893fc194fb89c4c4784a0a287f5bdbe36fb5d51141c674a
+size 40897

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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

tokenizer.model

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

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4beeb40d5c43247b10bae051c9418b0d39d9526943b534eb48da2c6bf260af4
+size 10424