初始化项目，由ModelHub XC社区提供模型
Model: CobraMamba/mamba-gpt-3b-v2 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
||||
214
README.md
Executable file
214
README.md
Executable file
@@ -0,0 +1,214 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
tags:
|
||||
- gpt
|
||||
- llm
|
||||
- large language model
|
||||
inference: false
|
||||
thumbnail: >-
|
||||
https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
|
||||
license: apache-2.0
|
||||
---
|
||||
# Model Card
|
||||
|
||||
**The Best 3B Model! Surpassing dolly-v2-12b**
|
||||
|
||||
The best 3B model on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard), with performance surpassing dolly-v2-12b
|
||||
|
||||
| Metric | Value |
|
||||
|-----------------------|-------|
|
||||
| MMLU (5-shot) | 27.1 |
|
||||
| ARC (25-shot) | 42.2 |
|
||||
| HellaSwag (10-shot) | 71.5 |
|
||||
| TruthfulQA (0-shot) | 36.7 |
|
||||
| Avg. | 44.4 |
|
||||
|
||||
We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above.
|
||||
|
||||
|
||||
|
||||
## Summary
|
||||
|
||||
We have fine-tuned the open-lama model and surpassed the original model in multiple evaluation subtasks, making it currently the best performing 3B model with comparable performance to llama-7b
|
||||
- Base model: [openlm-research/open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2)
|
||||
|
||||
## Usage
|
||||
|
||||
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate` and `torch` libraries installed.
|
||||
|
||||
```bash
|
||||
pip install transformers==4.29.2
|
||||
pip install accelerate==0.19.0
|
||||
pip install torch==2.0.0
|
||||
```
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import pipeline
|
||||
|
||||
generate_text = pipeline(
|
||||
model="CobraMamba/mamba-gpt-3b-v2",
|
||||
torch_dtype="auto",
|
||||
trust_remote_code=True,
|
||||
use_fast=False,
|
||||
device_map={"": "cuda:0"},
|
||||
)
|
||||
|
||||
res = generate_text(
|
||||
"Why is drinking water so healthy?",
|
||||
min_new_tokens=2,
|
||||
max_new_tokens=1024,
|
||||
do_sample=False,
|
||||
num_beams=1,
|
||||
temperature=float(0.3),
|
||||
repetition_penalty=float(1.2),
|
||||
renormalize_logits=True
|
||||
)
|
||||
print(res[0]["generated_text"])
|
||||
```
|
||||
|
||||
You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:
|
||||
|
||||
```python
|
||||
print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
|
||||
```
|
||||
|
||||
```bash
|
||||
<|prompt|>Why is drinking water so healthy?</s><|answer|>
|
||||
```
|
||||
|
||||
Alternatively, you can download the mamba_gpt_pipeline.py, store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer. If the model and the tokenizer are fully supported in the `transformers` package, this will allow you to set `trust_remote_code=False`.
|
||||
|
||||
```python
|
||||
import torch
|
||||
from mamba_gpt_pipeline import MambaGPTTextGenerationPipeline
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(
|
||||
"CobraMamba/mamba-gpt-3b-v2",
|
||||
use_fast=False,
|
||||
padding_side="left",
|
||||
trust_remote_code=False,
|
||||
)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"CobraMamba/mamba-gpt-3b-v2",
|
||||
torch_dtype="auto",
|
||||
device_map={"": "cuda:0"},
|
||||
trust_remote_code=False,
|
||||
)
|
||||
generate_text = MambaGPTTextGenerationPipeline(model=model, tokenizer=tokenizer)
|
||||
|
||||
res = generate_text(
|
||||
"Why is drinking water so healthy?",
|
||||
min_new_tokens=2,
|
||||
max_new_tokens=1024,
|
||||
do_sample=False,
|
||||
num_beams=1,
|
||||
temperature=float(0.3),
|
||||
repetition_penalty=float(1.2),
|
||||
renormalize_logits=True
|
||||
)
|
||||
print(res[0]["generated_text"])
|
||||
```
|
||||
|
||||
|
||||
You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "CobraMamba/mamba-gpt-3b-v2" # either local folder or huggingface model name
|
||||
# Important: The prompt needs to be in the same format the model was trained with.
|
||||
# You can find an example prompt in the experiment logs.
|
||||
prompt = "<|prompt|>How are you?</s><|answer|>"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(
|
||||
model_name,
|
||||
use_fast=False,
|
||||
trust_remote_code=False,
|
||||
)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype="auto",
|
||||
device_map={"": "cuda:0"},
|
||||
trust_remote_code=False,
|
||||
)
|
||||
model.cuda().eval()
|
||||
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")
|
||||
|
||||
# generate configuration can be modified to your needs
|
||||
tokens = model.generate(
|
||||
**inputs,
|
||||
min_new_tokens=2,
|
||||
max_new_tokens=1024,
|
||||
do_sample=False,
|
||||
num_beams=1,
|
||||
temperature=float(0.3),
|
||||
repetition_penalty=float(1.2),
|
||||
renormalize_logits=True
|
||||
)[0]
|
||||
|
||||
tokens = tokens[inputs["input_ids"].shape[1]:]
|
||||
answer = tokenizer.decode(tokens, skip_special_tokens=True)
|
||||
print(answer)
|
||||
```
|
||||
|
||||
## Model Architecture
|
||||
|
||||
```
|
||||
LlamaForCausalLM(
|
||||
(model): LlamaModel(
|
||||
(embed_tokens): Embedding(32000, 4096, padding_idx=0)
|
||||
(layers): ModuleList(
|
||||
(0-31): 32 x LlamaDecoderLayer(
|
||||
(self_attn): LlamaAttention(
|
||||
(q_proj): Linear(in_features=4096, out_features=4096, bias=False)
|
||||
(k_proj): Linear(in_features=4096, out_features=4096, bias=False)
|
||||
(v_proj): Linear(in_features=4096, out_features=4096, bias=False)
|
||||
(o_proj): Linear(in_features=4096, out_features=4096, bias=False)
|
||||
(rotary_emb): LlamaRotaryEmbedding()
|
||||
)
|
||||
(mlp): LlamaMLP(
|
||||
(gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
|
||||
(down_proj): Linear(in_features=11008, out_features=4096, bias=False)
|
||||
(up_proj): Linear(in_features=4096, out_features=11008, bias=False)
|
||||
(act_fn): SiLUActivation()
|
||||
)
|
||||
(input_layernorm): LlamaRMSNorm()
|
||||
(post_attention_layernorm): LlamaRMSNorm()
|
||||
)
|
||||
)
|
||||
(norm): LlamaRMSNorm()
|
||||
)
|
||||
(lm_head): Linear(in_features=4096, out_features=32000, bias=False)
|
||||
)
|
||||
```
|
||||
|
||||
## Citation
|
||||
|
||||
If this work is helpful, please kindly cite as:
|
||||
|
||||
```bibtex
|
||||
@Misc{mamba-gpt-3b-v2,
|
||||
title = {Mamba-GPT-3b-v2},
|
||||
author = {chiliu},
|
||||
howpublished = {\url{https://huggingface.co/CobraMamba/mamba-gpt-3b-v2}},
|
||||
year = {2023}
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
## Disclaimer
|
||||
|
||||
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
|
||||
|
||||
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
|
||||
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
|
||||
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
|
||||
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
|
||||
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
|
||||
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
|
||||
|
||||
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.
|
||||
21
adapter_config.json
Executable file
21
adapter_config.json
Executable file
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "openlm-research/open_llama_3b_v2",
|
||||
"bias": "none",
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"lora_alpha": 16,
|
||||
"lora_dropout": 0.1,
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"r": 256,
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"q_proj",
|
||||
"v_proj"
|
||||
],
|
||||
"task_type": "CAUSAL_LM"
|
||||
}
|
||||
115
cfg.yaml
Executable file
115
cfg.yaml
Executable file
@@ -0,0 +1,115 @@
|
||||
architecture:
|
||||
backbone_dtype: float16
|
||||
force_embedding_gradients: false
|
||||
gradient_checkpointing: true
|
||||
intermediate_dropout: 0.0
|
||||
pretrained: true
|
||||
pretrained_weights: ''
|
||||
augmentation:
|
||||
random_parent_probability: 0.0
|
||||
skip_parent_probability: 0.0
|
||||
token_mask_probability: 0.0
|
||||
dataset:
|
||||
add_eos_token_to_answer: true
|
||||
add_eos_token_to_prompt: true
|
||||
add_eos_token_to_system: true
|
||||
answer_column: output
|
||||
chatbot_author: H2O.ai
|
||||
chatbot_name: h2oGPT
|
||||
data_sample: 1.0
|
||||
data_sample_choice:
|
||||
- Train
|
||||
- Validation
|
||||
limit_chained_samples: false
|
||||
mask_prompt_labels: true
|
||||
parent_id_column: None
|
||||
personalize: false
|
||||
prompt_column:
|
||||
- instruction
|
||||
system_column: None
|
||||
text_answer_separator: <|answer|>
|
||||
text_prompt_start: <|prompt|>
|
||||
text_system_start: <|system|>
|
||||
train_dataframe: data/user/oasst/train_oasst_dolly_evol.csv
|
||||
validation_dataframe: data/user/oasst/valid_oasst_dolly_evol.csv
|
||||
validation_size: 0.01
|
||||
validation_strategy: custom
|
||||
environment:
|
||||
compile_model: false
|
||||
find_unused_parameters: false
|
||||
gpus:
|
||||
- '0'
|
||||
huggingface_branch: main
|
||||
mixed_precision: true
|
||||
number_of_workers: 1
|
||||
seed: -1
|
||||
trust_remote_code: true
|
||||
use_fsdp: false
|
||||
experiment_name: blue-zebu
|
||||
llm_backbone: openlm-research/open_llama_3b_v2
|
||||
logging:
|
||||
logger: None
|
||||
neptune_project: ''
|
||||
number_of_texts: 10
|
||||
output_directory: /workspace/output/user/blue-zebu/
|
||||
prediction:
|
||||
batch_size_inference: 0
|
||||
do_sample: true
|
||||
max_length_inference: 256
|
||||
metric: BLEU
|
||||
metric_gpt_model: gpt-3.5-turbo-0301
|
||||
min_length_inference: 2
|
||||
num_beams: 1
|
||||
num_history: 4
|
||||
repetition_penalty: 1.2
|
||||
stop_tokens: ''
|
||||
temperature: 0.3
|
||||
top_k: 40
|
||||
top_p: 0.8
|
||||
problem_type: text_causal_language_modeling
|
||||
tokenizer:
|
||||
add_prefix_space: false
|
||||
add_prompt_answer_tokens: false
|
||||
max_length: 2048
|
||||
max_length_answer: 2048
|
||||
max_length_prompt: 2048
|
||||
padding_quantile: 1.0
|
||||
use_fast: false
|
||||
training:
|
||||
adaptive_kl_control: true
|
||||
advantages_gamma: 0.99
|
||||
advantages_lambda: 0.95
|
||||
batch_size: 3
|
||||
differential_learning_rate: 1.0e-05
|
||||
differential_learning_rate_layers: []
|
||||
drop_last_batch: true
|
||||
epochs: 3
|
||||
evaluate_before_training: false
|
||||
evaluation_epochs: 1.0
|
||||
grad_accumulation: 1
|
||||
gradient_clip: 0.0
|
||||
initial_kl_coefficient: 0.2
|
||||
kl_horizon: 10000
|
||||
kl_target: 6.0
|
||||
learning_rate: 5.0e-05
|
||||
lora: true
|
||||
lora_alpha: 16
|
||||
lora_dropout: 0.1
|
||||
lora_r: 256
|
||||
lora_target_modules: ''
|
||||
loss_function: TokenAveragedCrossEntropy
|
||||
offload_reward_model: false
|
||||
optimizer: AdamW
|
||||
ppo_batch_size: 1
|
||||
ppo_clip_policy: 0.2
|
||||
ppo_clip_value: 0.2
|
||||
ppo_epochs: 4
|
||||
ppo_generate_temperature: 1.0
|
||||
reward_model: OpenAssistant/reward-model-deberta-v3-large-v2
|
||||
save_best_checkpoint: false
|
||||
scaling_factor_value_loss: 0.1
|
||||
schedule: Cosine
|
||||
train_validation_data: false
|
||||
use_rlhf: false
|
||||
warmup_epochs: 0.0
|
||||
weight_decay: 0.0
|
||||
28
config.json
Executable file
28
config.json
Executable file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "openlm-research/open_llama_3b_v2",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_probs_dropout_prob": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_dropout_prob": 0.0,
|
||||
"hidden_size": 3200,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8640,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 26,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.31.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
1
flags.json
Executable file
1
flags.json
Executable file
@@ -0,0 +1 @@
|
||||
{"status": "finished", "info": "Runtime: 14:50:58"}
|
||||
7
generation_config.json
Executable file
7
generation_config.json
Executable file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.31.0"
|
||||
}
|
||||
42
mamba_gpt_pipeline.py
Normal file
42
mamba_gpt_pipeline.py
Normal file
@@ -0,0 +1,42 @@
|
||||
from transformers import TextGenerationPipeline
|
||||
from transformers.pipelines.text_generation import ReturnType
|
||||
|
||||
STYLE = "<|prompt|>{instruction}</s><|answer|>"
|
||||
|
||||
|
||||
class MambaGPTTextGenerationPipeline(TextGenerationPipeline):
|
||||
def __init__(self, *args, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
self.prompt = STYLE
|
||||
|
||||
def preprocess(
|
||||
self, prompt_text, prefix="", handle_long_generation=None, **generate_kwargs
|
||||
):
|
||||
prompt_text = self.prompt.format(instruction=prompt_text)
|
||||
return super().preprocess(
|
||||
prompt_text,
|
||||
prefix=prefix,
|
||||
handle_long_generation=handle_long_generation,
|
||||
**generate_kwargs,
|
||||
)
|
||||
|
||||
def postprocess(
|
||||
self,
|
||||
model_outputs,
|
||||
return_type=ReturnType.FULL_TEXT,
|
||||
clean_up_tokenization_spaces=True,
|
||||
):
|
||||
records = super().postprocess(
|
||||
model_outputs,
|
||||
return_type=return_type,
|
||||
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
||||
)
|
||||
for rec in records:
|
||||
rec["generated_text"] = (
|
||||
rec["generated_text"]
|
||||
.split("<|answer|>")[1]
|
||||
.strip()
|
||||
.split("<|prompt|>")[0]
|
||||
.strip()
|
||||
)
|
||||
return records
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:19b5a149e37b11d0d56290b7d24328cbae91b455453352d895f0d7013dc8e159
|
||||
size 6852982288
|
||||
3
pytorch_model.bin
Executable file
3
pytorch_model.bin
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c596bce6a1ddcfcca723c78d56b01a108ff9b561048c349ea3f7c6161bacad6f
|
||||
size 6853041741
|
||||
26
special_tokens_map.json
Executable file
26
special_tokens_map.json
Executable file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"cls_token": "</s>",
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<unk>",
|
||||
"sep_token": "</s>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.model
Executable file
3
tokenizer.model
Executable file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
|
||||
size 511574
|
||||
35
tokenizer_config.json
Executable file
35
tokenizer_config.json
Executable file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": true,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user