rhluo9527/llama-160m
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: rhluo9527/llama-160m
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-28 14:46:10 +08:00
commit 9f9e255e61
21 changed files with 111856 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* 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
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

29
README.md Normal file
View File

@@ -0,0 +1,29 @@
---
license: apache-2.0
language:
- en
datasets:
- wikipedia
pipeline_tag: text-generation
---
## Model description
copy from https://huggingface.co/JackFram/llama-160m
This is a LLaMA-like model with only 160M parameters trained on Wikipedia and part of the C4-en and C4-realnewslike datasets.
No evaluation has been conducted yet, so use it with care.
The model is mainly developed as a base Small Speculative Model in the [SpecInfer](https://arxiv.org/abs/2305.09781) paper.
## Citation
To cite the model, please use
```bibtex
@misc{miao2023specinfer,
title={SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification},
author={Xupeng Miao and Gabriele Oliaro and Zhihao Zhang and Xinhao Cheng and Zeyu Wang and Rae Ying Yee Wong and Zhuoming Chen and Daiyaan Arfeen and Reyna Abhyankar and Zhihao Jia},
year={2023},
eprint={2305.09781},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```

162
_hf_internal_model_info.json Normal file
View File

@@ -0,0 +1,162 @@
{
"_id": "6470e3161f0e7ee7fb1e887d",
"id": "JackFram/llama-160m",
"private": false,
"pipeline_tag": "text-generation",
"library_name": "transformers",
"tags": [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"en",
"dataset:wikipedia",
"arxiv:2305.09781",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"downloads": 348491,
"likes": 35,
"modelId": "JackFram/llama-160m",
"author": "JackFram",
"sha": "aca9b687d1425f863dcf5de9a4c96e3fe36266dd",
"lastModified": "2024-01-04T09:26:17.000Z",
"gated": false,
"disabled": false,
"widgetData": [
{
"text": "My name is Julien and I like to"
},
{
"text": "I like traveling by train because"
},
{
"text": "Paris is an amazing place to visit,"
},
{
"text": "Once upon a time,"
}
],
"model-index": null,
"config": {
"architectures": [
"LlamaForCausalLM"
],
"model_type": "llama",
"tokenizer_config": {
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": null,
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
},
"additional_chat_templates": {}
},
"cardData": {
"license": "apache-2.0",
"language": [
"en"
],
"datasets": [
"wikipedia"
],
"pipeline_tag": "text-generation"
},
"transformersInfo": {
"auto_model": "AutoModelForCausalLM",
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
},
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "config.json"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model.safetensors"
},
{
"rfilename": "optimizer.pt"
},
{
"rfilename": "pytorch_model.bin"
},
{
"rfilename": "rng_state.pth"
},
{
"rfilename": "rng_state_0.pth"
},
{
"rfilename": "rng_state_1.pth"
},
{
"rfilename": "rng_state_2.pth"
},
{
"rfilename": "rng_state_3.pth"
},
{
"rfilename": "scheduler.pt"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer.model"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "trainer_state.json"
},
{
"rfilename": "training_args.bin"
}
],
"spaces": [],
"createdAt": "2023-05-26T16:49:26.000Z",
"safetensors": {
"parameters": {
"F32": 162417792
},
"total": 162417792
},
"usedStorage": 22444432762
}

23
config.json Normal file
View File

@@ -0,0 +1,23 @@
{
"_name_or_path": "JackFram/llama-160m",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"num_key_value_heads": 12,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.31.0.dev0",
"use_cache": true,
"vocab_size": 32000
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework":"Pytorch","task":"text-generation"}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0.dev0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3c89479bf6ca8dc8a6be5f78884caa3a5d95253f89b2a04a043720eaea479950
size 649684840

3
optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:739c87b934a445152ffb8345ff2d3f63170842e23dfecf033618722e226d7678
size 1299405253

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa6b1e0ff24eab3b6dfe1c84f8856a5f515dc687bda2dba74710d786d64dcf79
size 649712185

3
rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
size 14575

3
rng_state_0.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1eafe3d5e0585dde8c5033613de99a5d4f23df4284a488f4007b3944580c0b97
size 17655

3
rng_state_1.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e34eb456d2d003a2839f2daa9425e99bdd79ed7e24a1de9fc7d5738476bfb4b
size 17655

3
rng_state_2.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b374af4a2765d8771cee7a72921d3c2e438b9bee34f0b2d098ce6071afeb65e4
size 17655

3
rng_state_3.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5df75d8477fcc69c7abb03025313915ebfe3ac18c54a7c57aaa455c0099e13e5
size 17655

3
scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fbee4f91402d2995215f75eb802ad0f3303a5303d5847c5cbbf70a4ec511b9e2
size 627

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

93391
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

35
tokenizer_config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

18106
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:caa5aebd2b89a3a9ffc0f4b603243c329bf10889ce997948686829fc0b7b361d
size 3899