初始化项目，由ModelHub XC社区提供模型

Model: OpenAssistant/stablelm-7b-sft-v7-epoch-3
Source: Original Platform

.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

README.md

@@ -0,0 +1,152 @@
+---
+language:
+- en
+tags:
+- sft
+pipeline_tag: text-generation
+widget:
+- text: >-
+    <|prompter|>What is a meme, and what's the history behind this
+    word?<|endoftext|><|assistant|>
+- text: <|prompter|>What's the Earth total population<|endoftext|><|assistant|>
+- text: >-
+    <|prompter|>Write a story about future of AI
+    development<|endoftext|><|assistant|>
+---
+
+# Open-Assistant StableLM-7B SFT-7 Model
+
+
+This is the 7th iteration English supervised-fine-tuning (SFT) model of 
+the [Open-Assistant](https://github.com/LAION-AI/Open-Assistant) project. 
+It is based on a StableLM 7B that was fine-tuned on human demonstrations 
+of assistant conversations collected through the 
+[https://open-assistant.io/](https://open-assistant.io/) human feedback web 
+app before April 12, 2023. 
+
+## Model Details
+
+- **Developed by:** [Open-Assistant Contributors](https://open-assistant.io/)
+- **Model type:** Transformer-based Language Model
+- **Language:** English
+- **Finetuned from:** [stabilityai/stablelm-base-alpha-7b](https://huggingface.co/stabilityai/stablelm-base-alpha-7b)
+- **Code:** [Open-Assistant/model/model_training](https://github.com/LAION-AI/Open-Assistant/tree/main/model/model_training)
+- **Demo:** TODO
+- **License:** Creative Commons license ([CC BY-SA-4.0](https://creativecommons.org/licenses/by-sa/4.0/))
+- **Contact:** [Open-Assistant Discord](https://ykilcher.com/open-assistant-discord)
+
+## Prompting
+
+Two special tokens are used to mark the beginning of user and assistant turns:
+`<|prompter|>` and `<|assistant|>`. Each turn ends with a `<|endoftext|>` token.
+
+Input prompt example:
+```
+<|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>
+```
+The input ends with the `<|assistant|>` token to signal that the model should 
+start generating the assistant reply.
+
+
+## Dev Details
+
+- wandb: https://wandb.ai/open-assistant/supervised-finetuning/runs/08dfhyuc
+- base model: [stabilityai/stablelm-base-alpha-7b](https://huggingface.co/stabilityai/stablelm-base-alpha-7b)
+- checkpoint: 3 epochs (12000 steps)
+
+command: `deepspeed trainer_sft.py --configs defaults stablelm-7b oasst-mix --cache_dir /home/ubuntu/data_cache --output_dir .saved/stable-lm-7b-1 --num_train_epochs 4 --deepspeed`
+
+data:
+```
+oasst-mix:
+  save_strategy: epoch
+  sort_by_length: false
+  use_custom_sampler: false
+  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
+    - 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
+```
+
+
+stablelm:
+```
+stablelm-7b:
+  dtype: fp16
+  log_dir: stablelm_log_7b
+  model_name: stabilityai/stablelm-base-alpha-7b
+  output_dir: stablelm_7b
+  max_length: 4096
+  warmup_steps: 100
+  gradient_checkpointing: true
+  gradient_accumulation_steps: 2
+  per_device_train_batch_size: 4
+  per_device_eval_batch_size: 4
+  eval_steps: 100
+  save_steps: 500
+  num_train_epochs: 4
+  save_total_limit: 4
+  use_flash_attention: true
+```
+
+zero config:
+```
+{
+  "fp16": {
+    "enabled": "auto",
+    "loss_scale": 0,
+    "loss_scale_window": 1000,
+    "initial_scale_power": 16,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },
+  "bf16": {
+    "enabled": "auto"
+  },
+  "optimizer": {
+    "type": "AdamW",
+    "params": {
+      "lr": "auto",
+      "betas": "auto",
+      "eps": "auto",
+      "weight_decay": "auto"
+    }
+  },
+  "scheduler": {
+    "type": "WarmupDecayLR",
+    "params": {
+      "warmup_min_lr": "auto",
+      "warmup_max_lr": "auto",
+      "warmup_num_steps": "auto",
+      "total_num_steps": "auto"
+    }
+  },
+  "zero_optimization": {
+    "stage": 2,
+    "allgather_partitions": true,
+    "allgather_bucket_size": 1e9,
+    "overlap_comm": false,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 1e9,
+    "contiguous_gradients": true
+  },
+  "gradient_accumulation_steps": "auto",
+  "gradient_clipping": "auto",
+  "steps_per_print": 2000,
+  "train_batch_size": "auto",
+  "train_micro_batch_size_per_gpu": "auto",
+  "wall_clock_breakdown": false
+}
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": ".saved/stablelm-7b-sft-1/checkpoint-12099/",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 16,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50288
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69db4ceb2f7d9e4d5a80c34f200947b725961d33658015e9a3a1c498bb28c70
+size 10090416843

pytorch_model-00001-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f551ef92f008bcdcbd94289368db87024cbf4d611a29725e52e4d498522fe5
+size 1859720245

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e4496bdc8fefb303537120260915392669240cf64dbcf10ce1ba8f7666ca26
+size 5912076499

pytorch_model-00002-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57c91a0bdf23623a314c1231aeee71002ba013d680ed0f8a497e3eed91e9e18
+size 1845823467

pytorch_model-00003-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ae570934ed7628c7884491c1fff575c300028f0e6f5a2e58d97c23cbf95e0d
+size 1845823467

pytorch_model-00004-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e902a63e05d4aef4877a4771215ca7c11338bda70a91b747cb962c46546be26d
+size 1845823467

pytorch_model-00005-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce421c8c043104b2db1f0abde2431eab38157cbb1e7fb5fd3e6149f22c13095d
+size 1845823467

pytorch_model-00006-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6175459db55cc3b28521cb57410add83e7dec96184e37b1447c0e2c4031b442
+size 1845823467

pytorch_model-00007-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66a89786816afd46f0a1d1ee394af9ff30ed60d3ac9e4eb436c261b8c020eb6
+size 1845823467

pytorch_model-00008-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da6a21f316725a9b36a0bdd145ce509eabff1e97c8d8c6f724705e650ece3d7
+size 1845823467

pytorch_model-00009-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa949b42f8d0b77ddc2b8f729a2583b3c33cc67896510082f70f2f4f82ca55d1
+size 1222007504

pytorch_model.bin.index.json

@@ -0,0 +1,251 @@
+{
+  "metadata": {
+    "total_size": 15767528480.0
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.10.attention.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.12.attention.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.2.attention.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.4.attention.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.6.attention.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.8.attention.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|prefix_end|>",
+    "<|prefix_begin|>",
+    "<|assistant|>",
+    "<|prompter|>",
+    "<|system|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|padding|>",
+  "sep_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "special_tokens_map_file": "/home/ubuntu/data_cache/models--stabilityai--stablelm-base-alpha-7b/snapshots/1ef4c0039ec2dd491814bd0dbbb8293bda9d8aa1/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}