Upload folder using huggingface_hub

GPT4-x-Vicuna-13B-GPTQ-4bit-128g.compat.act-order.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f16c585dbad54501d66dadb724176d06ef7983ef0c5fa0f2fd02f41dd9b9b6
+size 7255179696

README.md

@@ -1,3 +1,22 @@
 ---
-license: other
+license: gpl
 ---
+As a base model used https://huggingface.co/eachadea/vicuna-13b-1.1
+
+Finetuned on Teknium's GPTeacher dataset, unreleased Roleplay v2 dataset, GPT-4-LLM dataset, and Nous Research Instruct Dataset
+
+Approx 180k instructions, all from GPT-4, all cleaned of any OpenAI censorship/"As an AI Language Model" etc.
+
+Base model still has OpenAI censorship. Soon, a new version will be released with cleaned vicuna from https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltere
+
+Trained on 8 A100-80GB GPUs for 5 epochs following Alpaca deepspeed training code.
+
+Nous Research Instruct Dataset will be released soon.
+
+GPTeacher, Roleplay v2 by https://huggingface.co/teknium
+
+Wizard LM by https://github.com/nlpxucan
+
+Nous Research Instruct Dataset by https://huggingface.co/karan4d and https://huggingface.co/huemin
+
+Compute provided by our project sponsor https://redmond.ai/

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "eachadea/vicuna-13b-1.1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32001
+}

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": "4.28.1"
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<unk>",
+    "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 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "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": 512,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.9973568281938325,
+  "global_step": 3545,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.85980221058755e-06,
+      "loss": 0.7246,
+      "step": 500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 7.405468295520653e-06,
+      "loss": 0.5968,
+      "step": 1000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 5.9511343804537524e-06,
+      "loss": 0.5052,
+      "step": 1500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 4.496800465386853e-06,
+      "loss": 0.3611,
+      "step": 2000
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 3.0424665503199537e-06,
+      "loss": 0.2573,
+      "step": 2500
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 1.5881326352530543e-06,
+      "loss": 0.1943,
+      "step": 3000
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 1.3379872018615477e-07,
+      "loss": 0.1354,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "step": 3545,
+      "total_flos": 897107395346432.0,
+      "train_loss": 0.3929895871785195,
+      "train_runtime": 101143.6052,
+      "train_samples_per_second": 8.977,
+      "train_steps_per_second": 0.035
+    }
+  ],
+  "max_steps": 3545,
+  "num_train_epochs": 5,
+  "total_flos": 897107395346432.0,
+  "trial_name": null,
+  "trial_params": null
+}