upload model file

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

README.md

@@ -1,3 +1,108 @@
----
-license: apache-2.0
----
+
+
+
+
+
+
+## Model Details
+
+This model is an int4 model with group_size 128 of [google/gemma-2b](https://huggingface.co/google/gemma-2b) generated by [intel/auto-round](https://github.com/intel/auto-round).
+
+
+
+### Use the model
+
+### INT4 Inference with AutoGPTQ's  kernel
+
+Install the latest [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) from source first
+
+```python
+##pip install auto-gptq[triton] 
+##pip install triton==2.2.0
+from transformers import AutoModelForCausalLM, AutoTokenizer
+quantized_model_dir = "Intel/gemma-2b-int4-inc"
+tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir)
+model = AutoModelForCausalLM.from_pretrained(quantized_model_dir,
+                                             device_map="auto",
+                                             trust_remote_code=False,
+                                             )
+tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir, use_fast=True)
+text = "There is a girl who likes adventure,"
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=True)[0]))
+```
+
+
+
+### Evaluate the model 
+
+Install [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness.git) from source,  and the git id we used is 96d185fa6232a5ab685ba7c43e45d1dbb3bb906d
+
+pip install auto-gptq[triton] 
+pip install triton==2.2.0
+
+Please note that there is a discrepancy between the baseline result and the official data, which is a known issue within the official model card community.
+
+```bash
+lm_eval --model hf --model_args pretrained="Intel/gemma-2b-int4-inc",autogptq=True,gptq_use_triton=True --device cuda:0 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,rte,arc_easy,arc_challenge,mmlu --batch_size 16
+```
+
+| Metric         | FP16   | int4   |
+| -------------- | ------ | ------ |
+| Avg.           | 0.5383 | 0.5338 |
+| mmlu           | 0.3337 | 0.3276 |
+| lambada_openai | 0.6398 | 0.6319 |
+| hellaswag      | 0.5271 | 0.5161 |
+| winogrande     | 0.6472 | 0.6472 |
+| piqa           | 0.7699 | 0.7622 |
+| truthfulqa_mc1 | 0.2203 | 0.2191 |
+| openbookqa     | 0.3020 | 0.2980 |
+| boolq          | 0.6939 | 0.6939 |
+| rte            | 0.6426 | 0.6498 |
+| arc_easy       | 0.7424 | 0.7348 |
+| arc_challenge  | 0.4019 | 0.3908 |
+
+
+
+### 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  google/gemma-2b \
+--device 0 \
+--group_size 128 \
+--bits 4 \
+--iters 400 \
+--use_quant_input \
+--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.
+
+

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "/models/gemma-2b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "autoround_version": "0.1",
+    "bits": 4,
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "enable_minmax_tuning": true,
+    "group_size": 128,
+    "is_marlin_format": false,
+    "iters": 400,
+    "lr": 0.0025,
+    "minmax_lr": 0.0025,
+    "model_file_base_name": "model",
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "scale_dtype": "torch.float32",
+    "static_groups": false,
+    "sym": false,
+    "true_sequential": false,
+    "use_quant_input": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee3302033aa9b45890be54a999acad6b7531ff900408b325eafd6a21bc20399
+size 3130472776

quantize_config.json

@@ -0,0 +1,20 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": false,
+  "true_sequential": false,
+  "model_name_or_path": null,
+  "model_file_base_name": "model",
+  "is_marlin_format": false,
+  "quant_method": "intel/auto-round",
+  "autoround_version": "0.1",
+  "iters": 400,
+  "lr": 0.0025,
+  "minmax_lr": 0.0025,
+  "enable_minmax_tuning": true,
+  "use_quant_input": true,
+  "scale_dtype": "torch.float32"
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "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 sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}