Upload folder using huggingface_hub

README.md

@@ -0,0 +1,25 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- mlx
+datasets:
+- allenai/dolma
+---
+
+# mlx-community/OLMo-7B-hf-4bit-mlx
+This model was converted to MLX format from [`allenai/OLMo-7B`]().
+Refer to the [original model card](https://huggingface.co/allenai/OLMo-7B) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/OLMo-7B-hf-4bit-mlx")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,112 @@
+{
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": null,
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": true,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "OlmoModelForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": null,
+    "pad_token_id": 1,
+    "eos_token_id": 50279,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "OLMo-7B",
+    "transformers_version": "4.37.2",
+    "d_model": 4096,
+    "n_heads": 32,
+    "n_layers": 32,
+    "mlp_ratio": 4,
+    "mlp_hidden_size": 22016,
+    "activation_type": "swiglu",
+    "block_type": "sequential",
+    "block_group_size": 1,
+    "alibi": false,
+    "alibi_bias_max": 8.0,
+    "rope": true,
+    "rope_full_precision": true,
+    "flash_attention": true,
+    "attention_dropout": 0.0,
+    "multi_query_attention": false,
+    "attention_layer_norm": false,
+    "residual_dropout": 0.0,
+    "embedding_dropout": 0.0,
+    "layer_norm_type": "default",
+    "layer_norm_with_affine": false,
+    "attention_layer_norm_with_affine": false,
+    "max_sequence_length": 2048,
+    "include_bias": false,
+    "bias_for_layer_norm": false,
+    "scale_logits": false,
+    "vocab_size": 50280,
+    "embedding_size": 50304,
+    "weight_tying": false,
+    "init_device": "meta",
+    "init_fn": "mitchell",
+    "init_std": 0.02,
+    "init_cutoff_factor": null,
+    "precision": "amp_bf16",
+    "model_type": "olmo",
+    "auto_map": {
+        "AutoConfig": "configuration_olmo.OLMoConfig",
+        "AutoModelForCausalLM": "modeling_olmo.OLMoForCausalLM",
+        "AutoTokenizer": [
+            "tokenization_olmo_fast.OLMoTokenizerFast",
+            "tokenization_olmo_fast.OLMoTokenizerFast"
+        ]
+    },
+    "use_cache": true,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    }
+}

configuration_olmo.py

@@ -0,0 +1 @@
+from hf_olmo import OLMoConfig

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f89eaa8dfefebce6fa0b42a98cde511f8c5cddadc4fc0ae21b327e103137d93c
+size 4170789690

model.safetensors.index.json

@@ -0,0 +1,395 @@
+{
+    "metadata": {
+        "total_size": 4170743808
+    },
+    "weight_map": {
+        "model.transformer.blocks.0.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.0.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.0.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.0.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.0.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.0.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.0.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.0.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.0.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.0.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.0.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.0.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.1.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.1.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.1.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.1.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.1.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.1.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.1.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.1.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.1.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.1.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.1.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.1.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.10.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.10.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.10.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.10.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.10.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.10.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.10.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.10.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.10.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.10.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.10.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.10.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.11.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.11.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.11.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.11.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.11.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.11.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.11.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.11.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.11.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.11.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.11.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.11.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.12.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.12.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.12.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.12.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.12.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.12.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.12.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.12.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.12.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.12.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.12.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.12.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.13.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.13.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.13.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.13.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.13.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.13.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.13.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.13.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.13.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.13.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.13.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.13.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.14.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.14.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.14.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.14.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.14.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.14.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.14.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.14.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.14.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.14.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.14.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.14.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.15.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.15.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.15.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.15.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.15.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.15.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.15.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.15.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.15.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.15.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.15.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.15.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.16.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.16.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.16.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.16.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.16.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.16.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.16.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.16.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.16.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.16.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.16.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.16.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.17.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.17.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.17.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.17.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.17.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.17.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.17.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.17.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.17.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.17.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.17.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.17.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.18.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.18.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.18.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.18.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.18.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.18.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.18.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.18.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.18.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.18.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.18.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.18.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.19.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.19.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.19.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.19.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.19.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.19.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.19.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.19.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.19.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.19.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.19.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.19.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.2.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.2.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.2.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.2.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.2.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.2.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.2.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.2.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.2.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.2.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.2.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.2.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.20.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.20.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.20.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.20.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.20.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.20.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.20.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.20.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.20.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.20.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.20.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.20.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.21.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.21.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.21.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.21.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.21.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.21.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.21.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.21.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.21.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.21.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.21.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.21.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.22.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.22.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.22.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.22.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.22.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.22.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.22.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.22.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.22.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.22.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.22.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.22.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.23.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.23.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.23.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.23.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.23.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.23.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.23.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.23.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.23.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.23.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.23.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.23.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.24.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.24.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.24.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.24.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.24.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.24.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.24.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.24.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.24.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.24.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.24.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.24.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.25.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.25.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.25.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.25.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.25.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.25.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.25.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.25.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.25.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.25.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.25.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.25.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.26.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.26.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.26.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.26.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.26.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.26.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.26.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.26.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.26.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.26.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.26.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.26.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.27.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.27.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.27.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.27.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.27.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.27.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.27.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.27.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.27.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.27.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.27.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.27.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.28.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.28.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.28.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.28.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.28.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.28.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.28.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.28.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.28.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.28.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.28.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.28.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.29.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.29.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.29.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.29.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.29.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.29.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.29.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.29.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.29.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.29.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.29.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.29.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.3.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.3.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.3.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.3.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.3.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.3.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.3.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.3.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.3.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.3.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.3.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.3.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.30.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.30.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.30.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.30.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.30.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.30.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.30.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.30.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.30.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.30.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.30.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.30.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.31.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.31.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.31.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.31.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.31.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.31.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.31.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.31.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.31.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.31.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.31.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.31.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.4.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.4.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.4.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.4.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.4.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.4.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.4.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.4.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.4.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.4.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.4.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.4.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.5.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.5.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.5.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.5.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.5.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.5.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.5.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.5.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.5.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.5.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.5.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.5.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.6.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.6.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.6.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.6.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.6.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.6.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.6.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.6.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.6.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.6.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.6.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.6.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.7.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.7.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.7.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.7.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.7.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.7.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.7.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.7.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.7.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.7.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.7.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.7.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.8.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.8.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.8.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.8.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.8.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.8.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.8.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.8.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.8.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.8.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.8.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.8.ff_proj.weight": "model.safetensors",
+        "model.transformer.blocks.9.att_proj.biases": "model.safetensors",
+        "model.transformer.blocks.9.att_proj.scales": "model.safetensors",
+        "model.transformer.blocks.9.att_proj.weight": "model.safetensors",
+        "model.transformer.blocks.9.attn_out.biases": "model.safetensors",
+        "model.transformer.blocks.9.attn_out.scales": "model.safetensors",
+        "model.transformer.blocks.9.attn_out.weight": "model.safetensors",
+        "model.transformer.blocks.9.ff_out.biases": "model.safetensors",
+        "model.transformer.blocks.9.ff_out.scales": "model.safetensors",
+        "model.transformer.blocks.9.ff_out.weight": "model.safetensors",
+        "model.transformer.blocks.9.ff_proj.biases": "model.safetensors",
+        "model.transformer.blocks.9.ff_proj.scales": "model.safetensors",
+        "model.transformer.blocks.9.ff_proj.weight": "model.safetensors",
+        "model.transformer.ff_out.biases": "model.safetensors",
+        "model.transformer.ff_out.scales": "model.safetensors",
+        "model.transformer.ff_out.weight": "model.safetensors",
+        "model.transformer.wte.weight": "model.safetensors"
+    }
+}

modeling_olmo.py

@@ -0,0 +1 @@
+from hf_olmo import OLMoForCausalLM

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenization_olmo_fast.py

@@ -0,0 +1 @@
+from hf_olmo.tokenization_olmo_fast import OLMoTokenizerFast

tokenizer_config.json

@@ -0,0 +1,242 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoConfig": "configuration_olmo.OLMoConfig",
+    "AutoTokenizer": [
+      "tokenization_olmo_fast.OLMoTokenizerFast",
+      "tokenization_olmo_fast.OLMoTokenizerFast"
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "OLMoTokenizer",
+  "truncation": "right"
+}