orig v1.8

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -8,7 +8,7 @@ tags:
 - retrieverapp
 - orig
 ---
-RetrieverApp *orig* model version 1.5 (trained with curated labels)
+RetrieverApp *orig* model version 1.8 (trained with curated labels)
 
 QLORA Fine-tuned, quantized (4bits), `mlx` compatible RetrieverApp model based on Llama3-8B-IT.
 

config.json

@@ -6,6 +6,7 @@
     "attention_dropout": 0.0,
     "bos_token_id": 128000,
     "eos_token_id": 128009,
+    "head_dim": 128,
     "hidden_act": "silu",
     "hidden_size": 4096,
     "initializer_range": 0.02,
@@ -21,12 +22,16 @@
         "group_size": 64,
         "bits": 4
     },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4
+    },
     "rms_norm_eps": 1e-05,
     "rope_scaling": null,
     "rope_theta": 500000.0,
     "tie_word_embeddings": false,
     "torch_dtype": "bfloat16",
-    "transformers_version": "4.43.3",
+    "transformers_version": "4.45.1",
     "use_cache": true,
     "vocab_size": 128256
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a823d4ef13a2267ead95344c72011bf5f8320b1bfdba0a3d9b160f02f6101a8
+oid sha256:bd68362078a251f98e6e1a15d14c9873a1f4101744e9c7095b49ace62c6f9f8c
 size 4517489037