初始化项目，由ModelHub XC社区提供模型
Model: ali-elganzory/SmolLM2-1.7B-SFT-Tulu3-decontaminated-masked Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
57
README.md
Normal file
57
README.md
Normal file
@@ -0,0 +1,57 @@
|
||||
---
|
||||
base_model: ali-elganzory/SmolLM2-1.7B-WithChatTemplate
|
||||
library_name: transformers
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- sft
|
||||
- trl
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for None
|
||||
|
||||
This model is a fine-tuned version of [ali-elganzory/SmolLM2-1.7B-WithChatTemplate](https://huggingface.co/ali-elganzory/SmolLM2-1.7B-WithChatTemplate).
|
||||
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
|
||||
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||
generator = pipeline("text-generation", model="None", device="cuda")
|
||||
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||
print(output["generated_text"])
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
|
||||
|
||||
|
||||
This model was trained with SFT.
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.27.1
|
||||
- Transformers: 4.57.6
|
||||
- Pytorch: 2.6.0+cu126
|
||||
- Datasets: 4.8.4
|
||||
- Tokenizers: 0.22.2
|
||||
|
||||
## Citations
|
||||
|
||||
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@misc{vonwerra2022trl,
|
||||
title = {{TRL: Transformer Reinforcement Learning}},
|
||||
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
||||
year = 2020,
|
||||
journal = {GitHub repository},
|
||||
publisher = {GitHub},
|
||||
howpublished = {\url{https://github.com/huggingface/trl}}
|
||||
}
|
||||
```
|
||||
5
added_tokens.json
Normal file
5
added_tokens.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"<|assistant|>": 49154,
|
||||
"<|system|>": 49152,
|
||||
"<|user|>": 49153
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"total_flos": 3199489317601280.0,
|
||||
"train_loss": 0.7106047359356158,
|
||||
"train_runtime": 48891.9802,
|
||||
"train_samples": 936509,
|
||||
"train_samples_per_second": 38.309,
|
||||
"train_steps_per_second": 0.299
|
||||
}
|
||||
16
chat_template.jinja
Normal file
16
chat_template.jinja
Normal file
@@ -0,0 +1,16 @@
|
||||
{%- for message in messages -%}
|
||||
{%- if message["role"] == "system" -%}
|
||||
{{- "<|system|>\n" + message["content"] + "\n" -}}
|
||||
{%- elif message["role"] == "user" -%}
|
||||
{{- "<|user|>\n" + message["content"] + "\n" -}}
|
||||
{%- elif message["role"] == "assistant" -%}
|
||||
{%- if not loop.last -%}
|
||||
{{- "<|assistant|>\n" -}}{% generation %}{{- message["content"] + eos_token -}}{% endgeneration %}{{- "\n" -}}
|
||||
{%- else -%}
|
||||
{{- "<|assistant|>\n" -}}{% generation %}{{- message["content"] + eos_token -}}{% endgeneration %}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{%- if loop.last and add_generation_prompt -%}
|
||||
{{- "<|assistant|>\n" -}}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 8192,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 130000,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": true,
|
||||
"vocab_size": 49216
|
||||
}
|
||||
55
config.yaml
Normal file
55
config.yaml
Normal file
@@ -0,0 +1,55 @@
|
||||
model_name_or_path: ali-elganzory/SmolLM2-1.7B-WithChatTemplate
|
||||
dtype: bfloat16
|
||||
attn_implementation: flash_attention_2
|
||||
trust_remote_code: true
|
||||
chat_template: "{%- for message in messages -%}\n\t{%- if message[\"role\"] == \"\
|
||||
system\" -%}\n\t\t{{- \"<|system|>\\n\" + message[\"content\"] + \"\\n\" -}}\n\t\
|
||||
{%- elif message[\"role\"] == \"user\" -%}\n\t\t{{- \"<|user|>\\n\" + message[\"\
|
||||
content\"] + \"\\n\" -}}\n\t{%- elif message[\"role\"] == \"assistant\" -%}\n\t\t\
|
||||
{%- if not loop.last -%}\n\t\t\t{{- \"<|assistant|>\\n\" -}}{% generation %}{{-\
|
||||
\ message[\"content\"] + eos_token -}}{% endgeneration %}{{- \"\\n\" -}}\n\t\t{%-\
|
||||
\ else -%}\n\t\t\t{{- \"<|assistant|>\\n\" -}}{% generation %}{{- message[\"content\"\
|
||||
] + eos_token -}}{% endgeneration %}\n\t\t{%- endif -%}\n\t{%- endif -%}\n\t{%-\
|
||||
\ if loop.last and add_generation_prompt -%}\n\t\t{{- \"<|assistant|>\\n\" -}}\n\
|
||||
\t{%- endif -%}\n{%- endfor -%}\n"
|
||||
additional_special_tokens:
|
||||
- <|system|>
|
||||
- <|user|>
|
||||
- <|assistant|>
|
||||
dataset_mixture:
|
||||
datasets:
|
||||
- id: ali-elganzory/tulu-3-sft-mixture-decontaminated
|
||||
config: default
|
||||
split: train
|
||||
columns:
|
||||
- messages
|
||||
dataset_num_proc: 32
|
||||
eval_strategy: 'no'
|
||||
remove_unused_columns: true
|
||||
dataset_kwargs:
|
||||
add_special_tokens: false
|
||||
append_concat_token: false
|
||||
output_dir: results/sft/ali-elganzory-SmolLM2-1.7B-WithChatTemplate_tulu-3-sft-mixture-decontaminated_H100-masked
|
||||
overwrite_output_dir: false
|
||||
save_strategy: steps
|
||||
save_steps: 200
|
||||
save_total_limit: 2
|
||||
push_to_hub: 'False'
|
||||
log_level: info
|
||||
report_to:
|
||||
- wandb
|
||||
logging_steps: 10
|
||||
logging_strategy: steps
|
||||
seed: 42
|
||||
bf16: true
|
||||
gradient_checkpointing: true
|
||||
learning_rate: 5.0e-06
|
||||
lr_scheduler_type: linear
|
||||
max_length: 4096
|
||||
warmup_ratio: 0.03
|
||||
num_train_epochs: 2
|
||||
per_device_train_batch_size: 16
|
||||
gradient_accumulation_steps: 1
|
||||
assistant_only_loss: true
|
||||
hub_model_id: ali-elganzory/SmolLM2-1.7B-SFT-Tulu3-decontaminated-masked
|
||||
hub_strategy: every_save
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 2,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
48901
merges.txt
Normal file
48901
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be30dbe0c2987d042336477b9701dc78ec1a636524143d92ab922fc4027dc9ed
|
||||
size 3423040096
|
||||
55
special_tokens_map.json
Normal file
55
special_tokens_map.json
Normal file
@@ -0,0 +1,55 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
{
|
||||
"content": "<|system|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
{
|
||||
"content": "<|user|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
{
|
||||
"content": "<|assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
244976
tokenizer.json
Normal file
244976
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
181
tokenizer_config.json
Normal file
181
tokenizer_config.json
Normal file
@@ -0,0 +1,181 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<repo_name>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "<reponame>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "<file_sep>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "<filename>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<gh_stars>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<issue_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<issue_comment>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "<issue_closed>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "<jupyter_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"12": {
|
||||
"content": "<jupyter_text>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"13": {
|
||||
"content": "<jupyter_code>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"14": {
|
||||
"content": "<jupyter_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"15": {
|
||||
"content": "<jupyter_script>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"16": {
|
||||
"content": "<empty_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49152": {
|
||||
"content": "<|system|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49153": {
|
||||
"content": "<|user|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49154": {
|
||||
"content": "<|assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|system|>",
|
||||
"<|user|>",
|
||||
"<|assistant|>"
|
||||
],
|
||||
"bos_token": "<|im_start|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 8192,
|
||||
"pad_token": "<|im_end|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"total_flos": 3199489317601280.0,
|
||||
"train_loss": 0.7106047359356158,
|
||||
"train_runtime": 48891.9802,
|
||||
"train_samples": 936509,
|
||||
"train_samples_per_second": 38.309,
|
||||
"train_steps_per_second": 0.299
|
||||
}
|
||||
14676
trainer_state.json
Normal file
14676
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:311bd9ae38ba25b350da3f0670d544dcad517776e874ab33629a64f56f2bf3ce
|
||||
size 8248
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user