Upload 9 files

allamo_config_ckpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d393985a0c30f0fa389c1107c166ec4f96c95631e6470c306b2e579b295064
+size 3504

allamo_model_ckpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596e0f419fba682a687323e4e37ab9d1dc809f2acd9de107505d127464c7a388
+size 4167086435

allamo_optimizer_ckpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7b363f05f33d700c9a1f69f7c8e8fe64b2c6f504908153c4187fc17652ffc5
+size 8334180469

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 31980
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5613ebc1a2a3938529d10d005fa5f7e2e02f7d513be6d16f30128a20274037f6
+size 4167035336

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "<pad>",
+    "[INST]",
+    "[/INST]",
+    "<<SYS>>",
+    "<</SYS>>"
+  ],
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}