Duplicate from localmodels/LLM

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

OpenAssistant-SFT-7-LLaMA-30B-GPTQ-4bit--1g.act.order.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ee1b559dc726c05a849281f07fdfd9ec0f2f520dae60a0b0e87f8ccfe8c894
+size 16940554392

README.md

@@ -0,0 +1,65 @@
+---
+duplicated_from: localmodels/LLM
+---
+# OpenAssistant LLaMA 30B SFT 7 GPTQ
+
+From: https://huggingface.co/OpenAssistant/oasst-sft-7-llama-30b-xor
+
+---
+
+| Model | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
+| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
+| OpenAssistant-SFT-7-LLaMA-30B-GPTQ-4bit--1g.act.order | 4 | None | True | 16.94 GB | True | GPTQ-for-LLaMa | Most compatible. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. |
+
+---
+
+# OpenAssistant LLaMA 30B SFT 7
+
+### Configuration
+
+```
+llama-30b-sft-7:
+  dtype: fp16
+  log_dir: "llama_log_30b"
+  learning_rate: 1e-5
+  model_name: /home/ubuntu/Open-Assistant/model/model_training/.saved/llama-30b-super-pretrain/checkpoint-3500
+  #model_name: OpenAssistant/llama-30b-super-pretrain
+  output_dir: llama_model_30b
+  deepspeed_config: configs/zero3_config_sft.json
+  weight_decay: 0.0
+  residual_dropout: 0.0
+  max_length: 2048
+  use_flash_attention: true
+  warmup_steps: 20
+  gradient_checkpointing: true
+  gradient_accumulation_steps: 12
+  per_device_train_batch_size: 2
+  per_device_eval_batch_size: 3
+  eval_steps: 101
+  save_steps: 485
+  num_train_epochs: 4
+  save_total_limit: 3
+  use_custom_sampler: true
+  sort_by_length: false
+  #save_strategy: steps
+  save_strategy: epoch
+  datasets:
+    - oasst_export:
+        lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk"
+        input_file_path: 2023-04-12_oasst_release_ready_synth.jsonl.gz
+        val_split: 0.05
+    - vicuna:
+        val_split: 0.05
+        max_val_set: 800
+        fraction: 1.0
+    - dolly15k:
+        val_split: 0.05
+        max_val_set: 300
+    - grade_school_math_instructions:
+        val_split: 0.05
+    - code_alpaca:
+        val_split: 0.05
+        max_val_set: 250
+```
+
+- **OASST dataset paper:** https://arxiv.org/abs/2304.07327

added_tokens.json

@@ -0,0 +1,18 @@
+{
+  "<|assistant|>": 32004,
+  "<|dummy10|>": 32014,
+  "<|dummy11|>": 32015,
+  "<|dummy1|>": 32005,
+  "<|dummy2|>": 32006,
+  "<|dummy3|>": 32007,
+  "<|dummy4|>": 32008,
+  "<|dummy5|>": 32009,
+  "<|dummy6|>": 32010,
+  "<|dummy7|>": 32011,
+  "<|dummy8|>": 32012,
+  "<|dummy9|>": 32013,
+  "<|prefix_begin|>": 32000,
+  "<|prefix_end|>": 32003,
+  "<|prompter|>": 32002,
+  "<|system|>": 32001
+}

config.json

@@ -0,0 +1,23 @@
+{
+    "_name_or_path": "/content/OpenAssistant-SFT-7/",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 6656,
+    "initializer_range": 0.02,
+    "intermediate_size": 17920,
+    "max_position_embeddings": 2048,
+    "model_type": "llama",
+    "num_attention_heads": 52,
+    "num_hidden_layers": 60,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.29.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32016
+}

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": "4.29.0.dev0"
+}

quantize_config.json

@@ -0,0 +1,8 @@
+{
+    "bits": 4,
+    "group_size": -1,
+    "damp_percent": 0.01,
+    "desc_act": true,
+    "sym": true,
+    "true_sequential": true
+}

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<|prompter|>",
+    "<|system|>",
+    "<|prefix_begin|>",
+    "<|prefix_end|>",
+    "<|assistant|>"
+  ],
+  "bos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "sep_token": "<s>",
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}