Upload LlamaForCausalLM

config.json

@@ -1,17 +1,21 @@
 {
-  "_name_or_path": "mattshumer/Reflection-Llama-3.1-70B",
+  "_name_or_path": "mattshumer/ref_70_e3",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128009,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "hidden_act": "silu",
   "hidden_size": 8192,
   "initializer_range": 0.02,
   "intermediate_size": 28672,
-  "max_position_embeddings": 8192,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 64,
@@ -34,7 +38,13 @@
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",

generation_config.json

@@ -3,9 +3,9 @@
   "do_sample": true,
   "eos_token_id": [
     128001,
+    128008,
     128009
   ],
-  "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
   "transformers_version": "4.44.2"

model-00001-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f25b44e5e89a38d84a1df21a4cc48250c405b1bb06ca263914f03d5d12d718c
-size 4949180592
+oid sha256:9306fc59ddfd0906cc4a554a6f87dd61252f88839e592e3e2db403feec1876a2
+size 4949180596

model-00002-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38ee9630f9113b81603505a416b3bde0cb0faa45f0271a17135c75a8c11d24cd
-size 4977054937
+oid sha256:891abb23a0059c9f13becd5037ae96a9e25d895a8b2d425553320f474378e8ab
+size 4977054932

model-00003-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f201406c98cb5ddb6556c7590972a2eafa1dd0a5a9b12388f2415aa83316ec
-size 4977088089
+oid sha256:0f7e9969ead51d756d3e9bcddf36aa96b21307ed104ad38be9de32467f7d3c43
+size 4977088085

model-00004-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:571409702b8e5805a3e29eba02a81e6c48c927a5661d280574f9a8b23a3e5e60
-size 4933786851
+oid sha256:6b5f8bd882253c2add028f060f4ad80a1ce5fd4c5488b76da92b73946d0aef84
+size 4933786843

model-00005-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e24219198f4136b092ed88f637f91c5777ece2a488833bb9cf3727b494e016a4
-size 4977055135
+oid sha256:f52398ba994433fe561a2801d1867223758b38d04a4209e65c86a015ff1a39ab
+size 4977055140

model-00006-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecaa5c823f92772e338093a6fc8356a3ee7c05d3fcfe5770d6b01879ad4d7a23
-size 4977055104
+oid sha256:1b4eaae7f54f4f3b9223cd73d08d89875575651ce099b8d539021a3e897073d3
+size 4977055097

model-00007-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeaabf66442e56253508eefce1a29eaee70cee84fb67616a3ac8dc78b6163da0
-size 4977088092
+oid sha256:92340d511e752837b70b3839d1389896dee68f5772d8fa459698987c90c130d8
+size 4977088087

model-00008-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a19adb72fba3822d66ac50c358914299fc86ca07cd9e9c983f87e3216df84e
-size 4750125895
+oid sha256:3dca28e2728bfaf1c224bfbe5664bbce1c03fb9a4b3c939e4012d7011ae23909
+size 4750125896

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 39518012903
+    "total_size": 39518012884
   },
   "weight_map": {
     "lm_head.weight": "model-00008-of-00008.safetensors",