Commit
•
02ca93d
1
Parent(s):
5ff6deb
Upload folder using huggingface_hub
Browse files- README.md +97 -0
- added_tokens.json +14 -0
- config.json +46 -0
- generation_config.json +13 -0
- model.safetensors.index.json +202 -0
- output.safetensors +3 -0
- result.png +0 -0
- result_ft.png +0 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +138 -0
README.md
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
---
|
6 |
+
# Structure Extraction Model by NuMind 🔥
|
7 |
+
|
8 |
+
NuExtract is a version of [phi-3-mini](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct), fine-tuned on a private high-quality synthetic dataset for information extraction.
|
9 |
+
To use the model, provide an input text (less than 2000 tokens) and a JSON template describing the information you need to extract.
|
10 |
+
|
11 |
+
Note: This model is purely extractive, so all text output by the model is present as is in the original text. You can also provide an example of output formatting to help the model understand your task more precisely.
|
12 |
+
|
13 |
+
Try it here: https://huggingface.co/spaces/numind/NuExtract
|
14 |
+
|
15 |
+
We also provide a tiny(0.5B) and large(7B) version of this model: [NuExtract-tiny](https://huggingface.co/numind/NuExtract-tiny) and [NuExtract-large](https://huggingface.co/numind/NuExtract-large)
|
16 |
+
|
17 |
+
**Checkout other models by NuMind:**
|
18 |
+
* SOTA Zero-shot NER Model [NuNER Zero](https://huggingface.co/numind/NuNER_Zero)
|
19 |
+
* SOTA Multilingual Entity Recognition Foundation Model: [link](https://huggingface.co/numind/entity-recognition-multilingual-general-sota-v1)
|
20 |
+
* SOTA Sentiment Analysis Foundation Model: [English](https://huggingface.co/numind/generic-sentiment-v1), [Multilingual](https://huggingface.co/numind/generic-sentiment-multi-v1)
|
21 |
+
|
22 |
+
|
23 |
+
## Benchmark
|
24 |
+
|
25 |
+
Benchmark 0 shot (will release soon):
|
26 |
+
|
27 |
+
<p align="left">
|
28 |
+
<img src="result.png" width="600">
|
29 |
+
</p>
|
30 |
+
|
31 |
+
Benchmark fine-tunning (see blog post):
|
32 |
+
|
33 |
+
<p align="left">
|
34 |
+
<img src="result_ft.png" width="600">
|
35 |
+
</p>
|
36 |
+
|
37 |
+
|
38 |
+
## Usage
|
39 |
+
|
40 |
+
To use the model:
|
41 |
+
|
42 |
+
```python
|
43 |
+
import json
|
44 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
45 |
+
|
46 |
+
|
47 |
+
def predict_NuExtract(model, tokenizer, text, schema, example=["", "", ""]):
|
48 |
+
schema = json.dumps(json.loads(schema), indent=4)
|
49 |
+
input_llm = "<|input|>\n### Template:\n" + schema + "\n"
|
50 |
+
for i in example:
|
51 |
+
if i != "":
|
52 |
+
input_llm += "### Example:\n"+ json.dumps(json.loads(i), indent=4)+"\n"
|
53 |
+
|
54 |
+
input_llm += "### Text:\n"+text +"\n<|output|>\n"
|
55 |
+
input_ids = tokenizer(input_llm, return_tensors="pt",truncation = True, max_length=4000).to("cuda")
|
56 |
+
|
57 |
+
output = tokenizer.decode(model.generate(**input_ids)[0], skip_special_tokens=True)
|
58 |
+
return output.split("<|output|>")[1].split("<|end-output|>")[0]
|
59 |
+
|
60 |
+
|
61 |
+
# We recommend using bf16 as it results in negligable performance loss
|
62 |
+
model = AutoModelForCausalLM.from_pretrained("numind/NuExtract", torch_dtype=torch.bfloat16, trust_remote_code=True)
|
63 |
+
tokenizer = AutoTokenizer.from_pretrained("numind/NuExtract", trust_remote_code=True)
|
64 |
+
|
65 |
+
model.to("cuda")
|
66 |
+
|
67 |
+
model.eval()
|
68 |
+
|
69 |
+
text = """We introduce Mistral 7B, a 7–billion-parameter language model engineered for
|
70 |
+
superior performance and efficiency. Mistral 7B outperforms the best open 13B
|
71 |
+
model (Llama 2) across all evaluated benchmarks, and the best released 34B
|
72 |
+
model (Llama 1) in reasoning, mathematics, and code generation. Our model
|
73 |
+
leverages grouped-query attention (GQA) for faster inference, coupled with sliding
|
74 |
+
window attention (SWA) to effectively handle sequences of arbitrary length with a
|
75 |
+
reduced inference cost. We also provide a model fine-tuned to follow instructions,
|
76 |
+
Mistral 7B – Instruct, that surpasses Llama 2 13B – chat model both on human and
|
77 |
+
automated benchmarks. Our models are released under the Apache 2.0 license.
|
78 |
+
Code: https://github.com/mistralai/mistral-src
|
79 |
+
Webpage: https://mistral.ai/news/announcing-mistral-7b/"""
|
80 |
+
|
81 |
+
schema = """{
|
82 |
+
"Model": {
|
83 |
+
"Name": "",
|
84 |
+
"Number of parameters": "",
|
85 |
+
"Number of max token": "",
|
86 |
+
"Architecture": []
|
87 |
+
},
|
88 |
+
"Usage": {
|
89 |
+
"Use case": [],
|
90 |
+
"Licence": ""
|
91 |
+
}
|
92 |
+
}"""
|
93 |
+
|
94 |
+
prediction = predict_NuExtract(model, tokenizer, text, schema, example=["","",""])
|
95 |
+
print(prediction)
|
96 |
+
|
97 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|end-output|>": 32011,
|
4 |
+
"<|endoftext|>": 32000,
|
5 |
+
"<|end|>": 32007,
|
6 |
+
"<|placeholder1|>": 32002,
|
7 |
+
"<|placeholder2|>": 32003,
|
8 |
+
"<|placeholder3|>": 32004,
|
9 |
+
"<|placeholder4|>": 32005,
|
10 |
+
"<|placeholder5|>": 32008,
|
11 |
+
"<|placeholder6|>": 32009,
|
12 |
+
"<|system|>": 32006,
|
13 |
+
"<|user|>": 32010
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
|
9 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": 32000,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 3072,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 8192,
|
18 |
+
"max_position_embeddings": 4096,
|
19 |
+
"model_type": "phi3",
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"original_max_position_embeddings": 4096,
|
24 |
+
"pad_token_id": 32000,
|
25 |
+
"resid_pdrop": 0.0,
|
26 |
+
"rms_norm_eps": 1e-05,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"sliding_window": 2047,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.42.0.dev0",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 32064,
|
35 |
+
"quantization_config": {
|
36 |
+
"quant_method": "exl2",
|
37 |
+
"version": "0.1.6",
|
38 |
+
"bits": 3.0,
|
39 |
+
"head_bits": 6,
|
40 |
+
"calibration": {
|
41 |
+
"rows": 115,
|
42 |
+
"length": 2048,
|
43 |
+
"dataset": "(default)"
|
44 |
+
}
|
45 |
+
}
|
46 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": [
|
5 |
+
32000,
|
6 |
+
32001,
|
7 |
+
32007,
|
8 |
+
32011
|
9 |
+
],
|
10 |
+
"pad_token_id": 32000,
|
11 |
+
"transformers_version": "4.42.0.dev0",
|
12 |
+
"max_new_tokens": 2000
|
13 |
+
}
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 15284318208
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
21 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
22 |
+
"model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
23 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
24 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
26 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
27 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
28 |
+
"model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
29 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
30 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
31 |
+
"model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
32 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.15.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
71 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
72 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
73 |
+
"model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
74 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
75 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
80 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
81 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
82 |
+
"model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
83 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
84 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
85 |
+
"model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
|
86 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
87 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
88 |
+
"model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
89 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
90 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
91 |
+
"model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
|
92 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
93 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
94 |
+
"model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
95 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
96 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
97 |
+
"model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
98 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
99 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
100 |
+
"model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
101 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
102 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
103 |
+
"model.layers.22.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
104 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
105 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
106 |
+
"model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
107 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
108 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
109 |
+
"model.layers.23.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
110 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
111 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
112 |
+
"model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
113 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
114 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
115 |
+
"model.layers.24.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
116 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
117 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
118 |
+
"model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
119 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
120 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
121 |
+
"model.layers.25.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
122 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
123 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
124 |
+
"model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
125 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
126 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
127 |
+
"model.layers.26.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
128 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
131 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
132 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
133 |
+
"model.layers.27.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
134 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
135 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
136 |
+
"model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
137 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
138 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
139 |
+
"model.layers.28.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
140 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.29.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
147 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
148 |
+
"model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
149 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
150 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
151 |
+
"model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
|
152 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
153 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
154 |
+
"model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
155 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
156 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
157 |
+
"model.layers.30.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
158 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
159 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
160 |
+
"model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
161 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
162 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
163 |
+
"model.layers.31.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
|
164 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
165 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
166 |
+
"model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
167 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
168 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
169 |
+
"model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
|
170 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
171 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
172 |
+
"model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
173 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
174 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
175 |
+
"model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
|
176 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
177 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
178 |
+
"model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
179 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
180 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
181 |
+
"model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
|
182 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
183 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
184 |
+
"model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
185 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
186 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
187 |
+
"model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
|
188 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
189 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
190 |
+
"model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
191 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
192 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
193 |
+
"model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
|
194 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
195 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
196 |
+
"model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
197 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
198 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
199 |
+
"model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
|
200 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
201 |
+
}
|
202 |
+
}
|
output.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6028e8e1414e81e80bf1f204381c263b0a0d4bb4f18090d77977108c4130a6b
|
3 |
+
size 1633112580
|
result.png
ADDED
![]() |
result_ft.png
ADDED
![]() |
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"32011": {
|
118 |
+
"content": "<|end-output|>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": true,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
}
|
125 |
+
},
|
126 |
+
"bos_token": "<s>",
|
127 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
128 |
+
"clean_up_tokenization_spaces": false,
|
129 |
+
"eos_token": "<|endoftext|>",
|
130 |
+
"legacy": false,
|
131 |
+
"model_max_length": 4096,
|
132 |
+
"pad_token": "<|end-output|>",
|
133 |
+
"padding_side": "left",
|
134 |
+
"sp_model_kwargs": {},
|
135 |
+
"tokenizer_class": "LlamaTokenizer",
|
136 |
+
"unk_token": "<unk>",
|
137 |
+
"use_default_system_prompt": false
|
138 |
+
}
|