HuggingFaceTB/SmolLM2-1.7B-sft-only
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: HuggingFaceTB/SmolLM2-1.7B-sft-only
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-18 21:24:13 +08:00
commit 5e734f6db3
18 changed files with 150044 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

30
README.md Normal file
View File

@@ -0,0 +1,30 @@
---
base_model: HuggingFaceTB/SmolLM2-1.7B-8k
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- HuggingFaceTB/magpie-ultra-v1.0-filtered-400K-H4
- HuggingFaceTB/OpenHermes-2.5-H4-200k
- HuggingFaceTB/ifeval-like-data-36k-H4
- HuggingFaceTB/Numina-CoT-H4
- HuggingFaceTB/MetaMathQA-H4-200k
- HuggingFaceTB/self-oss-instruct-sc2-H4
- HuggingFaceTB/systemchats2.0-H4-short
- HuggingFaceTB/summarization-data-10k-H4
- HuggingFaceTB/everyday-conversations-llama3.1-2k
- HuggingFaceTB/apigen-smollm-trl-FC-H4
- HuggingFaceTB/smollm-v2-summarization
- HuggingFaceTB/smollm-v2-rewriting-50k-H4
- HuggingFaceTB/explore-instruct-rewrite-H4
- HuggingFaceTB/LongAlign-16k-ctx-english-H4
model-index:
- name: smollm2-1.7B-8k-mix7-ep2-v2
results: []
---
SFT only version of https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct

14
all_results.json Normal file
View File

@@ -0,0 +1,14 @@
{
"epoch": 1.9983216783216782,
"eval_loss": 1.0629972219467163,
"eval_runtime": 364.8237,
"eval_samples": 264435,
"eval_samples_per_second": 56.435,
"eval_steps_per_second": 1.765,
"total_flos": 1127451463778304.0,
"train_loss": 0.777597175032935,
"train_runtime": 16051.5455,
"train_samples": 1029132,
"train_samples_per_second": 14.253,
"train_steps_per_second": 0.111
}

30
config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"_name_or_path": "HuggingFaceTB/SmolLM2-1.7B-8k",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"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,
"torch_dtype": "bfloat16",
"transformers_version": "4.42.3",
"use_cache": true,
"vocab_size": 49152
}

1
configuration.json Normal file
View File

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

8
eval_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.9983216783216782,
"eval_loss": 1.0629972219467163,
"eval_runtime": 364.8237,
"eval_samples": 264435,
"eval_samples_per_second": 56.435,
"eval_steps_per_second": 1.765
}

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": "4.42.3"
}

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 sha256:98360aebc58238dc07b4bcb78b709b7eb24d639e50a662f6bbdb57f610f6779c
size 3422777952

3
runs/Oct30_23-27-03_ip-26-0-164-18/events.out.tfevents.1730332615.ip-26-0-164-18.40006.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0873dd28e429f1d2206edf9d1303fb97e99dda399fea3d137c0e2cff6cda7703
size 81405

3
runs/Oct30_23-27-03_ip-26-0-164-18/events.out.tfevents.1730349116.ip-26-0-164-18.40006.1 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa19fb272bb4a029c44102f050b0bff1860a9e41aedb1c6c91eea9ac982e4163
size 359

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
}
}

98249
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

154
tokenizer_config.json Normal file
View File

@@ -0,0 +1,154 @@
{
"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|>",
"model_max_length": 2048,
"pad_token": "<|im_end|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>",
"vocab_size": 49152
}

9
train_results.json Normal file
View File

@@ -0,0 +1,9 @@
{
"epoch": 1.9983216783216782,
"total_flos": 1127451463778304.0,
"train_loss": 0.777597175032935,
"train_runtime": 16051.5455,
"train_samples": 1029132,
"train_samples_per_second": 14.253,
"train_steps_per_second": 0.111
}

2564
trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:290d7ecc3e2f19388b5c15b1a5cf555114883a038f5dc255f5173455bbbea8a2
size 6392

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long