Initial Upload

README.md

@@ -1,3 +1,86 @@
----
-license: apache-2.0
----
+---
+language:
+- en
+tags:
+- pytorch
+- causal-lm
+- tinyllama
+- autoround
+- autoawq
+- intel
+- awq
+- woq
+license: apache-2.0
+model_name: TinyLlama 1.1B v1.1
+base_model: TinyLlama/TinyLlama_v1.1
+inference: false
+model_creator: TinyLlama
+datasets:
+- cerebras/SlimPajama-627B
+pipeline_tag: text-generation
+prompt_template: '{prompt}
+  '
+quantized_by: fbaldassarri
+---
+
+
+
+## Model Information
+
+Quantized version of [TinyLlama 1.1B v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1/) using torch.float32 for quantization tuning.
+- 4 bits (INT4)
+- group size = 128
+- Asymmetrical Quantization
+- Method AutoAWQ
+
+Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round)
+
+Note: this INT4 version of TinyLlama 1.1B v1.1 has been quantized to run inference through CPU.
+
+## Replication Recipe
+
+### Step 1 Install Requirements
+
+I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment. 
+
+```
+python -m pip install <package> --upgrade
+```
+
+- accelerate==1.0.1
+- auto_gptq==0.7.1
+- neural_compressor==3.1
+- torch==2.3.0+cpu
+- torchaudio==2.5.0+cpu
+- torchvision==0.18.0+cpu
+- transformers==4.45.2
+
+### Step 2 Build Intel Autoround wheel from sources
+
+```
+python -m pip install git+https://github.com/intel/auto-round.git
+```
+
+### Step 3 Script for Quantization
+
+```
+  from transformers import AutoModelForCausalLM, AutoTokenizer
+  model_name = "TinyLlama/TinyLlama_v1.1"
+  model = AutoModelForCausalLM.from_pretrained(model_name)
+  tokenizer = AutoTokenizer.from_pretrained(model_name)
+  from auto_round import AutoRound
+  bits, group_size, sym = 4, 128, False
+  autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym)
+  autoround.quantize()
+  output_dir = "./AutoRound/TinyLlama_TinyLlama_v1.1-autoawq-int4-gs128-asym"
+  autoround.save_quantized(output_dir, format='auto_awq', inplace=True)
+```
+
+## License
+
+[Apache 2.0 License](https://choosealicense.com/licenses/apache-2.0/)
+
+## Disclaimer
+
+This quantized model comes with no warrenty. It has been developed only for research purposes. 
+

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama_v1.1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9211bfad770807f67ee5532df5757ef9aafd0d223f03d90800a58cf9e1198b3
+size 1028079184

quantization_config.json

@@ -0,0 +1,15 @@
+{
+  "quant_method": "awq",
+  "modules_to_not_convert": null,
+  "version": "gemm",
+  "iters": 200,
+  "lr": 0.005,
+  "minmax_lr": 0.005,
+  "enable_minmax_tuning": true,
+  "enable_quanted_input": true,
+  "scale_dtype": "float16",
+  "sym": false,
+  "bits": 4,
+  "group_size": 128,
+  "zero_point": true
+}

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": null,
+  "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,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}