meftah416/SmolLM-eppy-360m
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: meftah416/SmolLM-eppy-360m
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-13 13:37:32 +08:00
commit f86098fba9
7 changed files with 245225 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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

23
README.md Normal file
View File

@@ -0,0 +1,23 @@
---
base_model: unsloth/SmolLM-360M
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** meftah416
- **License:** apache-2.0
- **Finetuned from model :** unsloth/SmolLM-360M
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

35
config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"dtype": "bfloat16",
"eos_token_id": 0,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 960,
"initializer_range": 0.02,
"intermediate_size": 2560,
"max_position_embeddings": 4500,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 15,
"num_hidden_layers": 32,
"num_key_value_heads": 5,
"pad_token_id": 16,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"factor": 2.197265625,
"rope_theta": 10000.0,
"rope_type": "linear",
"type": "linear"
},
"tie_word_embeddings": true,
"transformers_version": "5.5.0",
"unsloth_version": "2026.5.10",
"use_cache": false,
"vocab_size": 49152
}

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"bos_token_id": 0,
"eos_token_id": [
0
],
"max_length": 4500,
"pad_token_id": 16,
"transformers_version": "5.5.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24908a6ef93e5da3a54bafee1354598c6070013acb1399a319cf21e7b71339fc
size 723674912

244965
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,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"extra_special_tokens": [],
"is_local": false,
"model_max_length": 4500,
"pad_token": "<empty_output>",
"padding_side": "left",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>",
"vocab_size": 49152,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"1": {
"content": "<|im_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"2": {
"content": "<|im_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"3": {
"content": "<repo_name>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"4": {
"content": "<reponame>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"5": {
"content": "<file_sep>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"6": {
"content": "<filename>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"7": {
"content": "<gh_stars>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"8": {
"content": "<issue_start>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"9": {
"content": "<issue_comment>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"10": {
"content": "<issue_closed>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"11": {
"content": "<jupyter_start>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"12": {
"content": "<jupyter_text>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"13": {
"content": "<jupyter_code>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"14": {
"content": "<jupyter_output>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"15": {
"content": "<jupyter_script>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"16": {
"content": "<empty_output>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
}
}