初始化项目，由ModelHub XC社区提供模型
Model: ragraph-ai/stable-cypher-instruct-3b Source: Original Platform
This commit is contained in:
ModelHub XC
39
.gitattributes
vendored
Normal file
39
.gitattributes
vendored
Normal file
@@ -0,0 +1,39 @@
|
||||
*.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
|
||||
stable-cypher-instruct-3b.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
stable-cypher-instruct-3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
stable-cypher-instruct-3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
stable-cypher-instruct-3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
194
README.md
Normal file
194
README.md
Normal file
@@ -0,0 +1,194 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
metrics:
|
||||
- bleu
|
||||
- rouge
|
||||
tags:
|
||||
- causal-lm
|
||||
- code
|
||||
- cypher
|
||||
- graph
|
||||
- neo4j
|
||||
inference: false
|
||||
widget:
|
||||
- text: >-
|
||||
Show me the people who have Python and Cloud skills and have been in the
|
||||
company for at least 3 years.
|
||||
example_title: Example 1
|
||||
- text: What is the IMDb rating of Pulp Fiction?
|
||||
example_title: Example 2
|
||||
- text: >-
|
||||
Display the first 3 users followed by 'Neo4j' who have more than 10000
|
||||
followers.
|
||||
example_title: Example 3
|
||||
base_model:
|
||||
- stabilityai/stable-code-instruct-3b
|
||||
base_model_relation: finetune
|
||||
---
|
||||
|
||||
## Model Description
|
||||
|
||||
A specialized 3B parameters model beating SOTA models such as GPT4-o at generating CYPHER.
|
||||
It's a finetune of https://huggingface.co/stabilityai/stable-code-instruct-3b trained on https://github.com/neo4j-labs/text2cypher/tree/main/datasets/synthetic_opus_demodbs to generate CYPHER queries from text to query GraphDB such as neo4j.
|
||||
|
||||
## Usage
|
||||
|
||||
### Safetensors (recommended)
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("ragraph-ai/stable-cypher-instruct-3b", trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained("ragraph-ai/stable-cypher-instruct-3b", torch_dtype=torch.bfloat16, trust_remote_code=True)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Show me the people who have Python and Cloud skills and have been in the company for at least 3 years."
|
||||
}
|
||||
]
|
||||
|
||||
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
|
||||
|
||||
inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
|
||||
|
||||
tokens = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=128,
|
||||
do_sample=True,
|
||||
top_p=0.9,
|
||||
temperature=0.2,
|
||||
pad_token_id=tokenizer.eos_token_id,
|
||||
)
|
||||
|
||||
outputs = tokenizer.batch_decode(tokens[:, inputs.input_ids.shape[-1]:], skip_special_tokens=False)[0]
|
||||
```
|
||||
|
||||
### GGUF
|
||||
|
||||
```python
|
||||
from llama_cpp import Llama
|
||||
|
||||
# Load the GGUF model
|
||||
print("Loading model...")
|
||||
model = Llama(
|
||||
model_path=r"C:\Users\John\stable-cypher-instruct-3b.Q4_K_M.gguf",
|
||||
n_ctx=512,
|
||||
n_batch=512,
|
||||
n_gpu_layers=-1, # Use all available GPU layers
|
||||
max_tokens=128,
|
||||
top_p=0.9,
|
||||
temperature=0.2,
|
||||
verbose=False
|
||||
)
|
||||
|
||||
# Define your question
|
||||
question = "Show me the people who have Python and Cloud skills and have been in the company for at least 3 years."
|
||||
|
||||
# Create the full prompt (simulating the apply_chat_template function)
|
||||
full_prompt = f"<|im_start|>system\nCreate a Cypher statement to answer the following question:<|im_end|>\n<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant\n"
|
||||
|
||||
# Generate response
|
||||
print("Generating response...")
|
||||
response = model(
|
||||
full_prompt,
|
||||
max_tokens=128,
|
||||
stop=["<|im_end|>", "<|im_start|>"],
|
||||
echo=False
|
||||
)
|
||||
|
||||
# Extract and print the generated response
|
||||
answer = response['choices'][0]['text'].strip()
|
||||
print("\nQuestion:", question)
|
||||
print("\nGenerated Cypher statement:")
|
||||
print(answer)
|
||||
```
|
||||
|
||||
## Performance
|
||||
|
||||
| Metric | stable-code-instruct-3b | gpt4-o | stable-cypher-instruct-3b |
|
||||
| :----------: | :---------------------: | :--------: | :-----------------------: |
|
||||
| BLEU-4 | 19.07 | 32.35 | **88.63** |
|
||||
| ROUGE-1 | 39.49 | 69.17 | **95.09** |
|
||||
| ROUGE-2 | 24.82 | 46.97 | **90.71** |
|
||||
| ROUGE-L | 29.63 | 65.24 | **91.51** |
|
||||
| Jaro-Winkler | 52.21 | 86.38 | **95.69** |
|
||||
| Jaccard | 25.55 | 72.80 | **90.78** |
|
||||
| Pass@1 | 0.00 | 0.00 | **51.80** |
|
||||
|
||||
### Example
|
||||
|
||||
|
||||
### Eval params
|
||||
|
||||
|
||||
## Reproducability
|
||||
|
||||
This is the config file from Llama Factory :
|
||||
|
||||
```json
|
||||
{
|
||||
"top.model_name": "Custom",
|
||||
"top.finetuning_type": "lora",
|
||||
"top.adapter_path": [],
|
||||
"top.quantization_bit": "none",
|
||||
"top.template": "default",
|
||||
"top.rope_scaling": "none",
|
||||
"top.booster": "none",
|
||||
"train.training_stage": "Supervised Fine-Tuning",
|
||||
"train.dataset_dir": "data",
|
||||
"train.dataset": [
|
||||
"cypher_opus"
|
||||
],
|
||||
"train.learning_rate": "2e-4",
|
||||
"train.num_train_epochs": "5.0",
|
||||
"train.max_grad_norm": "1.0",
|
||||
"train.max_samples": "5000",
|
||||
"train.compute_type": "fp16",
|
||||
"train.cutoff_len": 256,
|
||||
"train.batch_size": 16,
|
||||
"train.gradient_accumulation_steps": 2,
|
||||
"train.val_size": 0.1,
|
||||
"train.lr_scheduler_type": "cosine",
|
||||
"train.logging_steps": 10,
|
||||
"train.save_steps": 100,
|
||||
"train.warmup_steps": 20,
|
||||
"train.neftune_alpha": 0,
|
||||
"train.optim": "adamw_torch",
|
||||
"train.resize_vocab": false,
|
||||
"train.packing": false,
|
||||
"train.upcast_layernorm": false,
|
||||
"train.use_llama_pro": false,
|
||||
"train.shift_attn": false,
|
||||
"train.report_to": false,
|
||||
"train.num_layer_trainable": 3,
|
||||
"train.name_module_trainable": "all",
|
||||
"train.lora_rank": 64,
|
||||
"train.lora_alpha": 64,
|
||||
"train.lora_dropout": 0.1,
|
||||
"train.loraplus_lr_ratio": 0,
|
||||
"train.create_new_adapter": false,
|
||||
"train.use_rslora": false,
|
||||
"train.use_dora": true,
|
||||
"train.lora_target": "",
|
||||
"train.additional_target": "",
|
||||
"train.dpo_beta": 0.1,
|
||||
"train.dpo_ftx": 0,
|
||||
"train.orpo_beta": 0.1,
|
||||
"train.reward_model": null,
|
||||
"train.use_galore": false,
|
||||
"train.galore_rank": 16,
|
||||
"train.galore_update_interval": 200,
|
||||
"train.galore_scale": 0.25,
|
||||
"train.galore_target": "all"
|
||||
}
|
||||
```
|
||||
|
||||
I used llama.cpp to merge the LoRa and generate the quants.
|
||||
|
||||
The progress achieved from the base model is significant but you will still need to finetune on your company's syntax and entities.
|
||||
I've been tickering with the training parameters for a few batches of training but there is room for improvements.
|
||||
I'm open to the idea of making a full tutorial if there is enough interest in this project.
|
||||
46
config.json
Normal file
46
config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"_name_or_path": "lakkeo/stable-cypher-instruct-3b",
|
||||
"architectures": [
|
||||
"StableLmForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "silu",
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6912,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 16384,
|
||||
"model_type": "stablelm",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"partial_rotary_factor": 0.25,
|
||||
"qk_layernorm": false,
|
||||
"quantization_config": {
|
||||
"_load_in_4bit": false,
|
||||
"_load_in_8bit": true,
|
||||
"bnb_4bit_compute_dtype": "float32",
|
||||
"bnb_4bit_quant_storage": "uint8",
|
||||
"bnb_4bit_quant_type": "fp4",
|
||||
"bnb_4bit_use_double_quant": false,
|
||||
"llm_int8_enable_fp32_cpu_offload": false,
|
||||
"llm_int8_has_fp16_weight": false,
|
||||
"llm_int8_skip_modules": null,
|
||||
"llm_int8_threshold": 6.0,
|
||||
"load_in_4bit": false,
|
||||
"load_in_8bit": true,
|
||||
"quant_method": "bitsandbytes"
|
||||
},
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.41.2",
|
||||
"use_cache": false,
|
||||
"use_parallel_residual": false,
|
||||
"use_qkv_bias": false,
|
||||
"vocab_size": 50304
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 0,
|
||||
"transformers_version": "4.41.2"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:20c7707af6488d3d44f30884102fad45688b31a38604fe9323755ba6c9e65ca8
|
||||
size 3572608832
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"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": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
stable-cypher-instruct-3b.Q4_K_M.gguf
Normal file
3
stable-cypher-instruct-3b.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:21b229637f89146fcb009b509a9cee7478f0d245f8aed1961bb6352deb7d5d96
|
||||
size 1708596032
|
||||
3
stable-cypher-instruct-3b.Q5_K_M.gguf
Normal file
3
stable-cypher-instruct-3b.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:909cbc6f725b67cfdf08b29d8e00bffa0a3d6a20d4a65065edacac6c242f8aba
|
||||
size 1993390912
|
||||
3
stable-cypher-instruct-3b.Q8_0.gguf
Normal file
3
stable-cypher-instruct-3b.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7dfb2daef3625681a52d522dff0d54899c71459a49833ce2e851ad4f5dcc4d2f
|
||||
size 2972926272
|
||||
3
stable-cypher-instruct-3b.f16.gguf
Normal file
3
stable-cypher-instruct-3b.f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a7516f8a6144e671e284223d06c45b52cf51d05828d407dd31cfe8779b92f433
|
||||
size 5593342272
|
||||
100727
tokenizer.json
Normal file
100727
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
389
tokenizer_config.json
Normal file
389
tokenizer_config.json
Normal file
@@ -0,0 +1,389 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|padding|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50254": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50255": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50256": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50257": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50270": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50271": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50272": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50273": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50274": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50275": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50276": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50277": {
|
||||
"content": "<fim_prefix>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50278": {
|
||||
"content": "<fim_middle>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50279": {
|
||||
"content": "<fim_suffix>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50280": {
|
||||
"content": "<fim_pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50281": {
|
||||
"content": "<filename>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50282": {
|
||||
"content": "<gh_stars>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50283": {
|
||||
"content": "<issue_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50284": {
|
||||
"content": "<issue_comment>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50285": {
|
||||
"content": "<issue_closed>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50286": {
|
||||
"content": "<jupyter_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50287": {
|
||||
"content": "<jupyter_text>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50288": {
|
||||
"content": "<jupyter_code>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50289": {
|
||||
"content": "<jupyter_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50290": {
|
||||
"content": "<empty_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50291": {
|
||||
"content": "<commit_before>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50292": {
|
||||
"content": "<commit_msg>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50293": {
|
||||
"content": "<commit_after>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50294": {
|
||||
"content": "<reponame>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50295": {
|
||||
"content": "<repo_continuation>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50296": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50297": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50298": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'Create a Cypher statement to answer the following question:' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPTNeoXTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Reference in New Issue
Block a user