Duplicate from ganscs/Olmo7b-olmo-a100-new-20260908-CPT-merged-step-750

Co-authored-by: Ganesh Talluri <ganscs@users.noreply.huggingface.co>

.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 +1,53 @@
+---
+language: en
+library_name: transformers
+pipeline_tag: text-generation
+base_model: allenai/Olmo-3-1025-7B
+license: apache-2.0
+tags:
+- merged
+- continued-pretraining
+- bfloat16
+---
+
+# Olmo7b-olmo-a100-new-20260908-CPT-merged-step-750
+
+Standalone BF16 model combining `allenai/Olmo-3-1025-7B` with the trained
+LoRA adapter and full embedding/output weights from [checkpoint 750](https://huggingface.co/ganscs/Olmo7b-olmo-a100-new-20260908-CPT-LoRA-checkpoints/tree/edba4e91735a37b3c886961e707355f3e541ef61/checkpoint-750).
+Load this repository directly with Transformers; a separate PEFT adapter is not required.
+
+## Provenance
+
+- Base revision: `a81bae42db3975be1671e27b9c9a56da1a9f980f`.
+- Adapter repository revision: `edba4e91735a37b3c886961e707355f3e541ef61`.
+- Selected step: 750, the best validation checkpoint in this training run.
+- Source checkpoint training-time validation loss: 1.3001196.
+- rsLoRA rank 128, alpha 64.
+- The fully trained `embed_tokens` and `lm_head` weights replace the original endpoints.
+- The output uses the checkpoint tokenizer and the original base architecture/configuration.
+
+Adapters were trained with a 4-bit base. This export merges them into the original
+BF16 base revision using PEFT's safe merge operation. The training-time validation
+score above is not a new evaluation of this BF16 export.
+
+## Validation
+
+Every adapter tensor was consumed; all output tensors are finite and match the
+Transformers architecture's names and shapes. The model loaded locally without
+PEFT adapters and produced finite logits and a short greedy generation.
+`merge_manifest.json` records source hashes, merge details and output checksums;
+`validation.json` records the smoke test. `training_manifest.json` preserves
+the source experiment settings. This is a weights-only export, without optimizer state.
+
+## Load
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "ganscs/Olmo7b-olmo-a100-new-20260908-CPT-merged-step-750"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id, dtype=torch.bfloat16, device_map="auto"
+)
+```

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Olmo3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "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,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "vocab_size": 100278
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.57.0"
+}

merge_manifest.json

@@ -0,0 +1,39 @@
+{
+  "model": "olmo",
+  "base_model": "allenai/Olmo-3-1025-7B",
+  "base_revision": "a81bae42db3975be1671e27b9c9a56da1a9f980f",
+  "adapter_repo": "ganscs/Olmo7b-olmo-a100-new-20260908-CPT-LoRA-checkpoints",
+  "adapter_revision": "edba4e91735a37b3c886961e707355f3e541ef61",
+  "checkpoint_step": 750,
+  "adapter_sha256": "c1486c306d6a1a9b5a77d6abd8151f0a4f0f4a4051397181db754dda4700f04d",
+  "merged_lora_layers": 224,
+  "trained_endpoint_replacements": 2,
+  "weight_tensors": 355,
+  "weight_bytes": 14596022272,
+  "dtype": "bfloat16",
+  "method": "PEFT 0.20.0 Linear.merge(safe_merge=True), one tensor at a time",
+  "validation": {
+    "finite_weights": true,
+    "all_adapter_tensors_consumed": true,
+    "full_transformers_schema_matches": true,
+    "adapter_sha256_verified": true
+  },
+  "merge_seconds": 40.83,
+  "weight_sha256": {
+    "model-00001-of-00015.safetensors": "8376bb4c24049cd810dc20d18193d739c0baf63dd07055e0b96b21d95de59496",
+    "model-00002-of-00015.safetensors": "1d5215ba43fd79c856a79ce66e85f90acbfeab010923326ab003214747b7063c",
+    "model-00003-of-00015.safetensors": "281b3cdc5fc3f57760ca8a7debb31893fd2fe813a78933900df95ec44e160071",
+    "model-00004-of-00015.safetensors": "28cac4549f3626d9ab3f5f8610bd5e83b4d2c19ddb61942276dc6925c1425744",
+    "model-00005-of-00015.safetensors": "d61925d751db573bba307fd5c399dd1d102bbe70a06345836539969d589c8d60",
+    "model-00006-of-00015.safetensors": "f7034e3ccab4f92e5efc7b0f01828ab2c840885c4f326a35466a5f734646111d",
+    "model-00007-of-00015.safetensors": "52406e348170ced6d745977842bf3cde8f0898614ff1f940ddb286b9cb358f1a",
+    "model-00008-of-00015.safetensors": "54600bad604f5b4ff51c9c18a173911f3b8e6626fece6971612a29d0519857c8",
+    "model-00009-of-00015.safetensors": "56fcc5845ebc00bc2fadfcf79723a6585a74c763e7c3d02f0de3c95b83eabe3e",
+    "model-00010-of-00015.safetensors": "1f6f1790bc19f2b8d6f109ec68fc2389bc8fd7ea2d5708e6dcfe8605a846fa04",
+    "model-00011-of-00015.safetensors": "60e43893a87511ca32ed5ae404bbb1c889d605e49cf8a221838c846bc3d79699",
+    "model-00012-of-00015.safetensors": "c54fe2f961053ad131d060f0c791d1f6e7b0b36bb4be320e853dd76bbf54673f",
+    "model-00013-of-00015.safetensors": "838f67fe52c84dc60320a54bcb90bc0172a9e5db9dc3996116d91c7664f9b83e",
+    "model-00014-of-00015.safetensors": "050100b26fd0c53adaf85519f1601bcc6edc953e66658a86765780fdfd2a36fd",
+    "model-00015-of-00015.safetensors": "a2632cb85869b880f19c14840d072c17c1e2a7977bd6af9ea857d079462cfa9d"
+  }
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8376bb4c24049cd810dc20d18193d739c0baf63dd07055e0b96b21d95de59496
+size 1001832816

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5215ba43fd79c856a79ce66e85f90acbfeab010923326ab003214747b7063c
+size 1067552368

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281b3cdc5fc3f57760ca8a7debb31893fd2fe813a78933900df95ec44e160071
+size 1057033144

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28cac4549f3626d9ab3f5f8610bd5e83b4d2c19ddb61942276dc6925c1425744
+size 1033997808

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61925d751db573bba307fd5c399dd1d102bbe70a06345836539969d589c8d60
+size 989924048

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7034e3ccab4f92e5efc7b0f01828ab2c840885c4f326a35466a5f734646111d
+size 1023511848

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52406e348170ced6d745977842bf3cde8f0898614ff1f940ddb286b9cb358f1a
+size 1057066400

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54600bad604f5b4ff51c9c18a173911f3b8e6626fece6971612a29d0519857c8
+size 1057033168

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56fcc5845ebc00bc2fadfcf79723a6585a74c763e7c3d02f0de3c95b83eabe3e
+size 1033997840

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6f1790bc19f2b8d6f109ec68fc2389bc8fd7ea2d5708e6dcfe8605a846fa04
+size 629196848

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60e43893a87511ca32ed5ae404bbb1c889d605e49cf8a221838c846bc3d79699
+size 1001849432

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54fe2f961053ad131d060f0c791d1f6e7b0b36bb4be320e853dd76bbf54673f
+size 989924072

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838f67fe52c84dc60320a54bcb90bc0172a9e5db9dc3996116d91c7664f9b83e
+size 1033997840

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050100b26fd0c53adaf85519f1601bcc6edc953e66658a86765780fdfd2a36fd
+size 989924072

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2632cb85869b880f19c14840d072c17c1e2a7977bd6af9ea857d079462cfa9d
+size 629221752

model.safetensors.index.json

@@ -0,0 +1,362 @@
+{
+  "metadata": {
+    "total_size": 14596022272
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "lm_head.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors"
+  }
+}

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|>"
+}

training_manifest.json

@@ -0,0 +1,613 @@
+{
+  "model": "allenai/Olmo-3-1025-7B",
+  "model_revision": "a81bae42db3975be1671e27b9c9a56da1a9f980f",
+  "dataset_revision": "06248aa4c3fd26b22fdedded4dc172d00dd2e5cd",
+  "selection_hashes": {
+    "train": "3204b143004cce956c5f7f412d3d82aececfb99a9db0c27213ba92e44ff3c45b",
+    "validation": "495bc23def6c2a73277187a07a32f9e8191a2dba55de41bfeb83fa7e416c7e8a"
+  },
+  "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": "abnf",
+      "version": "2.2.0"
+    },
+    {
+      "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": "backoff",
+      "version": "2.2.1"
+    },
+    {
+      "name": "bitsandbytes",
+      "version": "0.50.2"
+    },
+    {
+      "name": "cachetools",
+      "version": "7.1.8"
+    },
+    {
+      "name": "certifi",
+      "version": "2026.7.22"
+    },
+    {
+      "name": "cffi",
+      "version": "2.1.1"
+    },
+    {
+      "name": "chardet",
+      "version": "7.6.0"
+    },
+    {
+      "name": "charset-normalizer",
+      "version": "3.5.1"
+    },
+    {
+      "name": "cint",
+      "version": "1.0.0"
+    },
+    {
+      "name": "click",
+      "version": "8.5.0"
+    },
+    {
+      "name": "cryptography",
+      "version": "50.0.1"
+    },
+    {
+      "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": "diskcache-weave",
+      "version": "5.6.3.post1"
+    },
+    {
+      "name": "distro",
+      "version": "1.9.0"
+    },
+    {
+      "name": "docstring_parser",
+      "version": "0.18.0"
+    },
+    {
+      "name": "fickling",
+      "version": "0.1.12"
+    },
+    {
+      "name": "filelock",
+      "version": "3.32.3"
+    },
+    {
+      "name": "frozenlist",
+      "version": "1.8.0"
+    },
+    {
+      "name": "fsspec",
+      "version": "2025.9.0"
+    },
+    {
+      "name": "googleapis-common-protos",
+      "version": "1.75.3"
+    },
+    {
+      "name": "gql",
+      "version": "4.0.0"
+    },
+    {
+      "name": "graphql-core",
+      "version": "3.2.12"
+    },
+    {
+      "name": "graphviz",
+      "version": "0.21"
+    },
+    {
+      "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": "3.19"
+    },
+    {
+      "name": "importlib_metadata",
+      "version": "9.0.1"
+    },
+    {
+      "name": "intervaltree",
+      "version": "3.2.1"
+    },
+    {
+      "name": "Jinja2",
+      "version": "3.1.6"
+    },
+    {
+      "name": "jsonschema",
+      "version": "4.26.0"
+    },
+    {
+      "name": "jsonschema-specifications",
+      "version": "2025.9.1"
+    },
+    {
+      "name": "kaitaistruct",
+      "version": "0.11"
+    },
+    {
+      "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": "0.21.1"
+    },
+    {
+      "name": "multidict",
+      "version": "6.7.1"
+    },
+    {
+      "name": "multiprocess",
+      "version": "0.70.16"
+    },
+    {
+      "name": "nest-asyncio",
+      "version": "1.6.0"
+    },
+    {
+      "name": "networkx",
+      "version": "3.6.1"
+    },
+    {
+      "name": "numpy",
+      "version": "2.4.6"
+    },
+    {
+      "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": "opentelemetry-api",
+      "version": "1.44.0"
+    },
+    {
+      "name": "opentelemetry-exporter-otlp-proto-common",
+      "version": "1.44.0"
+    },
+    {
+      "name": "opentelemetry-exporter-otlp-proto-http",
+      "version": "1.44.0"
+    },
+    {
+      "name": "opentelemetry-proto",
+      "version": "1.44.0"
+    },
+    {
+      "name": "opentelemetry-sdk",
+      "version": "1.44.0"
+    },
+    {
+      "name": "opentelemetry-semantic-conventions",
+      "version": "0.65b0"
+    },
+    {
+      "name": "packaging",
+      "version": "26.3"
+    },
+    {
+      "name": "pandas",
+      "version": "3.0.5"
+    },
+    {
+      "name": "pdfminer.six",
+      "version": "20260107"
+    },
+    {
+      "name": "peft",
+      "version": "0.20.0"
+    },
+    {
+      "name": "pillow",
+      "version": "12.3.0"
+    },
+    {
+      "name": "pip",
+      "version": "26.2.1"
+    },
+    {
+      "name": "platformdirs",
+      "version": "4.11.7"
+    },
+    {
+      "name": "polyfile-weave",
+      "version": "0.5.9"
+    },
+    {
+      "name": "propcache",
+      "version": "0.5.2"
+    },
+    {
+      "name": "protobuf",
+      "version": "7.36.1"
+    },
+    {
+      "name": "psutil",
+      "version": "7.2.2"
+    },
+    {
+      "name": "pyarrow",
+      "version": "25.0.1"
+    },
+    {
+      "name": "pycparser",
+      "version": "3.0"
+    },
+    {
+      "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": "referencing",
+      "version": "0.37.0"
+    },
+    {
+      "name": "regex",
+      "version": "2026.9.3"
+    },
+    {
+      "name": "requests",
+      "version": "2.34.2"
+    },
+    {
+      "name": "rich",
+      "version": "15.0.0"
+    },
+    {
+      "name": "rpds-py",
+      "version": "2026.6.3"
+    },
+    {
+      "name": "safetensors",
+      "version": "0.8.0"
+    },
+    {
+      "name": "sentencepiece",
+      "version": "0.2.2"
+    },
+    {
+      "name": "sentry-sdk",
+      "version": "2.69.1"
+    },
+    {
+      "name": "setuptools",
+      "version": "78.1.0"
+    },
+    {
+      "name": "shellingham",
+      "version": "1.5.4"
+    },
+    {
+      "name": "six",
+      "version": "1.17.0"
+    },
+    {
+      "name": "sniffio",
+      "version": "1.3.1"
+    },
+    {
+      "name": "sortedcontainers",
+      "version": "2.4.0"
+    },
+    {
+      "name": "structlog",
+      "version": "26.1.0"
+    },
+    {
+      "name": "sympy",
+      "version": "1.14.0"
+    },
+    {
+      "name": "tenacity",
+      "version": "9.1.4"
+    },
+    {
+      "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": "4.70.0"
+    },
+    {
+      "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": "2.7.0"
+    },
+    {
+      "name": "wandb",
+      "version": "0.28.1"
+    },
+    {
+      "name": "weave",
+      "version": "0.53.8"
+    },
+    {
+      "name": "wheel",
+      "version": "0.48.0"
+    },
+    {
+      "name": "xformers",
+      "version": "0.0.35"
+    },
+    {
+      "name": "xxhash",
+      "version": "4.0.1"
+    },
+    {
+      "name": "yarl",
+      "version": "1.24.5"
+    },
+    {
+      "name": "zipp",
+      "version": "4.1.0"
+    }
+  ],
+  "python": "3.11.10",
+  "cuda": "12.8",
+  "gpu": "NVIDIA H100 80GB HBM3",
+  "activation_checkpointing": "gpu",
+  "run_id": "olmo-a100-new-20260908",
+  "timing_test": false,
+  "collection_slug": "",
+  "local_only": false,
+  "push_to_hub": false,
+  "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": 3407,
+    "max_length": 8192
+  },
+  "adapter": {
+    "rank": 128,
+    "alpha": 64,
+    "dropout": 0.05,
+    "rslora": true
+  }
+}

validation.json

@@ -0,0 +1,7 @@
+{
+  "standalone_transformers_load": true,
+  "finite_logits": true,
+  "prompt": "Clinical research studies evaluate",
+  "generated_text": "Clinical research studies evaluate new treatments by comparing outcomes between a treatment",
+  "generated_tokens": 8
+}