Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,37 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz 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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.mnn filter=lfs diff=lfs merge=lfs -text
+*.mnn.* filter=lfs diff=lfs merge=lfs -text
+*.weight filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+# Llama-2-7b-chat-MNN
+
+## Introduction
+
+This model is a 4-bit quantized version of the MNN model exported from Llama-2-7b-chat using [llm-export](https://github.com/wangzhaode/llm-export).

config.json

@@ -0,0 +1,9 @@
+{
+    "llm_model": "llama2-7b-int4.mnn",
+    "llm_weight": "llama2-7b-int4.mnn.weight",
+
+    "backend_type": "cpu",
+    "thread_num": 4,
+    "precision": "low",
+    "memory": "low"
+}

embeddings_bf16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9211314048edb8aeda2bd06598c914abf1965b925e9c3820a7dcd747087b62
+size 262144000

llama2-7b-int4.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c436df6db1b99a577e995f427f0b6b871d6a2886908dfa6640f468f699517e95
+size 3317123634

llm_config.json

@@ -0,0 +1,15 @@
+{
+    "hidden_size": 4096,
+    "layer_nums": 32,
+    "attention_mask": "float",
+    "key_value_shape": [
+        2,
+        1,
+        0,
+        32,
+        128
+    ],
+    "prompt_template": "[INST]%s[/INST]",
+    "is_visual": false,
+    "is_single": true
+}