initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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 +1,155 @@
+---
+license: llama2
+inference:
+ parameters:
+ do_sample: false
+ max_length: 200
+widget:
+- text: "CREATE TABLE stadium (\n stadium_id number,\n location text,\n name text,\n capacity number,\n)\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- how many stadiums in total?\n\nSELECT"
+ example_title: "Number stadiums"
+- text: "CREATE TABLE work_orders ( ID NUMBER, CREATED_AT TEXT, COST FLOAT, INVOICE_AMOUNT FLOAT, IS_DUE BOOLEAN, IS_OPEN BOOLEAN, IS_OVERDUE BOOLEAN, COUNTRY_NAME TEXT, )\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- how many work orders are open?\n\nSELECT"
+ example_title: "Open work orders"
+- text: "CREATE TABLE stadium ( stadium_id number, location text, name text, capacity number, highest number, lowest number, average number )\n\nCREATE TABLE singer ( singer_id number, name text, country text, song_name text, song_release_year text, age number, is_male others )\n\nCREATE TABLE concert ( concert_id number, concert_name text, theme text, stadium_id text, year text )\n\nCREATE TABLE singer_in_concert ( concert_id number, singer_id text )\n\n-- Using valid SQLite, answer the following questions for the tables provided above.\n\n-- What is the maximum, the average, and the minimum capacity of stadiums ?\n\nSELECT"
+ example_title: "Stadium capacity"
+---
+
+# NSQL-Llama-2-7B
+
+## Model Description
+
+NSQL is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks.
+
+In this repository we are introducing a new member of NSQL, NSQL-Llama-2-7B. It's based on Meta's original [Llama-2 7B model](https://huggingface.co/meta-llama/Llama-2-7b) and further pre-trained on a dataset of general SQL queries and then fine-tuned on a dataset composed of text-to-SQL pairs.
+
+## Training Data
+
+The general SQL queries are the SQL subset from [The Stack](https://huggingface.co/datasets/bigcode/the-stack), containing 1M training samples. The labeled text-to-SQL pairs come from more than 20 public sources across the web from standard datasets. We hold out Spider and GeoQuery datasets for use in evaluation.
+
+## Evaluation Data
+
+We evaluate our models on two text-to-SQL benchmarks: Spider and GeoQuery.
+
+## Training Procedure
+
+NSQL was trained using cross-entropy loss to maximize the likelihood of sequential inputs. For finetuning on text-to-SQL pairs, we only compute the loss over the SQL portion of the pair. The model is trained using 80GB A100s, leveraging data and model parallelism. We pre-trained for 3 epochs and fine-tuned for 10 epochs.
+
+## Intended Use and Limitations
+
+The model was designed for text-to-SQL generation tasks from given table schema and natural language prompts. The model works best with the prompt format defined below and outputting `SELECT` queries.
+
+## How to Use
+
+Example 1:
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-llama-2-7B")
+model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-llama-2-7B", torch_dtype=torch.bfloat16)
+
+text = """CREATE TABLE stadium (
+ stadium_id number,
+ location text,
+ name text,
+ capacity number,
+ highest number,
+ lowest number,
+ average number
+)
+
+CREATE TABLE singer (
+ singer_id number,
+ name text,
+ country text,
+ song_name text,
+ song_release_year text,
+ age number,
+ is_male others
+)
+
+CREATE TABLE concert (
+ concert_id number,
+ concert_name text,
+ theme text,
+ stadium_id text,
+ year text
+)
+
+CREATE TABLE singer_in_concert (
+ concert_id number,
+ singer_id text
+)
+
+-- Using valid SQLite, answer the following questions for the tables provided above.
+
+-- What is the maximum, the average, and the minimum capacity of stadiums ?
+
+SELECT"""
+
+input_ids = tokenizer(text, return_tensors="pt").input_ids
+
+generated_ids = model.generate(input_ids, max_length=500)
+print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
+```
+
+Example 2:
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-llama-2-7B")
+model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-llama-2-7B", torch_dtype=torch.bfloat16)
+
+text = """CREATE TABLE stadium (
+ stadium_id number,
+ location text,
+ name text,
+ capacity number,
+)
+
+-- Using valid SQLite, answer the following questions for the tables provided above.
+
+-- how many stadiums in total?
+
+SELECT"""
+
+input_ids = tokenizer(text, return_tensors="pt").input_ids
+
+generated_ids = model.generate(input_ids, max_length=500)
+print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
+```
+
+Example 3:
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-llama-2-7B")
+model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-llama-2-7B", torch_dtype=torch.bfloat16)
+
+text = """CREATE TABLE work_orders (
+ ID NUMBER,
+ CREATED_AT TEXT,
+ COST FLOAT,
+ INVOICE_AMOUNT FLOAT,
+ IS_DUE BOOLEAN,
+ IS_OPEN BOOLEAN,
+ IS_OVERDUE BOOLEAN,
+ COUNTRY_NAME TEXT,
+)
+
+-- Using valid SQLite, answer the following questions for the tables provided above.
+
+-- how many work orders are open?
+
+SELECT"""
+
+input_ids = tokenizer(text, return_tensors="pt").input_ids
+
+generated_ids = model.generate(input_ids, max_length=500)
+print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
+```
+
+
+
+For more information (e.g., run with your local database), please find examples in [this repository](https://github.com/NumbersStationAI/NSQL).

config.json

@@ -0,0 +1,26 @@
+{
+ "_name_or_path": "nsql-llama-2-7B",
+ "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": 4096,
+ "model_type": "llama",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 32,
+ "pad_token_id": 2,
+ "pretraining_tp": 1,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.31.0",
+ "use_cache": true,
+ "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "max_length": 4096,
+ "pad_token_id": 0,
+ "temperature": 0.9,
+ "top_p": 0.6,
+ "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a62bdab6b9cd883f6e6c1bb14b8fcc1096f679df3cc639768868e33fc377d6
+size 9877989586

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d58d64c7cdd18dc0a397894e3715f16f1b49429669cf07dd20072583d83cf4b
+size 9894801014

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66a4a67ca594a373effd9112120d83b3d12bf66d27ab9a46f7ace4d113cb3fd
+size 7180990649

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+ "metadata": {
+ "total_size": 26953670656
+ },
+ "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-00003-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-00002-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"
+ }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+ "bos_token": {
+ "__type": "AddedToken",
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "clean_up_tokenization_spaces": false,
+ "eos_token": {
+ "__type": "AddedToken",
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "legacy": false,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": null,
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}