Upload folder using huggingface_hub (#1)

- 388e364c095ec7f44483358505abdebfef04e6d1ffc293dc854aace92cc2e880 (28f0e24e3547c48814606d62221c301d358b5883)
- 3b46752d769c86808208bd7079a8c00f90a47341f1298686c9c310d99ecac471 (451d153c77906c4b023dcbfefb0d0fff99f341c3)
- 17e9449facd6c804cb848952d35b20e065deffc0fd134493542a1c1f78a1a1e5 (e96f3bc3de8ac08fd71925a6410a5085f34c1ac8)

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "/work/desa_data/meta_llama1/huggingface_65B/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 64,
+  "pretraining_tp": 1,
+  "quip_params": {
+    "codebook": "E8P12",
+    "codesz": 8,
+    "idx_dtype": "torch.int16",
+    "lora_rank": 0,
+    "outlier_channel_split": false,
+    "rescale_WH": false
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "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": "4.34.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db8853ccde71bee061b39de760b774fddbfd13bbd594f01c6d5c4044654cc7f1
+size 9914510142

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52004edfcc80d3331eacbd9ffa2dfb5b31dd44a47fb578d59cde1b4977898389
+size 7348018442