Upload folder using huggingface_hub

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-70b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quip_params": {
+    "K": 2,
+    "L": 16,
+    "V": 2,
+    "codebook": "bitshift",
+    "codebook_version": 0,
+    "decode_mode": "quantlut_sym",
+    "td_x": 16,
+    "td_y": 16,
+    "tlut_bits": 9
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "attn_implementation": "sdpa",
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be6a597fc27c39c0ad0914548e723d35d4e9a9967c9e8e4a94a78ba84ea70663
+size 4965486872

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c11b588847c17fa649c8b30bfa373cd9162de8b68dd8b4c914f716d8eee2f0f
+size 4987305552

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3916df43968217f253d128229376351efb1aca8ed179991870038b24703f8266
+size 4966419048

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0192a8e213807cc04db544da4f8d87c82c83ad137b75aa1fd17fcd1e756a40c7
+size 3272052240