adapter

sft2/.gitattributes

@@ -0,0 +1 @@
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

sft2/README.md

@@ -0,0 +1,197 @@
+---
+library_name: peft
+license: gemma
+base_model: Lambent/Mira-v1.23.1-27B-dpo
+tags:
+- axolotl
+- base_model:adapter:Lambent/Mira-v1.23.1-27B-dpo
+- lora
+- transformers
+datasets:
+- Lambent/mira-offerings-jan29-8k
+- Lambent/mira-dpo-v1
+- Lambent/rp-ani-hydrated
+- Lambent/rp-mira-kurt-multi-hydrated
+- Lambent/mira-memories-2026-01-29
+- Lambent/mira-training-data
+- Lambent/mira-training-data-inclusive
+- Lambent/ifeval-shard-shard-3-of-7
+- Lambent/smoltalk2-instruct-shard-2-of-5
+pipeline_tag: text-generation
+model-index:
+- name: sft2
+  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: `0.13.0.dev0`
+```yaml
+base_model: Lambent/Mira-v1.23.1-27B-dpo
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+
+save_safetensors: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+ddp_find_unused_parameters: true
+
+eot_tokens:
+  - <end_of_turn>
+
+# total_num_tokens: 
+datasets:
+  - path: Lambent/mira-offerings-jan29-8k
+    type: completion
+    split: train
+
+  - path: Lambent/mira-dpo-v1
+    type:
+      system_prompt: ""
+      field_system: system
+      field_instruction: prompt
+      field_output: chosen
+
+  - path: Lambent/rp-ani-hydrated
+    type: chat_template
+    split: train
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+  - path: Lambent/rp-mira-kurt-multi-hydrated
+    type: chat_template
+    split: train
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+
+  - path: Lambent/mira-memories-2026-01-29
+    type: chat_template
+    split: train
+  - path: Lambent/mira-training-data
+    type: chat_template
+    split: train
+  - path: Lambent/mira-training-data-inclusive
+    type: chat_template
+    split: train
+
+
+  - path: Lambent/ifeval-shard-shard-3-of-7
+    type: chat_template
+    split: train
+  - path: Lambent/smoltalk2-instruct-shard-2-of-5
+    type: chat_template
+    split: train
+
+dataset_prepared_path: prepared-sft
+output_dir: ./sft2
+
+seed: 129262
+
+sequence_len: 8192
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: false
+
+adapter: qlora
+lora_model_dir:
+lora_r: 256
+lora_alpha: 256
+lora_dropout: 0.1
+lora_target_modules: 'model.language_model.layers.[\d]+.(cross_attn|self_attn).(q|k|v|o)_proj'
+
+wandb_project: mira-qlora-sft-jan29
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+num_epochs: 1
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 5e-7
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_ratio: 0.1
+saves_per_epoch: 2
+save_total_limit: 1
+debug:
+deepspeed:
+weight_decay: 0.001
+fsdp:
+fsdp_config:
+
+
+
+```
+
+</details><br>
+
+# sft2
+
+This model is a fine-tuned version of [Lambent/Mira-v1.23.1-27B-dpo](https://huggingface.co/Lambent/Mira-v1.23.1-27B-dpo) on the Lambent/mira-offerings-jan29-8k, the Lambent/mira-dpo-v1, the Lambent/rp-ani-hydrated, the Lambent/rp-mira-kurt-multi-hydrated, the Lambent/mira-memories-2026-01-29, the Lambent/mira-training-data, the Lambent/mira-training-data-inclusive, the Lambent/ifeval-shard-shard-3-of-7 and the Lambent/smoltalk2-instruct-shard-2-of-5 datasets.
+
+## 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: 5e-07
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 129262
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 33
+- training_steps: 331
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.17.0
+- Transformers 4.55.2
+- Pytorch 2.7.1+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

sft2/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Lambent/Mira-v1.23.1-27B-dpo",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "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": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "model.language_model.layers.[\\d]+.(cross_attn|self_attn).(q|k|v|o)_proj",
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft2/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d201a79a7d42b04d9b5eebaac69e66fec28952ea9ea1bc7e55d20100981af76f
+size 2145462824

sft2/added_tokens.json

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

sft2/chat_template.jinja

@@ -0,0 +1,53 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if message['role'] == 'assistant' -%}
+        {%- set role = 'model' -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '\n' + (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 -%}
+    {%- if message['role'] == 'assistant' and message.tool_calls is defined -%}
+        {%- for tool_call in message.tool_calls -%}
+            {%- if tool_call.function is defined -%}
+                {%- set tc = tool_call.function -%}
+            {%- else -%}
+                {%- set tc = tool_call -%}
+            {%- endif -%}
+            {{ '\n<tool_call>\n{"name": "' + tc.name + '", "arguments": ' }}
+            {%- if tc.arguments is string -%}
+                {{ tc.arguments }}
+            {%- else -%}
+                {{ tc.arguments | tojson }}
+            {%- endif -%}
+            {{ '}\n</tool_call>' }}
+        {%- endfor -%}
+    {%- endif -%}
+    {{ '<end_of_turn>\n' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model\n' }}
+{%- endif -%}

sft2/config.json

@@ -0,0 +1,141 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "dtype": "bfloat16",
+  "eoi_token_index": 256000,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "text_config": {
+    "_sliding_window_pattern": 6,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "dtype": "bfloat16",
+    "final_logit_softcapping": null,
+    "head_dim": 128,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 5376,
+    "initializer_range": 0.02,
+    "intermediate_size": 21504,
+    "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",
+      "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",
+      "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": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 62,
+    "num_key_value_heads": 16,
+    "query_pre_attn_scalar": 168,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "torch_dtype": "bfloat16",
+    "use_bidirectional_attention": false,
+    "use_cache": false,
+    "vocab_size": 262145
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  }
+}

sft2/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
+  }
+}

sft2/processor_config.json

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

sft2/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": "<end_of_turn>",
+    "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
+  }
+}

sft2/tokenizer.json

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

sft2/tokenizer.model

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