commit files to HF hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,29 @@
----
-license: mit
----
+
+
+---
+language: en
+tags:
+- hummingbird
+- causal-lm
+license: mit
+---
+
+# Hummingbird 0.0 Release
+
+This is Hummingbird 0.0, a 1B proof-of-concept causal language model based on **Efficient Attention**, which reduces the number of parameters in the attention layer by 50% compared to standard Multi-Head Attention.
+
+This version of Hummingbird is only meant to demonstrate Efficient Attention for use in causal language modelling. It has been trained on only 15 Billion tokens and is not safeguarded. Therefore, we do not recommend using it as a chatbot.
+
+## Model Details
+
+The models consists of 1.1 Billion parameters with the following specifications:
+
+| Parameter            | size |
+| -------------------- | ---- |
+| # Transformer Blocks | 10   |
+| Model Dimension      | 3072 |
+| # Heads              | 1    |
+
+
+The Attention Mechanism used is based on our newly proposed Efficient Attention from our paper, *You Need to Pay Better Attention: Rethinking the Mathematics of Attention Mechanism* ([arXiv:2403.01643](https://arxiv.org/abs/2403.01643)). We have chosen the number of heeads to be 1 as an interesting case study, since all current LMs use multiple heads.
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "weights/hummingbird/hummingbird_4th_epoch_full/hummingbird",
+  "architectures": [
+    "HummingbirdForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "hummingbird",
+  "num_attention_heads": 1,
+  "num_hidden_layers": 10,
+  "num_key_value_heads": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 3072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d9be6dcb51e509b4da01f627d7aecf8225fff016755c1c8fa1a1b064a5a54f6
+size 2280790152

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a769620450e3eb2f535cd5d3e6d354cfc04efbbc5760708aa738cd8fb97e30
+size 1795455

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}