Upload folder using huggingface_hub

README.md

@@ -1,3 +1,13 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+# Qwen2.5-0.5B-Instruct-MNN
+
+## Introduction
+
+This model is a 4-bit quantized version of the MNN model exported from Qwen2.5-0.5B-Instruct-MNN using [llm-export](https://github.com/wangzhaode/llm-export).

config.json

@@ -0,0 +1,8 @@
+{
+    "llm_model": "llm.mnn",
+    "llm_weight": "llm.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 sha256:4e96b0df6d274768cbb7e72404011853d23349999b658dc2f4dfb3c431ea223f
+size 272269312

llm.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480da511e603bd82f8d4af4e1f778ad72baadf8307f3585465ad9a94daca1a88
+size 566264

llm.mnn.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245ce4289f456dcb371a8f8deabf75c3c4ee75f34b19e0d9723ba09b2fbacf8c
+size 2808932

llm.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed0f4dcdd31dca15fcb548d2fc8b63b0014031fbd5f627508435726f90c75da
+size 277967498

llm_config.json

@@ -0,0 +1,14 @@
+{
+    "hidden_size": 896,
+    "layer_nums": 24,
+    "attention_mask": "float",
+    "key_value_shape": [
+        2,
+        1,
+        0,
+        2,
+        64
+    ],
+    "prompt_template": "<|im_start|>user\n%s<|im_end|>\n<|im_start|>assistant\n",
+    "is_visual": false
+}