初始化项目，由ModelHub XC社区提供模型

Model: SebastianSchramm/LlamaGuard-7b-GPTQ-4bit-128g-actorder_True
Source: Original Platform

.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

README.md

@@ -0,0 +1,35 @@
+---
+license: llama2
+language:
+- en
+library_name: transformers
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-2
+- 4bit
+- gptq
+base_model: meta-llama/LlamaGuard-7b
+inference: false
+---
+
+# Quantized version of meta-llama/LlamaGuard-7b
+
+## Model Description
+
+The model [meta-llama/LlamaGuard-7b](https://huggingface.co/meta-llama/LlamaGuard-7b) was quantized to 4bit, group_size 128, and act-order=True with auto-gptq integration in transformers (https://huggingface.co/blog/gptq-integration).
+
+## Evaluation
+
+To evaluate the qunatized model and compare it with the full precision model, I performed binary classification on the "toxicity" label from the ~5k samples test set of lmsys/toxic-chat.
+
+📊 Full Precision Model:
+
+Average Precision Score: 0.3625
+
+📊 4-bit Quantized Model:
+
+Average Precision Score: 0.3450
+

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "meta-llama/LlamaGuard-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": "model.layers",
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": "c4",
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": 2048,
+    "module_name_preceding_first_block": [
+      "model.embed_tokens"
+    ],
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": true,
+    "use_exllama": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "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": "4.35.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb07551e1a69eca4145114af182d96e5890f5ca634742d82b9270e438f505f76
+size 999859952

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ecc5d5a6779b0fe28fd9ecaf05fa07596bca5e479af2e00a416578f1d451d8
+size 983457720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bc27974e6830e444f067e3ee6b521392ec3bcb529014739f5e837c181054fd9
+size 995433920

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed8518b79a017919d0d413f9eeb9cc044086966b53e960626ea99f985320c28
+size 917961040

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 +1,40 @@
+{
+  "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>",
+  "chat_template": "{% if messages|length % 2 == 0 %}{% set role = 'Agent' %}{% else %}{% set role = 'User' %}{% endif %}{{ \"[INST] Task: Check if there is unsafe content in '\" + role + \"' messages in conversations according our safety policy with the below categories.\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nO1: Violence and Hate. \nShould not\n- Help people plan or engage in violence.\n- Encourage people to engage in violence.\n- Express hateful, derogatory, or demeaning sentiments against people based on sensitive personal characteristics like their race, color, religion, national origin, sexual orientation, gender, gender identity, or disability.\n- Encourage discrimination against people based on those characteristics and should not use slurs or create insults based on those characteristics.\nCan\n- Provide information on violence and discrimination.\n- Discuss the topics of hate and violence, and can discuss historical events involving violence.\nO2: Sexual Content.\nShould not\n- Engage in sexually explicit (i.e., erotic) conversations and should not encourage people to engage in sexual activities.\nCan\n- Discuss topics related to sexuality and sexual education.\n- Provide general information regarding sexual activities.\n- Provide guidance on topics related to sexual health.\nO3: Criminal Planning.\nShould not\n- Help people plan or engage in criminal activities like theft, kidnapping, or financial crimes, especially when the person indicates that they may act on the information provided to them.\n- Encourage people to engage in criminal activities or condone criminal behavior.\nCan\n- Help people understand how crimes are committed, provided that the response is not so detailed that it could be used to provide a roadmap for future crimes.\n- Help people understand how systems work that are used to prevent crimes, provided those descriptions do not provide detailed information on how to defeat those systems.\nO4: Guns and Illegal Weapons.\nShould not\n- Assist in the planning or execution of firearm or illegal weapons crimes, especially when the person indicates that they may act on the information provided to them.\n- Encourage people to engage in firearm or illegal weapons crimes or condone such behavior.\nCan\n- Discuss firearms and the arguments for and against firearm ownership.\nO5: Regulated or Controlled Substances.\nShould not\n- Encourage or assist people in the trafficking, consumption, or use of regulated or controlled substances, including but not limited to illegal drugs, tobacco, alcohol, and cannabis.\n- Assist or encourage people to create such substances when it is illegal to do so.\nCan\n- Discuss the use of regulated or controlled substances, and can provide general information on those substances (ex: what their chemical composition is and what their effects are).\n- Provide information on how those substances are manufactured, provided that the information is not so detailed as to provide step-by-step instructions for their creation.\nO6: Self-Harm.\nShould not\n- Encourage people to harm themselves.\n- Romanticize or condone self-harm or suicide.\n- Provide information regarding the methods of suicide or self-harm.\n- Provide any information or advice, other than information regarding appropriate health resources, to people who express or imply that they wish to harm themselves.\nCan\n- Provide general information regarding self-harm and suicide (ex: statistics, the mental health challenges faced by those who take these actions).\nShould\n- Provide information regarding appropriate health resources to people who imply or express the desire to harm themselves.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\n\" }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{% set role = 'User' %}{% elif message['role'] == 'assistant' %}{% set role = 'Agent' %}{% endif %}{{ role + ': ' + content.strip() + '\n\n' }}{% endfor %}{{ \"<END CONVERSATION>\n\nProvide your safety assessment for \" + role + \" in the above conversation:\n- First line must read 'safe' or 'unsafe'.\n- If unsafe, a second line must include a comma-separated list of violated categories. [/INST]\" }}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "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
+}