Duplicate from harindhar10/olmo_chem_lora_cpt_LoRA_500k

Co-authored-by: Harindhar <harindhar10@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 +1,81 @@
+---
+base_model: Codemaster67/Olmo-7b-spe
+datasets:
+- Codemaster67/Causal_lm_chemistry_1M_rows
+language: en
+library_name: transformers
+license: apache-2.0
+tags:
+- chemistry
+- smiles
+- olmo
+- causal-lm
+- full-finetune
+- fsdp
+---
+
+# OLMo-7B Full Fine-Tune — Chemistry SMILES CPT
+
+## Model Description
+
+This model is a **full-parameter fine-tuned** version of
+[Codemaster67/Olmo-7b-spe](https://huggingface.co/Codemaster67/Olmo-7b-spe) trained on chemistry
+SMILES strings from the
+[Codemaster67/Causal_lm_chemistry_1M_rows](https://huggingface.co/datasets/Codemaster67/Causal_lm_chemistry_1M_rows) dataset.
+
+The base model's tokenizer was pre-extended with ~300 SPE (SMILES Pair
+Encoding) chemistry tokens plus `<|start_of_smiles|>` / `<|end_of_smiles|>`
+special tokens, and its embedding & LM-head layers were resized with
+mean-initialised vectors for the new tokens.
+
+## Training Details
+
+| Parameter | Value |
+|---|---|
+| **Method** | Full Fine-Tune (all weights updated) |
+| **Parallelism** | FSDP (Fully Sharded Data Parallel) |
+| **Epochs** | 1 |
+| **Learning Rate** | 5e-06 |
+| **Batch Size (per device)** | 16 |
+| **Gradient Accumulation** | 1 |
+| **Max Sequence Length** | 512 |
+| **Warmup Ratio** | 0.1 |
+| **Weight Decay** | 0.01 |
+| **Scheduler** | Cosine |
+| **Precision** | bf16 |
+| **Augmentation** | OFF |
+| **Training Samples** | 250000 |
+| **Eval Samples** | 25000 |
+
+## Evaluation Results
+
+| Metric | Value |
+|---|---|
+| **Final Eval Loss** | 0.9727568626403809 |
+| **Final Eval Perplexity** | 2.645226943673604 |
+| **Training Loss** | 1.1177 |
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("harindhar10/olmo_chem_lora_cpt_LoRA_500k", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("harindhar10/olmo_chem_lora_cpt_LoRA_500k", trust_remote_code=True)
+
+smiles_input = "<|start_of_smiles|>CC(=O)Oc1ccccc1C(=O)O<|end_of_smiles|>"
+inputs = tokenizer(smiles_input, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=128)
+print(tokenizer.decode(outputs[0], skip_special_tokens=False))
+```
+
+## Intended Use
+
+Chemistry-domain language modelling, SMILES generation and completion,
+and downstream molecular property prediction via fine-tuning.
+
+## Limitations
+
+- Trained primarily on SMILES strings; natural-language instruction-following
+  ability may degrade compared to the base OLMo checkpoint.
+- Augmentation was disabled for this run.

adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Codemaster67/Olmo-7b-spe",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306c8f703dd6c1f4f90cbd62be92a57e2c679a996cec569a315a9b0ea2d58732
+size 1470623048

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "OlmoForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "clip_qkv": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 50279,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "olmo",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "vocab_size": 50716
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    50279,
+    0
+  ],
+  "pad_token_id": 1,
+  "transformers_version": "5.14.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fad1046895b9185884d99c66902998def45a187c3cc194f81460201e184c238
+size 13782968168

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|start_of_smiles|>",
+    "<|end_of_smiles|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trim_offsets": true,
+  "unk_token": null
+}