Initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+models

README.md

@@ -0,0 +1,27 @@
+---
+license: unknown
+---
+
+[ehartford/WizardLM-7B-Uncensored](https://huggingface.co/ehartford/WizardLM-7B-Uncensored) quantized to **8bit GPTQ** with act order + true sequential, no group size.
+
+*For most uses, this probably isn't what you want.*\
+*For 4bit with no act order or compatibility with `old-cuda` (text-generation-webui default) see [TheBloke/WizardLM-7B-uncensored-GPTQ](https://huggingface.co/TheBloke/WizardLM-7B-uncensored-GPTQ)*
+
+Quantized using AutoGPTQ with the following config:
+```python
+config: dict = dict(
+    quantize_config=dict(bits=8, desc_act=True, true_sequential=True, model_file_base_name='WizardLM-7B-Uncensored'),
+    use_safetensors=True
+)
+```
+See `quantize.py` for the full script.
+
+Tested for compatibility with:
+WSL with GPTQ-for-Llama `triton` branch.
+Windows with AutoGPTQ on `cuda` (triton deselected)
+
+AutoGPTQ loader should read configuration from `quantize_config.json`
+For GPTQ-for-Llama use the following configuration when loading:\
+wbits: 8\
+groupsize: None\
+model_type: llama\

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "models/WizardLM-7B-Uncensored",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 32001
+}

quantize.py

@@ -0,0 +1,22 @@
+from transformers import AutoTokenizer, TextGenerationPipeline
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+import logging
+
+pretrained_model_dir: str = "models/WizardLM-7B-Uncensored"
+quantized_model_dir: str = "./"
+config: dict = dict(
+    quantize_config=dict(bits=8, desc_act=True, true_sequential=True, model_file_base_name='WizardLM-7B-Uncensored'),
+    use_safetensors=True
+)
+
+logging.basicConfig(
+    format="%(asctime)s %(levelname)s [%(name)s] %(message)s", level=logging.INFO, datefmt="%Y-%m-%d %H:%M:%S"
+)
+
+tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True)
+examples: list[dict[str, list[int]]] = [tokenizer("It was a cold night")]
+
+model = AutoGPTQForCausalLM.from_pretrained(pretrained_model_dir, BaseQuantizeConfig(**config['quantize_config']))
+model.quantize(examples)
+
+model.save_quantized(quantized_model_dir, use_safetensors=config['use_safetensors'])

quantize_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 8,
+  "group_size": -1,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": "WizardLM-7B-Uncensored"
+}

tokenizer.model

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