Upload LlamaForCausalLM

README.md

@@ -1,6 +1,6 @@
 ---
-license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
+license: llama3.1
 pipeline_tag: text-generation
 tags:
 - unsloth

config.json

@@ -1,21 +1,17 @@
 {
-  "_name_or_path": "mattshumer/Reflection-70B",
+  "_name_or_path": "mattshumer/Reflection-Llama-3.1-70B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
+  "eos_token_id": 128009,
   "hidden_act": "silu",
   "hidden_size": 8192,
   "initializer_range": 0.02,
   "intermediate_size": 28672,
-  "max_position_embeddings": 131072,
+  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 64,
@@ -38,17 +34,11 @@
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
+  "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 128262
 }

generation_config.json

@@ -3,10 +3,10 @@
   "do_sample": true,
   "eos_token_id": [
     128001,
-    128008,
     128009
   ],
-  "temperature": 0.7,
-  "top_p": 0.95,
+  "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 sha256:611cd9876bc7cb6d1c2540c19e0b24beeabd4fb1197128b9b748c54536cfa948
-size 4949082290
+oid sha256:5f25b44e5e89a38d84a1df21a4cc48250c405b1bb06ca263914f03d5d12d718c
+size 4949180592

model-00002-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3294eeef8b7d554affa793791a6ee7c38415d2b4af8a5daac3556735cd700c5
-size 4977054939
+oid sha256:38ee9630f9113b81603505a416b3bde0cb0faa45f0271a17135c75a8c11d24cd
+size 4977054937

model-00003-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccb6c4b58606e925ab8a37a728052f7ed4cb309dd22fccd868ec89b044786e91
-size 4977088096
+oid sha256:b1f201406c98cb5ddb6556c7590972a2eafa1dd0a5a9b12388f2415aa83316ec
+size 4977088089

model-00004-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b100d91e34ff274403042bd32ac1c283d5fdc9c8b39cde41c88d12f9bc9667
-size 4933786844
+oid sha256:571409702b8e5805a3e29eba02a81e6c48c927a5661d280574f9a8b23a3e5e60
+size 4933786851

model-00005-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66780364e586394132739ed509a43531c0c49576a7b6b680f4534ea9930a4798
+oid sha256:e24219198f4136b092ed88f637f91c5777ece2a488833bb9cf3727b494e016a4
 size 4977055135

model-00006-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c49a7e32e03072f7cbe3cf644ed3acf95311ba26a5fbc70d0b0501a0bb72997
-size 4977055096
+oid sha256:ecaa5c823f92772e338093a6fc8356a3ee7c05d3fcfe5770d6b01879ad4d7a23
+size 4977055104

model-00007-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b65f113992c31139678fc1e21cf27ff9ff02a33d947995d36cbba9eb6810da24
-size 4977088086
+oid sha256:aeaabf66442e56253508eefce1a29eaee70cee84fb67616a3ac8dc78b6163da0
+size 4977088092

model-00008-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b2dc6991759a2e1718dac761b133dd8374f73443645dc0bdd06ea2932324f8c
-size 4750027590
+oid sha256:a9a19adb72fba3822d66ac50c358914299fc86ca07cd9e9c983f87e3216df84e
+size 4750125895

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 39517816284
+    "total_size": 39518012903
   },
   "weight_map": {
     "lm_head.weight": "model-00008-of-00008.safetensors",