Upload folder using huggingface_hub

README.md

@@ -0,0 +1,49 @@
+# Block-AP (EfficientQAT w/o E2E-AP)
+
+[EfficientQAT](https://arxiv.org/abs/2407.11062) involves two consecutive training phases: Block-wise training of all parameters (Block-AP) and end-to-end training of quantization parameters (E2E-QP).
+
+In this repo, we provide the quantized checkpoints of Block-AP. Anyone can use them to reproduce our results or carry following research.
+
+## Performance
+
+| Model | Quantization | WikiText2 PPL | Avg. Accuracy | Model Size (GB) | Hub link|
+|-------|--------------|---------------|---------------|-----------------|----------|
+Llama-2-7B|fp16|5.47|64.86|13.2|-|
+Llama-2-7B|w4g128|5.56|64.07|3.7|[Link](https://huggingface.co/ChenMnZ/Llama-2-7b-BlockAd-w4g128)|
+Llama-2-7B|w3g128|5.89|63.96|3.1|[Link](https://huggingface.co/ChenMnZ/Llama-2-7b-BlockAP-w3g128)|
+Llama-2-7B|w2g64|7.65|59.54|2.3|[Link](https://huggingface.co/ChenMnZ/Llama-2-7b-BlockAP-w2g64)|
+Llama-2-7B|w2g128|7.94|58.72|2.2|[Link](https://huggingface.co/ChenMnZ/Llama-2-7b-BlockAP-w2g128)|
+Llama-2-13B|fp16|4.88|67.81|25.4|-|
+Llama-2-13B|w4g128|4.96|67.27|6.8|[Link](https://huggingface.co/ChenMnZ/Llama-2-13b-BlockAP-w4g128)|
+Llama-2-13B|w3g128|5.20|67.30|5.6|[Link](https://huggingface.co/ChenMnZ/Llama-2-13b-BlockAP-w3g128)|
+Llama-2-13B|w2g64|6.55|63.10|4.0|[Link](https://huggingface.co/ChenMnZ/Llama-2-13b-BlockAP-w2g64)|
+Llama-2-13B|w2g128|6.68|63.49|3.8|[Link](https://huggingface.co/ChenMnZ/Llama-2-13b-BlockAP-w2g128)|
+Llama-2-70B|fp16|3.32|72.41|131.6|-|
+Llama-2-70B|w4g128|3.41|72.54|35.8|[Link](https://huggingface.co/ChenMnZ/Llama-2-70b-BlockAP-w4g128)|
+Llama-2-70B|w3g128|3.65|71.88|29.1|[Link](https://huggingface.co/ChenMnZ/Llama-2-70b-BlockAP-w3g128)|
+Llama-2-70B|w2g64|4.96|69.44|20.1|[Link](https://huggingface.co/ChenMnZ/Llama-2-70b-BlockAP-w2g64)|
+Llama-2-70B|w2g128|5.26|68.73|18.9|[Link](https://huggingface.co/ChenMnZ/Llama-2-70b-BlockAP-w2g128)|
+Llama-3-8B|fp16|6.14|68.58|13.0|-|
+Llama-3-8B|w4g128|6.50|68.43|5.4|[Link](https://huggingface.co/ChenMnZ/Llama-3-8b-BlockAP-w4g128)|
+Llama-3-8B|w3g128|7.34|66.72|4.7|[Link](https://huggingface.co/ChenMnZ/Llama-3-8b-BlockAP-w3g128)|
+Llama-3-8B|w2g64|12.47|58.65|3.9|[Link](https://huggingface.co/ChenMnZ/Llama-3-8b-BlockAP-w2g64)|
+Llama-3-8B|w2g128|13.25|58.23|3.8|[Link](https://huggingface.co/ChenMnZ/Llama-3-8b-BlockAP-w2g128)|
+Llama-3-70B|fp16|2.85|75.33|137.8|-|
+Llama-3-70B|w4g128|3.18|74.50|38.9|[Link](https://huggingface.co/ChenMnZ/Llama-3-70b-BlockAP-w4g128)|
+Llama-3-70B|w3g128|4.88|71.90|32.2|[Link](https://huggingface.co/ChenMnZ/Llama-3-70b-BlockAP-w3g128)|
+Llama-3-70B|w2g64|13.75|66.70|23.2|[Link](https://huggingface.co/ChenMnZ/Llama-3-70b-BlockAP-w2g64)|
+Llama-3-70B|w2g128|16.79|65.06|22.0|[Link](https://huggingface.co/ChenMnZ/Llama-3-70b-BlockAP-w2g128)|
+Llama-3-8B-Instruct|fp16|8.29|68.43|13.0|-|
+Llama-3-8B-Instruct|w4g128|8.76|67.80|5.4|[Link](https://huggingface.co/ChenMnZ/Llama-3-8b-instruct-BlockAP-w4g128)|
+Llama-3-8B-Instruct|w3g128|9.83|66.54|4.7|[Link](https://huggingface.co/ChenMnZ/Llama-3-8b-instruct-BlockAP-w3g128)|
+Llama-3-8B-Instruct|w2g64|16.77|58.62|3.9|[Link](https://huggingface.co/ChenMnZ/Llama-3-8b-instruct-BlockAP-w2g64)|
+Llama-3-8B-Instruct|w2g128|18.02|57.19|3.8|[Link](https://huggingface.co/ChenMnZ/Llama-3-8b-instruct-BlockAP-w2g128)|
+Llama-3-70B-Instruct|fp16|5.33|73.78|137.8|-|
+Llama-3-70B-Instruct|w4g128|5.77|73.52|38.9|[Link](https://huggingface.co/ChenMnZ/Llama-3-70b-instruct-BlockAP-w4g128)|
+Llama-3-70B-Instruct|w3g128|7.25|69.80|32.2|[Link](https://huggingface.co/ChenMnZ/Llama-3-70b-instruct-BlockAP-w3g128)|
+Llama-3-70B-Instruct|w2g64|12.48|65.60|23.2|[Link](https://huggingface.co/ChenMnZ/Llama-3-70b-instruct-BlockAP-w2g64)|
+Llama-3-70B-Instruct|w2g128|13.48|61.75|22.0|[Link](https://huggingface.co/ChenMnZ/Llama-3-70b-instruct-BlockAP-w2g128)|
+
+
+## Usage
+Please refer [https://github.com/OpenGVLab/EfficientQAT](https://github.com/OpenGVLab/EfficientQAT) for details. These checkpoints can be used to [following E2E-AP](https://github.com/OpenGVLab/EfficientQAT?tab=readme-ov-file#training), as well as be [inferenced](https://github.com/OpenGVLab/EfficientQAT?tab=readme-ov-file#inference) directly. 

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/cpfs01/user/chenmengzhao/llama_quantization/llama2-hf/Llama-2-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20227d5b8151a3310cb43c029c0e4226132ebddc357c25e2c0d488d569df5da8
+size 3243394080

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}