Upload LlamaForCausalLM

config.json

@@ -6,7 +6,20 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "compression_config": {
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "quantization_config": {
     "config_groups": {
       "group_0": {
         "input_activations": {
@@ -47,21 +60,8 @@
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed",
-    "version": "0.6.0.20240927"
+    "version": "0.6.0.20240928"
   },
-  "eos_token_id": 2,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 2048,
-  "initializer_range": 0.02,
-  "intermediate_size": 5632,
-  "max_position_embeddings": 2048,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 22,
-  "num_key_value_heads": 4,
-  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,