初始化项目，由ModelHub XC社区提供模型
Model: theprint/Boptruth-Agatha-7B Source: Original Platform
This commit is contained in:
ModelHub XC
53
.gitattributes
vendored
Normal file
53
.gitattributes
vendored
Normal file
@@ -0,0 +1,53 @@
|
||||
*.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
|
||||
unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Boptruth-Agatha-7B.F16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Boptruth-Agatha-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Boptruth-Agatha-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Boptruth-Agatha-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Boptruth-Agatha-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Boptruth-Agatha-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Boptruth-Agatha-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Boptruth-Agatha-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Boptruth-Agatha-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Boptruth-Agatha-7B.F16.gguf
Normal file
3
Boptruth-Agatha-7B.F16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f14d0c97c4f70c320f0c6205b5f17c98ac668bd584dc911e5ade184cafccc47
|
||||
size 14484732672
|
||||
3
Boptruth-Agatha-7B.Q2_K.gguf
Normal file
3
Boptruth-Agatha-7B.Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f52cf050ee30c087af75933cb461d4952eb4156c9aa4c62df9001e7f0877f26
|
||||
size 2719243008
|
||||
3
Boptruth-Agatha-7B.Q3_K_M.gguf
Normal file
3
Boptruth-Agatha-7B.Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:177e59d7f25ea431dd2e1aa3e7430ca744aa7ce5deb7659e50b9254f49e46820
|
||||
size 3518987008
|
||||
3
Boptruth-Agatha-7B.Q3_K_S.gguf
Normal file
3
Boptruth-Agatha-7B.Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:19842cad3e10676bd99e4da525e2e62cbb6375a3a4e078ba210646c9d168d2fd
|
||||
size 3164568320
|
||||
3
Boptruth-Agatha-7B.Q4_K_M.gguf
Normal file
3
Boptruth-Agatha-7B.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2683e42ee1c110bbaa4d8c6a016a5bd84cf7d87727455529b5d1df073113d59e
|
||||
size 4368440064
|
||||
3
Boptruth-Agatha-7B.Q4_K_S.gguf
Normal file
3
Boptruth-Agatha-7B.Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7d9cf2833ce8ba7e6263a17c71327b8b13d8dd1db5047f68e09b20eac20f0cd9
|
||||
size 4140374784
|
||||
3
Boptruth-Agatha-7B.Q5_K_M.gguf
Normal file
3
Boptruth-Agatha-7B.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9b318f114a8ebea23d64131671737ee4b5bc4dd3de9a2c7f8264dbc717ef94bc
|
||||
size 5131410176
|
||||
3
Boptruth-Agatha-7B.Q6_K.gguf
Normal file
3
Boptruth-Agatha-7B.Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c9c489badabe992d386831013d9900392f98b4089b3f57b50a71698a979e7e6d
|
||||
size 5942065920
|
||||
3
Boptruth-Agatha-7B.Q8_0.gguf
Normal file
3
Boptruth-Agatha-7B.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:70da6848172e8eaa185557872ef99ac7539cf1ff2e5538d7852bd0d75118d3fe
|
||||
size 7695858432
|
||||
299
README.md
Normal file
299
README.md
Normal file
@@ -0,0 +1,299 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
tags:
|
||||
- gpt
|
||||
- llm
|
||||
- large language model
|
||||
- h2o-llmstudio
|
||||
- theprint
|
||||
- boptruth
|
||||
datasets:
|
||||
- theprint/MysteryWriter
|
||||
inference: false
|
||||
thumbnail: https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
|
||||
model-index:
|
||||
- name: Boptruth-Agatha-7B
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: IFEval (0-Shot)
|
||||
type: HuggingFaceH4/ifeval
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: inst_level_strict_acc and prompt_level_strict_acc
|
||||
value: 31.24
|
||||
name: strict accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Boptruth-Agatha-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: BBH (3-Shot)
|
||||
type: BBH
|
||||
args:
|
||||
num_few_shot: 3
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 29.29
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Boptruth-Agatha-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MATH Lvl 5 (4-Shot)
|
||||
type: hendrycks/competition_math
|
||||
args:
|
||||
num_few_shot: 4
|
||||
metrics:
|
||||
- type: exact_match
|
||||
value: 4.61
|
||||
name: exact match
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Boptruth-Agatha-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GPQA (0-shot)
|
||||
type: Idavidrein/gpqa
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 6.6
|
||||
name: acc_norm
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Boptruth-Agatha-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MuSR (0-shot)
|
||||
type: TAUR-Lab/MuSR
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 11.76
|
||||
name: acc_norm
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Boptruth-Agatha-7B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU-PRO (5-shot)
|
||||
type: TIGER-Lab/MMLU-Pro
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 20.67
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Boptruth-Agatha-7B
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
# Model Card
|
||||
## Summary
|
||||
|
||||
Boptruth-Agatha is a finetune of Boptruth-NeuralMonarch on the MysteryWriter data set. This data set is created to help guide writers structure and plan their work, mainly crime, mystery and thriller novels.
|
||||
|
||||
This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
|
||||
- Base model: [theprint/Boptruth-NeuralMonarch-7B](https://huggingface.co/theprint/Boptruth-NeuralMonarch-7B)
|
||||
|
||||
|
||||
## Usage
|
||||
|
||||
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers` library installed.
|
||||
|
||||
```bash
|
||||
pip install transformers==4.43.1
|
||||
```
|
||||
|
||||
Also make sure you are providing your huggingface token to the pipeline if the model is lying in a private repo.
|
||||
|
||||
- Either leave `token=True` in the `pipeline` and login to hugginface_hub by running
|
||||
|
||||
```python
|
||||
import huggingface_hub
|
||||
huggingface_hub.login(<ACCESS_TOKEN>)
|
||||
```
|
||||
|
||||
- Or directly pass your <ACCESS_TOKEN> to `token` in the `pipeline`
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
|
||||
generate_text = pipeline(
|
||||
model="theprint/Boptruth-Agatha-7B",
|
||||
torch_dtype="auto",
|
||||
trust_remote_code=True,
|
||||
device_map={"": "cuda:0"},
|
||||
token=True,
|
||||
)
|
||||
|
||||
# generate configuration can be modified to your needs
|
||||
# generate_text.model.generation_config.min_new_tokens = 2
|
||||
# generate_text.model.generation_config.max_new_tokens = 256
|
||||
# generate_text.model.generation_config.do_sample = False
|
||||
# generate_text.model.generation_config.num_beams = 1
|
||||
# generate_text.model.generation_config.temperature = float(0.0)
|
||||
# generate_text.model.generation_config.repetition_penalty = float(1.0)
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "Hi, how are you?"},
|
||||
{"role": "assistant", "content": "I'm doing great, how about you?"},
|
||||
{"role": "user", "content": "Why is drinking water so healthy?"},
|
||||
]
|
||||
|
||||
res = generate_text(
|
||||
messages,
|
||||
renormalize_logits=True
|
||||
)
|
||||
print(res[0]["generated_text"][-1]['content'])
|
||||
```
|
||||
|
||||
You can print a sample prompt after applying chat template to see how it is feed to the tokenizer:
|
||||
|
||||
```python
|
||||
print(generate_text.tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
))
|
||||
```
|
||||
|
||||
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 = "theprint/Boptruth-Agatha-7B" # either local folder or Hugging Face 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.
|
||||
messages = [
|
||||
{"role": "user", "content": "Hi, how are you?"},
|
||||
{"role": "assistant", "content": "I'm doing great, how about you?"},
|
||||
{"role": "user", "content": "Why is drinking water so healthy?"},
|
||||
]
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(
|
||||
model_name,
|
||||
trust_remote_code=True,
|
||||
)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype="auto",
|
||||
device_map={"": "cuda:0"},
|
||||
trust_remote_code=True,
|
||||
)
|
||||
model.cuda().eval()
|
||||
|
||||
# generate configuration can be modified to your needs
|
||||
# model.generation_config.min_new_tokens = 2
|
||||
# model.generation_config.max_new_tokens = 256
|
||||
# model.generation_config.do_sample = False
|
||||
# model.generation_config.num_beams = 1
|
||||
# model.generation_config.temperature = float(0.0)
|
||||
# model.generation_config.repetition_penalty = float(1.0)
|
||||
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt",
|
||||
return_dict=True,
|
||||
).to("cuda")
|
||||
|
||||
tokens = model.generate(
|
||||
input_ids=inputs["input_ids"],
|
||||
attention_mask=inputs["attention_mask"],
|
||||
renormalize_logits=True
|
||||
)[0]
|
||||
|
||||
tokens = tokens[inputs["input_ids"].shape[1]:]
|
||||
answer = tokenizer.decode(tokens, skip_special_tokens=True)
|
||||
print(answer)
|
||||
```
|
||||
|
||||
## Quantization and sharding
|
||||
|
||||
You can load the models using quantization by specifying ```load_in_8bit=True``` or ```load_in_4bit=True```. Also, sharding on multiple GPUs is possible by setting ```device_map=auto```.
|
||||
|
||||
## Model Architecture
|
||||
|
||||
```
|
||||
MistralForCausalLM(
|
||||
(model): MistralModel(
|
||||
(embed_tokens): Embedding(32000, 4096, padding_idx=0)
|
||||
(layers): ModuleList(
|
||||
(0-31): 32 x MistralDecoderLayer(
|
||||
(self_attn): MistralSdpaAttention(
|
||||
(q_proj): Linear(in_features=4096, out_features=4096, bias=False)
|
||||
(k_proj): Linear(in_features=4096, out_features=1024, bias=False)
|
||||
(v_proj): Linear(in_features=4096, out_features=1024, bias=False)
|
||||
(o_proj): Linear(in_features=4096, out_features=4096, bias=False)
|
||||
(rotary_emb): MistralRotaryEmbedding()
|
||||
)
|
||||
(mlp): MistralMLP(
|
||||
(gate_proj): Linear(in_features=4096, out_features=14336, bias=False)
|
||||
(up_proj): Linear(in_features=4096, out_features=14336, bias=False)
|
||||
(down_proj): Linear(in_features=14336, out_features=4096, bias=False)
|
||||
(act_fn): SiLU()
|
||||
)
|
||||
(input_layernorm): MistralRMSNorm()
|
||||
(post_attention_layernorm): MistralRMSNorm()
|
||||
)
|
||||
)
|
||||
(norm): MistralRMSNorm()
|
||||
)
|
||||
(lm_head): Linear(in_features=4096, out_features=32000, bias=False)
|
||||
)
|
||||
```
|
||||
|
||||
## Model Configuration
|
||||
|
||||
This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models.
|
||||
|
||||
|
||||
## 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.
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_theprint__Boptruth-Agatha-7B)
|
||||
|
||||
| Metric |Value|
|
||||
|-------------------|----:|
|
||||
|Avg. |17.36|
|
||||
|IFEval (0-Shot) |31.24|
|
||||
|BBH (3-Shot) |29.29|
|
||||
|MATH Lvl 5 (4-Shot)| 4.61|
|
||||
|GPQA (0-shot) | 6.60|
|
||||
|MuSR (0-shot) |11.76|
|
||||
|MMLU-PRO (5-shot) |20.67|
|
||||
|
||||
117
cfg.yaml
Normal file
117
cfg.yaml
Normal file
@@ -0,0 +1,117 @@
|
||||
architecture:
|
||||
backbone_dtype: int4
|
||||
gradient_checkpointing: true
|
||||
intermediate_dropout: 0.0
|
||||
pretrained: true
|
||||
pretrained_weights: ''
|
||||
augmentation:
|
||||
neftune_noise_alpha: 0.0
|
||||
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
|
||||
only_last_answer: false
|
||||
parent_id_column: None
|
||||
personalize: false
|
||||
prompt_column:
|
||||
- instruction
|
||||
- input
|
||||
prompt_column_separator: \n\n
|
||||
system_column: None
|
||||
text_answer_separator: <|answer|>
|
||||
text_prompt_start: <|prompt|>
|
||||
text_system_start: <|system|>
|
||||
train_dataframe: /home/llmstudio/mount/data/user/MysteryWriter_train/MysteryWriter_train.pq
|
||||
validation_dataframe: None
|
||||
validation_size: 0.01
|
||||
validation_strategy: automatic
|
||||
environment:
|
||||
compile_model: false
|
||||
deepspeed_allgather_bucket_size: 1000000
|
||||
deepspeed_method: ZeRO2
|
||||
deepspeed_reduce_bucket_size: 1000000
|
||||
deepspeed_stage3_param_persistence_threshold: 1000000
|
||||
deepspeed_stage3_prefetch_bucket_size: 1000000
|
||||
find_unused_parameters: false
|
||||
gpus:
|
||||
- '0'
|
||||
huggingface_branch: main
|
||||
mixed_precision: true
|
||||
mixed_precision_dtype: bfloat16
|
||||
number_of_workers: 8
|
||||
seed: -1
|
||||
trust_remote_code: true
|
||||
use_deepspeed: false
|
||||
experiment_name: Boptruth-Agatha
|
||||
llm_backbone: theprint/Boptruth-NeuralMonarch-7B
|
||||
logging:
|
||||
log_all_ranks: false
|
||||
log_step_size: absolute
|
||||
logger: None
|
||||
neptune_project: ''
|
||||
wandb_entity: ''
|
||||
wandb_project: ''
|
||||
output_directory: /home/llmstudio/mount/output/user/Boptruth-Agatha/
|
||||
prediction:
|
||||
batch_size_inference: 0
|
||||
do_sample: false
|
||||
max_length_inference: 256
|
||||
max_time: 0.0
|
||||
metric: BLEU
|
||||
metric_gpt_model: gpt-3.5-turbo-0301
|
||||
metric_gpt_template: general
|
||||
min_length_inference: 2
|
||||
num_beams: 1
|
||||
num_history: 4
|
||||
repetition_penalty: 1.0
|
||||
stop_tokens: ''
|
||||
temperature: 0.0
|
||||
top_k: 0
|
||||
top_p: 1.0
|
||||
problem_type: text_causal_language_modeling
|
||||
tokenizer:
|
||||
add_prompt_answer_tokens: false
|
||||
max_length: 1024
|
||||
padding_quantile: 1.0
|
||||
tokenizer_kwargs: '{"use_fast": true, "add_prefix_space": false}'
|
||||
training:
|
||||
attention_implementation: auto
|
||||
batch_size: 3
|
||||
differential_learning_rate: 1.0e-05
|
||||
differential_learning_rate_layers: []
|
||||
drop_last_batch: true
|
||||
epochs: 1
|
||||
evaluate_before_training: false
|
||||
evaluation_epochs: 1.0
|
||||
freeze_layers: []
|
||||
grad_accumulation: 1
|
||||
gradient_clip: 0.0
|
||||
learning_rate: 0.0001
|
||||
lora: true
|
||||
lora_alpha: 16
|
||||
lora_dropout: 0.05
|
||||
lora_r: 4
|
||||
lora_target_modules: ''
|
||||
lora_unfreeze_layers: []
|
||||
loss_function: TokenAveragedCrossEntropy
|
||||
min_learning_rate_ratio: 0.0
|
||||
optimizer: AdamW
|
||||
save_checkpoint: last
|
||||
schedule: Cosine
|
||||
train_validation_data: false
|
||||
use_dora: false
|
||||
use_rslora: false
|
||||
warmup_epochs: 0.0
|
||||
weight_decay: 0.0
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "theprint/Boptruth-Agatha-7B",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.38.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"max_new_tokens": 256,
|
||||
"min_new_tokens": 2,
|
||||
"pad_token_id": 0,
|
||||
"temperature": null,
|
||||
"top_k": null,
|
||||
"top_p": null,
|
||||
"transformers_version": "4.43.1"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:27f0c131beba3bffbed022ad20e1efcc12e828266c302bbf0d285bf9160bd210
|
||||
size 4943162240
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:659efa89e7d245f5004b31c9caa4a5cf512d4d264e0ff93ee69213b90a758e4b
|
||||
size 4999819232
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6aa44426c1c1ec94df74d364e631ee4a2402ec11e10316bb2747f8e73fb0b8c1
|
||||
size 4540516256
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14483464192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"cls_token": "</s>",
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91085
tokenizer.json
Normal file
91085
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
46
tokenizer_config.json
Normal file
46
tokenizer_config.json
Normal file
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"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": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% if ((message['role'] == 'user') != (loop.index0 % 2 == 0)) or ((message['role'] == 'assistant') != (loop.index0 % 2 == 1)) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '<|prompt|>' + message['content'].strip() + eos_token }}{% elif message['role'] == 'assistant' %}{{ '<|answer|>' + message['content'].strip() + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|answer|>' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"cls_token": "</s>",
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<unk>",
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user