0dd9a9dba1f303a4b415efc6fdf1c681df961a481e43772da0d83fbb80e4e498

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "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"
+}