first commit

Signed-off-by: wenhuach <wenhuach87@gmail.com>

README.md

@@ -1,3 +1,102 @@
----
-license: apache-2.0
----
+## Model Details
+
+This model is an int4 model with group_size 32 sym of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) generated by [intel/auto-round](https://github.com/intel/auto-round), we will generate group_size 128 later
+
+## How To Use
+
+### INT4 Inference with AutoGPTQ
+
+
+
+```python
+##pip install auto-gptq==0.7.1
+from transformers import AutoModelForCausalLM,AutoTokenizer
+quantized_model_dir = "Intel/Qwen2-1.5B-Insturct-int4-inc"
+tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+text = "There is a girl who likes adventure,"
+text = "Once upon a time,"
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0]))
+##There is a girl who likes adventure, she is always looking for new things to do. She is very adventurous and loves to try new things. She is always looking for new things to do and is always looking for new things to try. She is always looking for new things to do and
+
+##Once upon a time, there was a young boy named Jack. He lived in a small village in England. Jack was very curious and loved to explore the world around him. One day, he decided to go on a journey to find a magical tree that could grant him three
+
+```
+
+
+
+### Evaluate the model 
+
+pip3 install lm-eval==0.4.2
+
+```bash
+lm_eval --model hf --model_args pretrained="Intel/Qwen2-1.5B-Instuct-int4-inc" --device cuda:0 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu --batch_size 16
+```
+
+
+
+| Metric-1.5B-instruct | BF16   | W4G32 sym |
+| -------------------- | ------ | --------- |
+| Avg                  | 0.5518 | 0.5474    |
+| mmlu                 | 0.5565 | 0.5499    |
+| lambada_openai       | 0.6484 | 0.6412    |
+| hellaswag            | 0.4935 | 0.4859    |
+| winogrande           | 0.6543 | 0.6606    |
+| piqa                 | 0.7612 | 0.7573    |
+| truthfulqa_mc1       | 0.2827 | 0.2766    |
+| openbookqa           | 0.2780 | 0.274     |
+| boolq                | 0.7654 | 0.7639    |
+| arc_easy             | 0.7024 | 0.6949    |
+| arc_challenge        | 0.3754 | 0.3695    |
+
+
+
+### Reproduce the model
+
+Here is the sample command to reproduce the model
+
+```bash
+git clone https://github.com/intel/auto-round
+cd auto-round/examples/language-modeling
+pip install -r requirements.txt
+python3 main.py \
+--model_name  Qwen/Qwen2-1.5B-Instruct \
+--device 0 \
+--group_size 32 \
+--bits 4 \
+--sym \
+--iter 1000 \
+--deployment_device 'gpu' \
+--output_dir "./tmp_autoround" 
+```
+
+
+
+## Ethical Considerations and Limitations
+
+The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
+
+Therefore, before deploying any applications of the model, developers should perform safety testing.
+
+## Caveats and Recommendations
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
+
+Here are a couple of useful links to learn more about Intel's AI software:
+
+* Intel Neural Compressor [link](https://github.com/intel/neural-compressor)
+* Intel Extension for Transformers [link](https://github.com/intel/intel-extension-for-transformers)
+
+## Disclaimer
+
+The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
+
+
+
+## Cite
+
+@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
+
+[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "/models/Qwen2-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "quantization_config": {
+    "autoround_version": "0.2.1.dev",
+    "bits": 4,
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "enable_minmax_tuning": true,
+    "enable_quanted_input": true,
+    "group_size": 32,
+    "is_marlin_format": false,
+    "iters": 1000,
+    "lr": 0.001,
+    "minmax_lr": 0.001,
+    "model_file_base_name": "model",
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "scale_dtype": "float16",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": false
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f22fd4f4bfa905c4f983cad04d07b8bff73a3f364c6f4807e97ee51ea4e148a
+size 1694567560

quantize_config.json

@@ -0,0 +1,20 @@
+{
+  "bits": 4,
+  "group_size": 32,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": false,
+  "model_name_or_path": null,
+  "model_file_base_name": "model",
+  "is_marlin_format": false,
+  "quant_method": "intel/auto-round",
+  "autoround_version": "0.2.1.dev",
+  "iters": 1000,
+  "lr": 0.001,
+  "minmax_lr": 0.001,
+  "enable_minmax_tuning": true,
+  "enable_quanted_input": true,
+  "scale_dtype": "float16"
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}