first commit

config.json

@@ -1,22 +1,24 @@
 {
-  "_name_or_path": "decapoda-research/llama-13b-hf",
+  "_name_or_path": "huggyllama/llama-13b",
   "architectures": [
-    "LLaMAForCausalLM"
+    "LlamaForCausalLM"
   ],
-  "bos_token_id": 0,
-  "eos_token_id": 1,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 5120,
   "initializer_range": 0.02,
   "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
   "model_type": "llama",
   "num_attention_heads": 40,
   "num_hidden_layers": 40,
-  "pad_token_id": -1,
+  "pad_token_id": 0,
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.28.0",
   "use_cache": true,
   "vocab_size": 32000
-}
+}

quant_config.json

@@ -8,4 +8,4 @@
   "seed": 0,
   "nearest": false,
   "save": "./llama-13b-3bit"
-}
+}

quantized_weights.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f18c3eace4426c0b2c1fce4b21b97e29334fd826c9247200d20541ec320cdf
-size 5892526893
+oid sha256:9fefc19fd9ce45c5b779c30c43ec9c0a8e03c35ec315d467ffc5d87d62f2ae19
+size 5892515588