sync with main branch

.gitattributes

@@ -32,3 +32,14 @@ saved_model/**/* 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
+added_tokens.json filter=lfs diff=lfs merge=lfs -text
+config.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin.index.json filter=lfs diff=lfs merge=lfs -text
+README.md filter=lfs diff=lfs merge=lfs -text
+special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
+tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
+generation_config.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,25 +1,3 @@
----
-license: cc-by-nc-4.0
----
-
-### Stanford Alpaca-7B
-
-This repo hosts the weight diff for [Stanford Alpaca-7B](https://github.com/tatsu-lab/stanford_alpaca/) that can be used to reconstruct the original model weights when applied to Meta's LLaMA weights. 
-
-To recover the original Alpaca-7B weights, follow these steps:
-```text
-1. Convert Meta's released weights into huggingface format. Follow this guide:
-    https://huggingface.co/docs/transformers/main/model_doc/llama
-2. Make sure you cloned the released weight diff into your local machine. The weight diff is located at:
-    https://huggingface.co/tatsu-lab/alpaca-7b/tree/main
-3. Run this function with the correct paths. E.g.,
-    python weight_diff.py recover --path_raw <path_to_step_1_dir> --path_diff <path_to_step_2_dir> --path_tuned <path_to_store_recovered_weights>
-```
-
-Once step 3 completes, you should have a directory with the recovered weights, from which you can load the model like the following
-
-```python
-import transformers
-alpaca_model = transformers.AutoModelForCausalLM.from_pretrained("<path_to_store_recovered_weights>")
-alpaca_tokenizer = transformers.AutoTokenizer.from_pretrained("<path_to_store_recovered_weights>")
-```
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17913b0f97b6c92903cbf2c6d8ff9e412644769ba8ea848fd4dc4246a38c8d0
+size 1205

added_tokens.json

@@ -1,3 +1,3 @@
-{
-  "[PAD]": 32000
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e3ca5df2973756aa612cb17246ef6020a68ff8d94671508987d373642f7a36
+size 21

config.json

@@ -1,23 +1,3 @@
-{
-  "_name_or_path": "/juice5/scr5/nlp/crfm/human-feedback/models/selfinstruct/sft_v6_52k_llama_7b_regen_v7_3ep",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "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,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-06,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.28.0.dev0",
-  "use_cache": true,
-  "vocab_size": 32001
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e67c7ad4d82c2401d65e60e215aa007776c83ae7b42137b3e59fa5e4bf3fb1a
+size 619

generation_config.json

@@ -1,7 +1,3 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 0,
-  "transformers_version": "4.28.0.dev0"
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7ff399e5568cc21a0a8414f43df88ef7c424995b9b97a90563165d2cf79efd
+size 137

pytorch_model.bin.index.json

@@ -1,330 +1,3 @@
-{
-  "metadata": {
-    "total_size": 26953703424
-  },
-  "weight_map": {
-    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
-    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8865cf1c09c5f82fce56838736fed80a20ecebec9e7bb3c44eeea5c787ec43
+size 26788

special_tokens_map.json

@@ -1,24 +1,3 @@
-{
-  "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
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bfb6b77704f7d25dae2ad9be51d2703a093d829e71f39da83fb04b731ba79d1
+size 435

tokenizer_config.json

@@ -1,35 +1,3 @@
-{
-  "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": {},
-  "special_tokens_map_file": "/juice5/scr5/nlp/llama_model/llama_hf_latest/llama-7b/special_tokens_map.json",
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:e471461479d8cb4193f06f6bae5e852502211d17417f5cd2a8e702ed0e1f525e
+size 836