Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "checkpoints/rft-dedup-llama2-7b-gsm8k-20230830-195810/checkpoint_7810",
+  "_name_or_path": "/admin/home-reciprocate/gsm8k-rm/reciprocate_llama2-7b-gsm8k_a99b9c5a_reciprocate_gsm8k_pairwise_larger_2e-06",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -7,19 +7,27 @@
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 11008,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
+  "pad_token_id": 32001,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.32.0",
+  "transformers_version": "4.33.1",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 32002
 }

generation_config.json

@@ -1,10 +1,7 @@
 {
+  "_from_model_config": true,
   "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": "4.32.0"
+  "pad_token_id": 32001,
+  "transformers_version": "4.33.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b28fa0b0ab2f2116099896daef5b9fbf5f9f9215a00eb41ac635e59092b473
-size 13476927589
+oid sha256:6f668e0332fa048c5d545c2c8f335499006f4d563ffaecc4b88560c7fd7488fd
+size 13476960357