Upload folder using huggingface_hub

README.md

@@ -0,0 +1,137 @@
+---
+library_name: transformers
+license: other
+base_model: LiquidAI/LFM2.5-1.2B-Instruct
+tags:
+- generated_from_trainer
+datasets:
+- WokeAI/polititune-tankie-warmup-3
+model-index:
+- name: model-output
+  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: `0.15.0.dev0`
+```yaml
+# === Model Configuration ===
+base_model: LiquidAI/LFM2.5-1.2B-Instruct
+load_in_8bit: false
+load_in_4bit: false
+
+# === Training Setup ===
+num_epochs: 4
+micro_batch_size: 2
+gradient_accumulation_steps: 2
+sequence_len: 2048
+sample_packing: true
+pad_to_sequence_len: true
+
+# === Hyperparameter Configuration ===
+optimizer: adamw_torch_8bit
+learning_rate: 5e-5
+lr_scheduler: constant
+weight_decay: 0.001
+max_grad_norm: 0.1
+warmup_ratio: 0.2
+cosine_min_lr_ratio: 0.1
+
+# === Data Configuration ===
+datasets:
+  - path: WokeAI/polititune-tankie-warmup-3
+    type: chat_template
+    split: train
+chat_template: tokenizer_default
+
+dataset_prepared_path: last_run_prepared
+
+# === Hardware Optimization ===
+gradient_checkpointing: offload
+
+# === Wandb Tracking ===
+wandb_project: polititune-3-lfm2.5_1.2b-warmup
+
+# === Checkpointing ===
+saves_per_epoch: 1
+
+# === Advanced Settings ===
+output_dir: ./model-output
+bf16: auto
+flash_attention: true
+train_on_inputs: false
+group_by_length: false
+logging_steps: 1
+trust_remote_code: false
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+    #  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+
+fsdp:
+  - auto_wrap
+  - full_shard
+fsdp_config:
+  fsdp_version: 2
+  fsdp_offload_params: false
+  fsdp_cpu_ram_efficient_loading: true
+  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
+  fsdp_transformer_layer_cls_to_wrap: Lfm2DecoderLayer
+  fsdp_state_dict_type: SHARDED_STATE_DICT
+  fsdp_sharding_strategy: FULL_SHARD
+  fsdp_reshard_after_forward: true
+  fsdp_activation_checkpointing: true # will disable if doesnt work
+
+```
+
+</details><br>
+
+# model-output
+
+This model is a fine-tuned version of [LiquidAI/LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) on the WokeAI/polititune-tankie-warmup-3 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 24
+- training_steps: 120
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.0.0
+- Pytorch 2.8.0+cu128
+- Datasets 4.5.0
+- Tokenizers 0.22.2

chat_template.jinja

@@ -0,0 +1,45 @@
+{{- bos_token -}}
+{%- set keep_past_thinking = keep_past_thinking | default(false) -%}
+{%- set ns = namespace(system_prompt="") -%}
+{%- if messages[0]["role"] == "system" -%}
+    {%- set ns.system_prompt = messages[0]["content"] -%}
+    {%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+    {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
+    {%- for tool in tools -%}
+        {%- if tool is not string -%}
+            {%- set tool = tool | tojson -%}
+        {%- endif -%}
+        {%- set ns.system_prompt = ns.system_prompt + tool -%}
+        {%- if not loop.last -%}
+            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns.system_prompt = ns.system_prompt + "]" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- set ns.last_assistant_index = -1 -%}
+{%- for message in messages -%}
+    {%- if message["role"] == "assistant" -%}
+        {%- set ns.last_assistant_index = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+    {{- "<|im_start|>" + message["role"] + "\n" -}}
+    {%- set content = message["content"] -%}
+    {%- if content is not string -%}
+        {%- set content = content | tojson -%}
+    {%- endif -%}
+    {%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
+        {%- if "</think>" in content -%}
+            {%- set content = content.split("</think>")[-1] | trim -%}
+        {%- endif -%}
+    {%- endif -%}
+    {{- content + "<|im_end|>\n" -}}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 2048,
+  "block_ff_dim": 12288,
+  "block_ffn_dim_multiplier": 1.0,
+  "block_mlp_init_scale": 1.0,
+  "block_multiple_of": 256,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "conv_dim": 2048,
+  "conv_use_xavier_init": true,
+  "dtype": "bfloat16",
+  "eos_token_id": 7,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 32,
+  "num_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "tie_embedding": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

debug.log

@@ -0,0 +1,11 @@
+[2026-02-08 20:44:08,881] [WARNING] [huggingface_hub.utils._http._warn_on_warning_headers:779] [PID:10500] Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
+[2026-02-08 20:44:11,018] [WARNING] [py.warnings._showwarnmsg:110] [PID:10500] /root/axolotl/.venv/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4807: UserWarning: No device id is provided via `init_process_group` or `barrier `. Using the current device set by the user. 
+  warnings.warn(  # warn only once
+
+
+[2026-02-08 20:44:36,298] [WARNING] [accelerate.utils.dataclasses.__post_init__:1962] [PID:10500] sync_module_states is obsolete in FSDP2, as it is not needed anymore.Setting sync_module_states to None.Multiple deprecation warnings due to FSDP2 conversion:
+sharding_strategy is deprecated in favor of reshard_after_forward. This will be removed in a future version of Accelerate.
+[2026-02-08 20:44:37,935] [WARNING] [py.warnings._showwarnmsg:110] [PID:10500] /root/axolotl/.venv/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4807: UserWarning: No device id is provided via `init_process_group` or `barrier `. Using the current device set by the user. 
+  warnings.warn(  # warn only once
+
+

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81efae66588f15d91bd9f9fe617dd5fc607b6821d9ae6f41c012baefdb67bab8
+size 2609133520

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|pad|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}