gi111f11cb7f354a74a8c123f5b155498e
/
NuExtract-1.5_a13714748337156096101495
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

first commit

This commit is contained in:
xxl 2024-11-25 11:05:17 +08:00
parent 0e25a5fb8d
commit 4b6317798c
19 changed files with 94220 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
10-20_long_context.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 173 KiB

BIN
8-10_long_context.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 146 KiB

189
README.md
View File

@ -1,3 +1,188 @@
# NuExtract-1.5_a13714748337156096101495 ---
license: mit
language:
- multilingual
tags:
- nlp
base_model: microsoft/Phi-3.5-mini-instruct
pipeline_tag: text-generation
inference: true
---
NuExtract-1.5 # NuExtract-v1.5 by NuMind 🔥
NuExtract-v1.5 is a fine-tuning of [Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct), trained on a private high-quality dataset for structured information extraction. It supports long documents and several languages (English, French, Spanish, German, Portuguese, and Italian).
To use the model, provide an input text and a JSON template describing the information you need to extract.
Note: This model is trained to prioritize pure extraction, so in most cases all text generated by the model is present as is in the original text.
Check out the [blog post](https://numind.ai/blog/nuextract-1-5---multilingual-infinite-context-still-small-and-better-than-gpt-4o).
Try it here: [Playground](https://huggingface.co/spaces/numind/NuExtract-v1.5)
We also provide a tiny (0.5B) version which is based on Qwen2.5-0.5B: [NuExtract-tiny-v1.5](https://huggingface.co/numind/NuExtract-tiny-v1.5)
⚠️ We recommend using NuExtract with a temperature at or very close to 0. Some inference frameworks, such as Ollama, use a default of 0.7 which is not well suited to pure extraction tasks.
## Benchmark
Zero-shot performance (English):
<p align="left">
<img src="english_bench.png" style="height: auto;">
</p>
Zero-shot performance (Multilingual):
<p align="left">
<img src="multilingual_bench.png" style="height: auto;">
</p>
Long documents (8-10k tokens):
<p align="left">
<img src="8-10_long_context.png" style="height: auto;">
</p>
Very long documents (10-20k tokens):
<p align="left">
<img src="10-20_long_context.png" style="height: auto;">
</p>
Few-shot fine-tuning:
<p align="left">
<img src="fewshot_bench.png" style="height: auto;">
</p>
## Usage
To use the model:
```python
import json
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
def predict_NuExtract(model, tokenizer, texts, template, batch_size=1, max_length=10_000, max_new_tokens=4_000):
template = json.dumps(json.loads(template), indent=4)
prompts = [f"""<|input|>\n### Template:\n{template}\n### Text:\n{text}\n\n<|output|>""" for text in texts]
outputs = []
with torch.no_grad():
for i in range(0, len(prompts), batch_size):
batch_prompts = prompts[i:i+batch_size]
batch_encodings = tokenizer(batch_prompts, return_tensors="pt", truncation=True, padding=True, max_length=max_length).to(model.device)
pred_ids = model.generate(**batch_encodings, max_new_tokens=max_new_tokens)
outputs += tokenizer.batch_decode(pred_ids, skip_special_tokens=True)
return [output.split("<|output|>")[1] for output in outputs]
model_name = "numind/NuExtract-v1.5"
device = "cuda"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True).to(device).eval()
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
text = """We introduce Mistral 7B, a 7–billion-parameter language model engineered for
superior performance and efficiency. Mistral 7B outperforms the best open 13B
model (Llama 2) across all evaluated benchmarks, and the best released 34B
model (Llama 1) in reasoning, mathematics, and code generation. Our model
leverages grouped-query attention (GQA) for faster inference, coupled with sliding
window attention (SWA) to effectively handle sequences of arbitrary length with a
reduced inference cost. We also provide a model fine-tuned to follow instructions,
Mistral 7B – Instruct, that surpasses Llama 2 13B – chat model both on human and
automated benchmarks. Our models are released under the Apache 2.0 license.
Code: <https://github.com/mistralai/mistral-src>
Webpage: <https://mistral.ai/news/announcing-mistral-7b/>"""
template = """{
"Model": {
"Name": "",
"Number of parameters": "",
"Number of max token": "",
"Architecture": []
},
"Usage": {
"Use case": [],
"Licence": ""
}
}"""
prediction = predict_NuExtract(model, tokenizer, [text], template)[0]
print(prediction)
```
Sliding window prompting:
```python
import json
MAX_INPUT_SIZE = 20_000
MAX_NEW_TOKENS = 6000
def clean_json_text(text):
text = text.strip()
text = text.replace("\#", "#").replace("\&", "&")
return text
def predict_chunk(text, template, current, model, tokenizer):
current = clean_json_text(current)
input_llm = f"<|input|>\n### Template:\n{template}\n### Current:\n{current}\n### Text:\n{text}\n\n<|output|>" + "{"
input_ids = tokenizer(input_llm, return_tensors="pt", truncation=True, max_length=MAX_INPUT_SIZE).to("cuda")
output = tokenizer.decode(model.generate(**input_ids, max_new_tokens=MAX_NEW_TOKENS)[0], skip_special_tokens=True)
return clean_json_text(output.split("<|output|>")[1])
def split_document(document, window_size, overlap):
tokens = tokenizer.tokenize(document)
print(f"\tLength of document: {len(tokens)} tokens")
chunks = []
if len(tokens) > window_size:
for i in range(0, len(tokens), window_size-overlap):
print(f"\t{i} to {i + len(tokens[i:i + window_size])}")
chunk = tokenizer.convert_tokens_to_string(tokens[i:i + window_size])
chunks.append(chunk)
if i + len(tokens[i:i + window_size]) >= len(tokens):
break
else:
chunks.append(document)
print(f"\tSplit into {len(chunks)} chunks")
return chunks
def handle_broken_output(pred, prev):
try:
if all([(v in ["", []]) for v in json.loads(pred).values()]):
# if empty json, return previous
pred = prev
except:
# if broken json, return previous
pred = prev
return pred
def sliding_window_prediction(text, template, model, tokenizer, window_size=4000, overlap=128):
# split text into chunks of n tokens
tokens = tokenizer.tokenize(text)
chunks = split_document(text, window_size, overlap)
# iterate over text chunks
prev = template
for i, chunk in enumerate(chunks):
print(f"Processing chunk {i}...")
pred = predict_chunk(chunk, template, prev, model, tokenizer)
# handle broken output
pred = handle_broken_output(pred, prev)
# iterate
prev = pred
return pred
```

138
config.json Normal file
View File

@ -0,0 +1,138 @@
{
"_name_or_path": "numind/NuExtract-v1.5",
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "microsoft/Phi-3.5-mini-instruct--configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "microsoft/Phi-3.5-mini-instruct--modeling_phi3.Phi3ForCausalLM"
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"model_type": "phi3",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"original_max_position_embeddings": 4096,
"pad_token_id": 32000,
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"long_factor": [
1.0800000429153442,
1.1100000143051147,
1.1399999856948853,
1.340000033378601,
1.5899999141693115,
1.600000023841858,
1.6200000047683716,
2.620000123977661,
3.2300000190734863,
3.2300000190734863,
4.789999961853027,
7.400000095367432,
7.700000286102295,
9.09000015258789,
12.199999809265137,
17.670000076293945,
24.46000099182129,
28.57000160217285,
30.420001983642578,
30.840002059936523,
32.590003967285156,
32.93000411987305,
42.320003509521484,
44.96000289916992,
50.340003967285156,
50.45000457763672,
57.55000305175781,
57.93000411987305,
58.21000289916992,
60.1400032043457,
62.61000442504883,
62.62000274658203,
62.71000289916992,
63.1400032043457,
63.1400032043457,
63.77000427246094,
63.93000411987305,
63.96000289916992,
63.970001220703125,
64.02999877929688,
64.06999969482422,
64.08000183105469,
64.12000274658203,
64.41000366210938,
64.4800033569336,
64.51000213623047,
64.52999877929688,
64.83999633789062
],
"short_factor": [
1.0,
1.0199999809265137,
1.0299999713897705,
1.0299999713897705,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0699999332427979,
1.0999999046325684,
1.1099998950958252,
1.1599998474121094,
1.1599998474121094,
1.1699998378753662,
1.2899998426437378,
1.339999794960022,
1.679999828338623,
1.7899998426437378,
1.8199998140335083,
1.8499997854232788,
1.8799997568130493,
1.9099997282028198,
1.9399996995925903,
1.9899996519088745,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0199997425079346,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0299997329711914,
2.0799996852874756,
2.0899996757507324,
2.189999580383301,
2.2199995517730713,
2.5899994373321533,
2.729999542236328,
2.749999523162842,
2.8399994373321533
],
"type": "longrope"
},
"rope_theta": 10000.0,
"sliding_window": 262144,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.0",
"use_cache": true,
"vocab_size": 32064
}

1
configuration.json Normal file
View File

@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

BIN
english_bench.pdf Normal file
View File

Binary file not shown.

BIN
english_bench.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 125 KiB

BIN
fewshot_bench.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 148 KiB

BIN
finetuned_gains.pdf Normal file
View File

Binary file not shown.

7
generation_config.json Normal file
View File

@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 32000,
"pad_token_id": 32000,
"transformers_version": "4.44.0"
}

37
handler.py Normal file
View File

@ -0,0 +1,37 @@
from typing import Dict, List, Any
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import os
MAX_INPUT_SIZE = 10_000
MAX_NEW_TOKENS = 4_000
def clean_json_text(text):
"""
Cleans JSON text by removing leading/trailing whitespace and escaping special characters.
"""
text = text.strip()
text = text.replace("\#", "#").replace("\&", "&")
return text
class EndpointHandler:
def __init__(self, path=""):
# load model and processor from path
self.model = AutoModelForCausalLM.from_pretrained(path,
trust_remote_code=True,
torch_dtype=torch.bfloat16,
device_map="auto")
self.model.eval()
self.tokenizer = AutoTokenizer.from_pretrained(path)
def __call__(self, data: Dict[str, Any]) -> str:
data = data.pop("inputs")
template = data.pop("template")
text = data.pop("text")
input_llm = f"<|input|>\n### Template:\n{template}\n### Text:\n{text}\n\n<|output|>" + "{"
input_ids = self.tokenizer(input_llm, return_tensors="pt", truncation=True, max_length=MAX_INPUT_SIZE).to("cuda")
output = self.tokenizer.decode(self.model.generate(**input_ids, max_new_tokens=MAX_NEW_TOKENS)[0], skip_special_tokens=True)
return clean_json_text(output.split("<|output|>")[1])

BIN
model-00001-of-00002.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

BIN
model-00002-of-00002.safetensors (Stored with Git LFS) Normal file
View File

Binary file not shown.

202
model.safetensors.index.json Normal file
View File

@ -0,0 +1,202 @@
{
"metadata": {
"total_size": 7642159104
},
"weight_map": {
"lm_head.weight": "model-00002-of-00002.safetensors",
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
"model.norm.weight": "model-00002-of-00002.safetensors"
}
}

BIN
multilingual_bench.pdf Normal file
View File

Binary file not shown.

BIN
multilingual_bench.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 102 KiB

30
special_tokens_map.json Normal file
View File

@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

93475
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

137
tokenizer_config.json Normal file
View File

@ -0,0 +1,137 @@
{
"add_bos_token": false,
"add_eos_token": false,
"add_prefix_space": null,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"32000": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32002": {
"content": "<|placeholder1|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32003": {
"content": "<|placeholder2|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32004": {
"content": "<|placeholder3|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32005": {
"content": "<|placeholder4|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32006": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32007": {
"content": "<|end|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32008": {
"content": "<|placeholder5|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32009": {
"content": "<|placeholder6|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32010": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": false,
"max_length": 4000,
"model_max_length": 131072,
"pad_to_multiple_of": null,
"pad_token": "<|endoftext|>",
"pad_token_type_id": 0,
"padding_side": "left",
"sp_model_kwargs": {},
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": false
}