Upload 16 files

README.md

@@ -0,0 +1,59 @@
+---
+license: creativeml-openrail-m
+language:
+- en
+thumbnail:
+tags:
+- text generation
+- conversational
+inference: false
+---
+
+# Pygmalion 6B
+
+## Model description
+
+Pymalion 6B is a proof-of-concept dialogue model based on EleutherAI's [GPT-J-6B](https://huggingface.co/EleutherAI/gpt-j-6B).
+
+**Warning:** This model is **NOT** suitable for use by minors. It **will** output X-rated content under certain circumstances.
+
+## Training data
+
+The fine-tuning dataset consisted of 56MB of dialogue data gathered from multiple sources, which includes both real _and_ partially machine-generated conversations.
+
+## Training procedure
+
+Model weights were initialized from the `uft-6b` ConvoGPT model made available in [this commit](https://huggingface.co/hakurei/convogpt/tree/41b67bfddb6cd97070ffddf708e9720c9cb8d224/6b-uft).
+
+The model was then further fine-tuned on ~48.5 million tokens for ~5k steps on 4 NVIDIA A40s using DeepSpeed.
+
+## Intended use
+
+### The easy way
+
+We provide a notebook with a Gradio UI for playing around with the model without having to manually format inputs. This notebook can be found [here](https://github.com/PygmalionAI/gradio-ui/blob/master/notebooks/GPU.ipynb).
+
+### The manual way
+
+The model can be used as a regular text generation model, but it'll perform best if the input prompt adheres to the following format:
+
+```
+[CHARACTER]'s Persona: [A few sentences about the character you want the model to play]
+<START>
+[DIALOGUE HISTORY]
+You: [Your input message here]
+[CHARACTER]:
+```
+
+Where `[CHARACTER]` is, as you can probably guess, the name of the character you want the model to portray, `<START>` should be used verbatim as a delimiter token to separate persona and scenario data from the dialogue, and `[DIALOGUE HISTORY]` is chat history so the model can have some conversational context to draw from. Ideally it'll be pairs of messages like:
+
+```
+[CHARACTER]: [some dialogue here]
+You: [your response to the dialogue above]
+```
+
+Apart from chat history, you can also just add example conversations in `[DIALOGUE HISTORY]` to show how the character should speak - ideally at the beginning, so it doesn't get confused as to what's conversation history vs. character definition.
+
+## Known issues
+
+We haven't played around with the model enough to enumerate them. Feel free to give us some feedback!

added_tokens.json

@@ -0,0 +1,145 @@
+{
+  "<|extratoken_100|>": 50356,
+  "<|extratoken_101|>": 50357,
+  "<|extratoken_102|>": 50358,
+  "<|extratoken_103|>": 50359,
+  "<|extratoken_104|>": 50360,
+  "<|extratoken_105|>": 50361,
+  "<|extratoken_106|>": 50362,
+  "<|extratoken_107|>": 50363,
+  "<|extratoken_108|>": 50364,
+  "<|extratoken_109|>": 50365,
+  "<|extratoken_10|>": 50266,
+  "<|extratoken_110|>": 50366,
+  "<|extratoken_111|>": 50367,
+  "<|extratoken_112|>": 50368,
+  "<|extratoken_113|>": 50369,
+  "<|extratoken_114|>": 50370,
+  "<|extratoken_115|>": 50371,
+  "<|extratoken_116|>": 50372,
+  "<|extratoken_117|>": 50373,
+  "<|extratoken_118|>": 50374,
+  "<|extratoken_119|>": 50375,
+  "<|extratoken_11|>": 50267,
+  "<|extratoken_120|>": 50376,
+  "<|extratoken_121|>": 50377,
+  "<|extratoken_122|>": 50378,
+  "<|extratoken_123|>": 50379,
+  "<|extratoken_124|>": 50380,
+  "<|extratoken_125|>": 50381,
+  "<|extratoken_126|>": 50382,
+  "<|extratoken_127|>": 50383,
+  "<|extratoken_128|>": 50384,
+  "<|extratoken_129|>": 50385,
+  "<|extratoken_12|>": 50268,
+  "<|extratoken_130|>": 50386,
+  "<|extratoken_131|>": 50387,
+  "<|extratoken_132|>": 50388,
+  "<|extratoken_133|>": 50389,
+  "<|extratoken_134|>": 50390,
+  "<|extratoken_135|>": 50391,
+  "<|extratoken_136|>": 50392,
+  "<|extratoken_137|>": 50393,
+  "<|extratoken_138|>": 50394,
+  "<|extratoken_139|>": 50395,
+  "<|extratoken_13|>": 50269,
+  "<|extratoken_140|>": 50396,
+  "<|extratoken_141|>": 50397,
+  "<|extratoken_142|>": 50398,
+  "<|extratoken_143|>": 50399,
+  "<|extratoken_14|>": 50270,
+  "<|extratoken_15|>": 50271,
+  "<|extratoken_16|>": 50272,
+  "<|extratoken_17|>": 50273,
+  "<|extratoken_18|>": 50274,
+  "<|extratoken_19|>": 50275,
+  "<|extratoken_1|>": 50257,
+  "<|extratoken_20|>": 50276,
+  "<|extratoken_21|>": 50277,
+  "<|extratoken_22|>": 50278,
+  "<|extratoken_23|>": 50279,
+  "<|extratoken_24|>": 50280,
+  "<|extratoken_25|>": 50281,
+  "<|extratoken_26|>": 50282,
+  "<|extratoken_27|>": 50283,
+  "<|extratoken_28|>": 50284,
+  "<|extratoken_29|>": 50285,
+  "<|extratoken_2|>": 50258,
+  "<|extratoken_30|>": 50286,
+  "<|extratoken_31|>": 50287,
+  "<|extratoken_32|>": 50288,
+  "<|extratoken_33|>": 50289,
+  "<|extratoken_34|>": 50290,
+  "<|extratoken_35|>": 50291,
+  "<|extratoken_36|>": 50292,
+  "<|extratoken_37|>": 50293,
+  "<|extratoken_38|>": 50294,
+  "<|extratoken_39|>": 50295,
+  "<|extratoken_3|>": 50259,
+  "<|extratoken_40|>": 50296,
+  "<|extratoken_41|>": 50297,
+  "<|extratoken_42|>": 50298,
+  "<|extratoken_43|>": 50299,
+  "<|extratoken_44|>": 50300,
+  "<|extratoken_45|>": 50301,
+  "<|extratoken_46|>": 50302,
+  "<|extratoken_47|>": 50303,
+  "<|extratoken_48|>": 50304,
+  "<|extratoken_49|>": 50305,
+  "<|extratoken_4|>": 50260,
+  "<|extratoken_50|>": 50306,
+  "<|extratoken_51|>": 50307,
+  "<|extratoken_52|>": 50308,
+  "<|extratoken_53|>": 50309,
+  "<|extratoken_54|>": 50310,
+  "<|extratoken_55|>": 50311,
+  "<|extratoken_56|>": 50312,
+  "<|extratoken_57|>": 50313,
+  "<|extratoken_58|>": 50314,
+  "<|extratoken_59|>": 50315,
+  "<|extratoken_5|>": 50261,
+  "<|extratoken_60|>": 50316,
+  "<|extratoken_61|>": 50317,
+  "<|extratoken_62|>": 50318,
+  "<|extratoken_63|>": 50319,
+  "<|extratoken_64|>": 50320,
+  "<|extratoken_65|>": 50321,
+  "<|extratoken_66|>": 50322,
+  "<|extratoken_67|>": 50323,
+  "<|extratoken_68|>": 50324,
+  "<|extratoken_69|>": 50325,
+  "<|extratoken_6|>": 50262,
+  "<|extratoken_70|>": 50326,
+  "<|extratoken_71|>": 50327,
+  "<|extratoken_72|>": 50328,
+  "<|extratoken_73|>": 50329,
+  "<|extratoken_74|>": 50330,
+  "<|extratoken_75|>": 50331,
+  "<|extratoken_76|>": 50332,
+  "<|extratoken_77|>": 50333,
+  "<|extratoken_78|>": 50334,
+  "<|extratoken_79|>": 50335,
+  "<|extratoken_7|>": 50263,
+  "<|extratoken_80|>": 50336,
+  "<|extratoken_81|>": 50337,
+  "<|extratoken_82|>": 50338,
+  "<|extratoken_83|>": 50339,
+  "<|extratoken_84|>": 50340,
+  "<|extratoken_85|>": 50341,
+  "<|extratoken_86|>": 50342,
+  "<|extratoken_87|>": 50343,
+  "<|extratoken_88|>": 50344,
+  "<|extratoken_89|>": 50345,
+  "<|extratoken_8|>": 50264,
+  "<|extratoken_90|>": 50346,
+  "<|extratoken_91|>": 50347,
+  "<|extratoken_92|>": 50348,
+  "<|extratoken_93|>": 50349,
+  "<|extratoken_94|>": 50350,
+  "<|extratoken_95|>": 50351,
+  "<|extratoken_96|>": 50352,
+  "<|extratoken_97|>": 50353,
+  "<|extratoken_98|>": 50354,
+  "<|extratoken_99|>": 50355,
+  "<|extratoken_9|>": 50265
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "pygmalion-6b",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 64,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 50400
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7051f5e264710f249c9358fbd7d361e95d7fee3549aceb75ba34866826491b0d
+size 1906275200

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7216ee6e1ea43d6e1800afc723b2f64f76dd4a4c1e28da2d07fee33f60825c24
+size 1900279852

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73801b6b857a7c2ceab5c723863d7bcc566ca96430ee208d25a40d9bab7f80a
+size 1967421507

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc963e1ed68790c7d5c1ad933a82d3b9bf3dad3cdd531410c101014388a34787
+size 1967421541

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860546d6e90abee8dc862f230387cee8cdde6c0af4138245b4986f302e02c22e
+size 1896093392

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c569daf4aabf9a7c14952798249ee38f829c1ec9368f867f8f137f81f0817
+size 1900279910

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f68ef3f4d1b9eb0a68a1d007c9b50654eee69cc0896f608f9ed401877ee4a53
+size 681471214

model.safetensors.index.json

@@ -0,0 +1,348 @@
+{
+  "metadata": {
+    "total_size": 12219206136
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00007-of-00007.safetensors",
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "transformer.h.0.attn.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.0.attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.0.attn.masked_bias": "model-00001-of-00007.safetensors",
+    "transformer.h.0.attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.0.attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.0.attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.0.mlp.fc_in.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.0.mlp.fc_in.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.0.mlp.fc_out.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.0.mlp.fc_out.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.1.attn.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.1.attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.1.attn.masked_bias": "model-00001-of-00007.safetensors",
+    "transformer.h.1.attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.1.attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.1.attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.1.mlp.fc_in.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.1.mlp.fc_in.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.1.mlp.fc_out.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.1.mlp.fc_out.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.10.attn.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.10.attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.10.attn.masked_bias": "model-00003-of-00007.safetensors",
+    "transformer.h.10.attn.out_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.10.attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.10.attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.10.mlp.fc_in.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.10.mlp.fc_in.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.10.mlp.fc_out.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.10.mlp.fc_out.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.11.attn.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.11.attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.11.attn.masked_bias": "model-00003-of-00007.safetensors",
+    "transformer.h.11.attn.out_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.11.attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.11.attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.11.mlp.fc_in.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.11.mlp.fc_in.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.11.mlp.fc_out.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.11.mlp.fc_out.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.12.attn.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.12.attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.12.attn.masked_bias": "model-00003-of-00007.safetensors",
+    "transformer.h.12.attn.out_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.12.attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.12.attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.12.mlp.fc_in.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.12.mlp.fc_in.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.12.mlp.fc_out.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.12.mlp.fc_out.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.13.attn.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.13.attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.13.attn.masked_bias": "model-00003-of-00007.safetensors",
+    "transformer.h.13.attn.out_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.13.attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.13.attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.13.mlp.fc_in.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.13.mlp.fc_in.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.13.mlp.fc_out.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.13.mlp.fc_out.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.14.attn.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.14.attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.14.attn.masked_bias": "model-00004-of-00007.safetensors",
+    "transformer.h.14.attn.out_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.14.attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.14.attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.14.mlp.fc_in.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.14.mlp.fc_in.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.14.mlp.fc_out.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.14.mlp.fc_out.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.15.attn.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.15.attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.15.attn.masked_bias": "model-00004-of-00007.safetensors",
+    "transformer.h.15.attn.out_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.15.attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.15.attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.15.mlp.fc_in.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.15.mlp.fc_in.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.15.mlp.fc_out.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.15.mlp.fc_out.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.16.attn.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.16.attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.16.attn.masked_bias": "model-00004-of-00007.safetensors",
+    "transformer.h.16.attn.out_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.16.attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.16.attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.16.mlp.fc_in.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.16.mlp.fc_in.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.16.mlp.fc_out.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.16.mlp.fc_out.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.17.attn.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.17.attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.17.attn.masked_bias": "model-00004-of-00007.safetensors",
+    "transformer.h.17.attn.out_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.17.attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.17.attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.17.mlp.fc_in.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.17.mlp.fc_in.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.17.mlp.fc_out.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.17.mlp.fc_out.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.18.attn.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.18.attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.18.attn.masked_bias": "model-00004-of-00007.safetensors",
+    "transformer.h.18.attn.out_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.18.attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.18.attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00004-of-00007.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00004-of-00007.safetensors",
+    "transformer.h.18.mlp.fc_in.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.18.mlp.fc_in.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.18.mlp.fc_out.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.18.mlp.fc_out.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.19.attn.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.19.attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.19.attn.masked_bias": "model-00005-of-00007.safetensors",
+    "transformer.h.19.attn.out_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.19.attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.19.attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.19.mlp.fc_in.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.19.mlp.fc_in.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.19.mlp.fc_out.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.19.mlp.fc_out.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.2.attn.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.2.attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.2.attn.masked_bias": "model-00001-of-00007.safetensors",
+    "transformer.h.2.attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.2.attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.2.attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.2.mlp.fc_in.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.2.mlp.fc_in.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.2.mlp.fc_out.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.2.mlp.fc_out.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.20.attn.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.20.attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.20.attn.masked_bias": "model-00005-of-00007.safetensors",
+    "transformer.h.20.attn.out_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.20.attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.20.attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.20.mlp.fc_in.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.20.mlp.fc_in.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.20.mlp.fc_out.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.20.mlp.fc_out.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.21.attn.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.21.attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.21.attn.masked_bias": "model-00005-of-00007.safetensors",
+    "transformer.h.21.attn.out_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.21.attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.21.attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.21.mlp.fc_in.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.21.mlp.fc_in.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.21.mlp.fc_out.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.21.mlp.fc_out.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.22.attn.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.22.attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.22.attn.masked_bias": "model-00005-of-00007.safetensors",
+    "transformer.h.22.attn.out_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.22.attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.22.attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.22.mlp.fc_in.bias": "model-00005-of-00007.safetensors",
+    "transformer.h.22.mlp.fc_in.weight": "model-00005-of-00007.safetensors",
+    "transformer.h.22.mlp.fc_out.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.22.mlp.fc_out.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.23.attn.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.23.attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.23.attn.masked_bias": "model-00006-of-00007.safetensors",
+    "transformer.h.23.attn.out_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.23.attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.23.attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.23.mlp.fc_in.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.23.mlp.fc_in.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.23.mlp.fc_out.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.23.mlp.fc_out.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.24.attn.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.24.attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.24.attn.masked_bias": "model-00006-of-00007.safetensors",
+    "transformer.h.24.attn.out_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.24.attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.24.attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.24.mlp.fc_in.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.24.mlp.fc_in.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.24.mlp.fc_out.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.24.mlp.fc_out.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.25.attn.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.25.attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.25.attn.masked_bias": "model-00006-of-00007.safetensors",
+    "transformer.h.25.attn.out_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.25.attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.25.attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.25.mlp.fc_in.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.25.mlp.fc_in.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.25.mlp.fc_out.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.25.mlp.fc_out.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.26.attn.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.26.attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.26.attn.masked_bias": "model-00006-of-00007.safetensors",
+    "transformer.h.26.attn.out_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.26.attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.26.attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.26.mlp.fc_in.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.26.mlp.fc_in.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.26.mlp.fc_out.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.26.mlp.fc_out.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.27.attn.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.27.attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.27.attn.masked_bias": "model-00006-of-00007.safetensors",
+    "transformer.h.27.attn.out_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.27.attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.27.attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00006-of-00007.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00006-of-00007.safetensors",
+    "transformer.h.27.mlp.fc_in.bias": "model-00007-of-00007.safetensors",
+    "transformer.h.27.mlp.fc_in.weight": "model-00007-of-00007.safetensors",
+    "transformer.h.27.mlp.fc_out.bias": "model-00007-of-00007.safetensors",
+    "transformer.h.27.mlp.fc_out.weight": "model-00007-of-00007.safetensors",
+    "transformer.h.3.attn.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.3.attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.3.attn.masked_bias": "model-00001-of-00007.safetensors",
+    "transformer.h.3.attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.3.attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.3.attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.3.mlp.fc_in.bias": "model-00001-of-00007.safetensors",
+    "transformer.h.3.mlp.fc_in.weight": "model-00001-of-00007.safetensors",
+    "transformer.h.3.mlp.fc_out.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.3.mlp.fc_out.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.4.attn.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.4.attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.4.attn.masked_bias": "model-00002-of-00007.safetensors",
+    "transformer.h.4.attn.out_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.4.attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.4.attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.4.mlp.fc_in.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.4.mlp.fc_in.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.4.mlp.fc_out.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.4.mlp.fc_out.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.5.attn.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.5.attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.5.attn.masked_bias": "model-00002-of-00007.safetensors",
+    "transformer.h.5.attn.out_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.5.attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.5.attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.5.mlp.fc_in.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.5.mlp.fc_in.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.5.mlp.fc_out.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.5.mlp.fc_out.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.6.attn.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.6.attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.6.attn.masked_bias": "model-00002-of-00007.safetensors",
+    "transformer.h.6.attn.out_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.6.attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.6.attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.6.mlp.fc_in.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.6.mlp.fc_in.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.6.mlp.fc_out.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.6.mlp.fc_out.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.7.attn.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.7.attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.7.attn.masked_bias": "model-00002-of-00007.safetensors",
+    "transformer.h.7.attn.out_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.7.attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.7.attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.7.mlp.fc_in.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.7.mlp.fc_in.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.7.mlp.fc_out.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.7.mlp.fc_out.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.8.attn.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.8.attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.8.attn.masked_bias": "model-00002-of-00007.safetensors",
+    "transformer.h.8.attn.out_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.8.attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.8.attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00002-of-00007.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00002-of-00007.safetensors",
+    "transformer.h.8.mlp.fc_in.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.8.mlp.fc_in.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.8.mlp.fc_out.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.8.mlp.fc_out.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.9.attn.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.9.attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.9.attn.masked_bias": "model-00003-of-00007.safetensors",
+    "transformer.h.9.attn.out_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.9.attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.9.attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.9.mlp.fc_in.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.9.mlp.fc_in.weight": "model-00003-of-00007.safetensors",
+    "transformer.h.9.mlp.fc_out.bias": "model-00003-of-00007.safetensors",
+    "transformer.h.9.mlp.fc_out.weight": "model-00003-of-00007.safetensors",
+    "transformer.ln_f.bias": "model-00007-of-00007.safetensors",
+    "transformer.ln_f.weight": "model-00007-of-00007.safetensors",
+    "transformer.wte.weight": "model-00001-of-00007.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "pygmalion-6b",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}