update ckpt0815 with git lfs

config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "silu",
+  "architectures": [
+    "HawkForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 65535,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 65535,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "hawk",
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": 2688,
+  "n_layer": 20,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 64,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.0,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "tokenizer_class": "HawkTokenizer",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 65536
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b480a7b7ae3505e37d0c3da7c354bf856eef1e2edd4ea7b12b296b9184fcdcd
+size 982801364

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2722796dc07a0b78edca0daf34bef1a1d5e3f53c226b20295bbf91f0fd36ec77
+size 282171835

pytorch_model.bin.index.json

@@ -0,0 +1,171 @@
+{
+  "metadata": {
+    "total_size": 1264918528
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00002.bin",
+    "model.final_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.final_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.14.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.15.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.15.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.15.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.16.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.16.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.16.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.16.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.17.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.17.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.17.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.17.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.18.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.18.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.18.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.18.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.19.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.19.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.19.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.19.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.word_embeddings.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "HawkTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}