argilla/SmolLM2-360M-synthetic-concise-reasoning
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: argilla/SmolLM2-360M-synthetic-concise-reasoning
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-03 01:12:15 +08:00
commit 18f3f47552
20 changed files with 294210 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View 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
model.safetensors filter=lfs diff=lfs merge=lfs -text

64
README.md Normal file
View File

@@ -0,0 +1,64 @@
---
base_model: HuggingFaceTB/SmolLM2-360M
library_name: transformers
model_name: SmolLM2-360M-synthetic-concise-reasoning
tags:
- generated_from_trainer
- trl
- sft
- datacraft
licence: license
license: apache-2.0
datasets:
- argilla/synthetic-concise-reasoning-sft-filtered
language:
- en
---
# Model Card for SmolLM2-360M-synthetic-concise-reasoning
This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M).
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="argilla/SmolLM2-360M-synthetic-concise-reasoning", 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: 0.13.0
- Transformers: 4.48.0.dev0
- Pytorch: 2.5.0
- Datasets: 3.1.0
- Tokenizers: 0.21.0
## 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 Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```

33
config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"_name_or_path": "HuggingFaceTB/SmolLM2-360M",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 960,
"initializer_range": 0.02,
"intermediate_size": 2560,
"is_llama_config": true,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 15,
"num_hidden_layers": 32,
"num_key_value_heads": 5,
"pad_token_id": 2,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_interleaved": false,
"rope_scaling": null,
"rope_theta": 100000,
"tie_word_embeddings": true,
"torch_dtype": "float32",
"transformers_version": "4.48.0.dev0",
"use_cache": true,
"vocab_size": 49152
}

1
configuration.json Normal file
View File

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

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 2,
"transformers_version": "4.48.0.dev0"
}

48901
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ff53b73048cd1ae43614f62cce6cf551c32f9c856513fc60de946c6996039fb4
size 1447317080

3
runs/Jan03_15-00-35_Davids-MacBook-Pro.local/events.out.tfevents.1735912836.Davids-MacBook-Pro.local.38035.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7fb23a2a6718048d51fd35da87a6e9b90390d9b05d3b76783a851c670b8ac629
size 6193

3
runs/Jan03_15-06-35_Davids-MacBook-Pro.local/events.out.tfevents.1735913196.Davids-MacBook-Pro.local.38939.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:50b93f12e4eefdc2f03ac45dd0301ee26733936a56d8bc5e359dee0d27039322
size 5563

3
runs/Jan03_15-07-36_Davids-MacBook-Pro.local/events.out.tfevents.1735913257.Davids-MacBook-Pro.local.39079.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:152a210df90a494d555413f0b1f8cd2ec2dce7d3390f404e4504379bbbaa6a0d
size 6969

3
runs/Jan03_15-24-08_Davids-MacBook-Pro.local/events.out.tfevents.1735914250.Davids-MacBook-Pro.local.41301.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61f76cfbf346869c90b8c681bf3b5c3e413c5d479e30754eb6670eea814d6649
size 5564

3
runs/Jan03_15-25-07_Davids-MacBook-Pro.local/events.out.tfevents.1735914308.Davids-MacBook-Pro.local.41510.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0e47a116031d7e9e160313268983b967872f35af95ea7826f3159227a63cf076
size 5561

3
runs/Jan03_15-28-09_Davids-MacBook-Pro.local/events.out.tfevents.1735914490.Davids-MacBook-Pro.local.42024.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:48bd740635347454093171dcc6baac67a146daa54ffdc13b1ed476e271926f3f
size 5549

3
runs/Jan03_15-31-59_Davids-MacBook-Pro.local/events.out.tfevents.1735914720.Davids-MacBook-Pro.local.42510.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eab17d5d34f956741e2bfbf0c977be42e4be69eed09819ce96029a0f12ffcc42
size 5896

3
runs/Jan03_15-38-49_Davids-MacBook-Pro.local/events.out.tfevents.1735915130.Davids-MacBook-Pro.local.43370.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ba23b1deaddde36a85ebd31801c7bfd729e246b304996bad8201f54db7240232
size 6954

28
special_tokens_map.json Normal file
View File

@@ -0,0 +1,28 @@
{
"additional_special_tokens": [
{
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
],
"bos_token": "<|im_start|>",
"eos_token": "<|im_end|>",
"pad_token": "<|im_end|>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

244954
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

155
tokenizer_config.json Normal file
View File

@@ -0,0 +1,155 @@
{
"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
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": "<|im_start|>",
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"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
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de0245cd4c3440d4a3c2134039ad5e248b6e8224b97af592d88eb8986cacacc2
size 5624

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long