初始化项目，由ModelHub XC社区提供模型

Model: BrandonHowe/Olmo7b-compassion-seed2-20261001-CPT-final
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,22 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+base_model: allenai/Olmo-3-1025-7B
+datasets:
+- CompassioninMachineLearning/compassion_12185_cleaned
+tags:
+- continued-pretraining
+- bf16
+---
+
+# Olmo7b-compassion-seed2-20261001-CPT-merged-epoch-2
+
+Standalone merged BF16 model from epoch 2.0, step 750.
+
+Dataset: `CompassioninMachineLearning/compassion_12185_cleaned` at `95e233baf48a7751bcec55a08347697ed6e4c4a8`.
+
+Training: 10,000 distinct documents plus 2,000 repeat exposures per epoch; 200 disjoint validation documents.
+
+Merged with Unsloth's native `save_pretrained_merged(save_method="merged_16bit")`. Weights are validated BF16 and packaged losslessly into eight safetensors shards. No adapter is required to load this model.
+
+See `run_manifest.json` for base revision, document selection hashes, training parameters and export validation. Training does not establish an improvement in compassion; evaluate that separately.

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Olmo3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "torch_dtype": "bfloat16",
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 65536,
+  "model_type": "olmo3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "attention_factor": 1.2079441541679836,
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 8.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "yarn"
+  },
+  "rope_theta": 500000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 100278,
+  "_name_or_path": "allenai/Olmo-3-1025-7B"
+}

export_validation.json

@@ -0,0 +1,15 @@
+{
+  "weight_shards": 8,
+  "weight_tensors": 355,
+  "weight_bytes": 14596022272,
+  "tensor_dtypes": [
+    "BF16"
+  ],
+  "finite_weights": true,
+  "packaging_changes_tensor_values": false,
+  "serialization_method": "huggingface_hub.save_torch_state_dict",
+  "max_shard_size": 2000000000,
+  "base_model": "allenai/Olmo-3-1025-7B",
+  "base_revision": "a81bae42db3975be1671e27b9c9a56da1a9f980f",
+  "merge_method": "Unsloth save_pretrained_merged(save_method=\"merged_16bit\")"
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    100257
+  ],
+  "max_length": 65536,
+  "pad_token_id": 100277,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ef4239c943256252222f13d44566f099602f813336a1332882c61a1ece1864
+size 1912065224

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1823a9448afe7f145504fc4f486a4df97c94c50ad24805061b8c4eafeb6c0163
+size 1933744224

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2065555a121258fe8415fb9b7d34b6a077bfee23dec6f12cc3bab14541951640
+size 1923258264

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b591da20022099474d96cca950479047d43b26bf36c15760a847a90a1ad2fb
+size 1933744288

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c81cbe8100c1b8211523e97b756ab14ad58ca9a2646c561486ba63480e19dd2
+size 1990367392

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a1f5e254461bb6b2ed5ea04ebcfb57743f65caa977824993f8d2a153bfc49c
+size 1968713272

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:327b3fdba4b4ed6edf6f9ad1a30ee01643c545093124ced57cbb5c84d85542a6
+size 1990367384

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b113fbe9eeb8e87e326af03941c1a88954e0d3ffad305f4f636aec18b01f5216
+size 943803544

model.safetensors.index.json

@@ -0,0 +1,362 @@
+{
+  "metadata": {
+    "total_size": 14596022272
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "lm_head.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.norm.weight": "model-00008-of-00008.safetensors"
+  }
+}

run_manifest.json

@@ -0,0 +1,521 @@
+{
+  "model": "allenai/Olmo-3-1025-7B",
+  "model_revision": "a81bae42db3975be1671e27b9c9a56da1a9f980f",
+  "dataset": "CompassioninMachineLearning/compassion_12185_cleaned",
+  "dataset_revision": "95e233baf48a7751bcec55a08347697ed6e4c4a8",
+  "dataset_text_column": "output",
+  "selection_hashes": {
+    "train": "b7d095dd7a11728f29c79f88ed960ab608c8a844ef38827eae69eb0f463e30b6",
+    "validation": "6a7fd9c09c280c911bb567bf56745e201909d42199d3aebff99f903617fed0a4"
+  },
+  "dataset_selection": {
+    "seed": 3407,
+    "source_rows": 12185,
+    "unique_train_rows": 10000,
+    "replay_rows": 2000,
+    "validation_rows": 200,
+    "holdout_rows": 200,
+    "train_tokens_per_epoch": 13938028,
+    "validation_tokens": 232969
+  },
+  "packages": {
+    "unsloth": "2026.9.2",
+    "unsloth-zoo": "2026.9.1",
+    "transformers": "4.57.6",
+    "trl": "0.22.2",
+    "datasets": "4.3.0",
+    "huggingface_hub": "0.36.2",
+    "tokenizers": "0.22.2",
+    "peft": "0.20.0",
+    "accelerate": "1.14.0",
+    "bitsandbytes": "0.50.2",
+    "wandb": "0.28.1",
+    "torch": "2.11.0+cu128",
+    "torchvision": "0.26.0+cu128",
+    "torchaudio": "2.11.0+cu128",
+    "triton": "3.6.0",
+    "xformers": "0.0.35"
+  },
+  "environment_packages": [
+    {
+      "name": "accelerate",
+      "version": "1.14.0"
+    },
+    {
+      "name": "aiohappyeyeballs",
+      "version": "2.7.1"
+    },
+    {
+      "name": "aiohttp",
+      "version": "3.14.3"
+    },
+    {
+      "name": "aiosignal",
+      "version": "1.4.0"
+    },
+    {
+      "name": "annotated-doc",
+      "version": "0.0.5"
+    },
+    {
+      "name": "annotated-types",
+      "version": "0.8.0"
+    },
+    {
+      "name": "anyio",
+      "version": "4.15.1"
+    },
+    {
+      "name": "attrs",
+      "version": "26.1.0"
+    },
+    {
+      "name": "bitsandbytes",
+      "version": "0.50.2"
+    },
+    {
+      "name": "certifi",
+      "version": "2026.7.22"
+    },
+    {
+      "name": "charset-normalizer",
+      "version": "3.5.2"
+    },
+    {
+      "name": "click",
+      "version": "8.5.0"
+    },
+    {
+      "name": "cuda-bindings",
+      "version": "12.9.7"
+    },
+    {
+      "name": "cuda-pathfinder",
+      "version": "1.6.0"
+    },
+    {
+      "name": "cuda-toolkit",
+      "version": "12.8.1"
+    },
+    {
+      "name": "cut-cross-entropy",
+      "version": "25.1.1"
+    },
+    {
+      "name": "datasets",
+      "version": "4.3.0"
+    },
+    {
+      "name": "diffusers",
+      "version": "0.39.0"
+    },
+    {
+      "name": "dill",
+      "version": "0.4.0"
+    },
+    {
+      "name": "docstring_parser",
+      "version": "0.18.0"
+    },
+    {
+      "name": "filelock",
+      "version": "3.32.3"
+    },
+    {
+      "name": "frozenlist",
+      "version": "1.8.0"
+    },
+    {
+      "name": "fsspec",
+      "version": "2025.9.0"
+    },
+    {
+      "name": "h11",
+      "version": "0.16.0"
+    },
+    {
+      "name": "hf_transfer",
+      "version": "0.1.9"
+    },
+    {
+      "name": "hf-xet",
+      "version": "1.6.0"
+    },
+    {
+      "name": "httpcore",
+      "version": "1.0.9"
+    },
+    {
+      "name": "httpx",
+      "version": "0.28.1"
+    },
+    {
+      "name": "huggingface_hub",
+      "version": "0.36.2"
+    },
+    {
+      "name": "idna",
+      "version": "3.20"
+    },
+    {
+      "name": "importlib_metadata",
+      "version": "9.0.1"
+    },
+    {
+      "name": "Jinja2",
+      "version": "3.1.6"
+    },
+    {
+      "name": "markdown-it-py",
+      "version": "4.2.0"
+    },
+    {
+      "name": "MarkupSafe",
+      "version": "3.0.3"
+    },
+    {
+      "name": "mdurl",
+      "version": "0.1.2"
+    },
+    {
+      "name": "mpmath",
+      "version": "1.3.0"
+    },
+    {
+      "name": "msgspec",
+      "version": "0.22.0"
+    },
+    {
+      "name": "multidict",
+      "version": "6.9.1"
+    },
+    {
+      "name": "multiprocess",
+      "version": "0.70.16"
+    },
+    {
+      "name": "nest-asyncio",
+      "version": "1.6.0"
+    },
+    {
+      "name": "networkx",
+      "version": "3.6.1"
+    },
+    {
+      "name": "numpy",
+      "version": "2.5.2"
+    },
+    {
+      "name": "nvidia-cublas-cu12",
+      "version": "12.8.4.1"
+    },
+    {
+      "name": "nvidia-cuda-cupti-cu12",
+      "version": "12.8.90"
+    },
+    {
+      "name": "nvidia-cuda-nvrtc-cu12",
+      "version": "12.8.93"
+    },
+    {
+      "name": "nvidia-cuda-runtime-cu12",
+      "version": "12.8.90"
+    },
+    {
+      "name": "nvidia-cudnn-cu12",
+      "version": "9.19.0.56"
+    },
+    {
+      "name": "nvidia-cufft-cu12",
+      "version": "11.3.3.83"
+    },
+    {
+      "name": "nvidia-cufile-cu12",
+      "version": "1.13.1.3"
+    },
+    {
+      "name": "nvidia-curand-cu12",
+      "version": "10.3.9.90"
+    },
+    {
+      "name": "nvidia-cusolver-cu12",
+      "version": "11.7.3.90"
+    },
+    {
+      "name": "nvidia-cusparse-cu12",
+      "version": "12.5.8.93"
+    },
+    {
+      "name": "nvidia-cusparselt-cu12",
+      "version": "0.7.1"
+    },
+    {
+      "name": "nvidia-nccl-cu12",
+      "version": "2.28.9"
+    },
+    {
+      "name": "nvidia-nvjitlink-cu12",
+      "version": "12.8.93"
+    },
+    {
+      "name": "nvidia-nvshmem-cu12",
+      "version": "3.4.5"
+    },
+    {
+      "name": "nvidia-nvtx-cu12",
+      "version": "12.8.90"
+    },
+    {
+      "name": "packaging",
+      "version": "26.3"
+    },
+    {
+      "name": "pandas",
+      "version": "3.0.6"
+    },
+    {
+      "name": "peft",
+      "version": "0.20.0"
+    },
+    {
+      "name": "pillow",
+      "version": "12.3.0"
+    },
+    {
+      "name": "pip",
+      "version": "26.2.1"
+    },
+    {
+      "name": "platformdirs",
+      "version": "4.12.2"
+    },
+    {
+      "name": "propcache",
+      "version": "0.5.4"
+    },
+    {
+      "name": "protobuf",
+      "version": "7.36.2"
+    },
+    {
+      "name": "psutil",
+      "version": "7.2.2"
+    },
+    {
+      "name": "pyarrow",
+      "version": "25.0.1"
+    },
+    {
+      "name": "pydantic",
+      "version": "2.13.5"
+    },
+    {
+      "name": "pydantic_core",
+      "version": "2.46.5"
+    },
+    {
+      "name": "Pygments",
+      "version": "2.21.0"
+    },
+    {
+      "name": "python-dateutil",
+      "version": "2.9.0.post0"
+    },
+    {
+      "name": "PyYAML",
+      "version": "6.0.3"
+    },
+    {
+      "name": "regex",
+      "version": "2026.9.29"
+    },
+    {
+      "name": "requests",
+      "version": "2.34.2"
+    },
+    {
+      "name": "rich",
+      "version": "15.0.0"
+    },
+    {
+      "name": "safetensors",
+      "version": "0.8.0"
+    },
+    {
+      "name": "sentencepiece",
+      "version": "0.2.2"
+    },
+    {
+      "name": "sentry-sdk",
+      "version": "2.71.0"
+    },
+    {
+      "name": "setuptools",
+      "version": "78.1.0"
+    },
+    {
+      "name": "shellingham",
+      "version": "1.5.4"
+    },
+    {
+      "name": "six",
+      "version": "1.17.0"
+    },
+    {
+      "name": "structlog",
+      "version": "26.1.0"
+    },
+    {
+      "name": "sympy",
+      "version": "1.14.0"
+    },
+    {
+      "name": "tokenizers",
+      "version": "0.22.2"
+    },
+    {
+      "name": "torch",
+      "version": "2.11.0+cu128"
+    },
+    {
+      "name": "torchao",
+      "version": "0.18.0"
+    },
+    {
+      "name": "torchaudio",
+      "version": "2.11.0+cu128"
+    },
+    {
+      "name": "torchvision",
+      "version": "0.26.0+cu128"
+    },
+    {
+      "name": "tqdm",
+      "version": "4.70.1"
+    },
+    {
+      "name": "transformers",
+      "version": "4.57.6"
+    },
+    {
+      "name": "triton",
+      "version": "3.6.0"
+    },
+    {
+      "name": "trl",
+      "version": "0.22.2"
+    },
+    {
+      "name": "typeguard",
+      "version": "4.6.0"
+    },
+    {
+      "name": "typer",
+      "version": "0.27.2"
+    },
+    {
+      "name": "typing_extensions",
+      "version": "4.16.0"
+    },
+    {
+      "name": "typing-inspection",
+      "version": "0.4.4"
+    },
+    {
+      "name": "tyro",
+      "version": "1.0.16"
+    },
+    {
+      "name": "unsloth",
+      "version": "2026.9.2"
+    },
+    {
+      "name": "unsloth_zoo",
+      "version": "2026.9.1"
+    },
+    {
+      "name": "urllib3",
+      "version": "2.8.0"
+    },
+    {
+      "name": "wandb",
+      "version": "0.28.1"
+    },
+    {
+      "name": "wheel",
+      "version": "0.48.0"
+    },
+    {
+      "name": "xformers",
+      "version": "0.0.35"
+    },
+    {
+      "name": "xxhash",
+      "version": "4.0.1"
+    },
+    {
+      "name": "yarl",
+      "version": "1.25.1"
+    },
+    {
+      "name": "zipp",
+      "version": "4.1.0"
+    }
+  ],
+  "python": "3.12.3",
+  "cuda": "12.8",
+  "gpu": "NVIDIA H100 80GB HBM3",
+  "activation_checkpointing": "offload",
+  "run_id": "compassion-seed2-20261001",
+  "timing_test": false,
+  "collection_slug": "",
+  "local_only": false,
+  "push_to_hub": true,
+  "merged_namespace": "BrandonHowe",
+  "training": {
+    "learning_rate": 5e-05,
+    "embedding_learning_rate": 5e-06,
+    "num_train_epochs": 5,
+    "warmup_ratio": 0.05,
+    "lr_scheduler_type": "cosine",
+    "weight_decay": 0.01,
+    "per_device_train_batch_size": 4,
+    "gradient_accumulation_steps": 8,
+    "per_device_eval_batch_size": 4,
+    "seed": 2,
+    "max_length": 8192
+  },
+  "early_stopping": {
+    "patience": 2,
+    "threshold": 0.0005,
+    "eval_steps": 125
+  },
+  "adapter": {
+    "rank": 128,
+    "alpha": 64,
+    "dropout": 0.05,
+    "rslora": true,
+    "random_state": 2
+  },
+  "execution": {
+    "mode": "full",
+    "max_steps": -1
+  },
+  "completed_epoch": 2.0,
+  "global_step": 750,
+  "merged_export": {
+    "weight_shards": 8,
+    "weight_tensors": 355,
+    "weight_bytes": 14596022272,
+    "tensor_dtypes": [
+      "BF16"
+    ],
+    "finite_weights": true,
+    "packaging_changes_tensor_values": false,
+    "serialization_method": "huggingface_hub.save_torch_state_dict",
+    "max_shard_size": 2000000000,
+    "base_model": "allenai/Olmo-3-1025-7B",
+    "base_revision": "a81bae42db3975be1671e27b9c9a56da1a9f980f",
+    "merge_method": "Unsloth save_pretrained_merged(save_method=\"merged_16bit\")"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,190 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|extra_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|extra_id_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|extra_id_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<|extra_id_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "<|extra_id_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<|extra_id_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "<|extra_id_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<|extra_id_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "<|extra_id_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<|extra_id_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "<|extra_id_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 65536,
+  "pad_token": "<|pad|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}