初始化项目，由ModelHub XC社区提供模型
Model: ModelCloud.AI/Marin-32B-Base-GPTQMODEL-AWQ-W4A16 Source: Original Platform
This commit is contained in:
ModelHub XC
54
.gitattributes
vendored
Normal file
54
.gitattributes
vendored
Normal file
@@ -0,0 +1,54 @@
|
||||
*.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
|
||||
|
||||
*.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
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
57
README.md
Normal file
57
README.md
Normal file
@@ -0,0 +1,57 @@
|
||||
---
|
||||
license: other
|
||||
license_name: modelcloud
|
||||
license_link: LICENSE
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- marin-community/marin-32b-base
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- gptqmodel
|
||||
- modelcloud
|
||||
- chat
|
||||
- marin
|
||||
- instruct
|
||||
- int4
|
||||
- awq
|
||||
- 4bit
|
||||
- w4a16
|
||||
---
|
||||
|
||||
This 4bit W4A16 model has been quantized by <a href='https://x.com/qubitium'>@Qubitum</a> at ModelCloud using
|
||||
[GPT-QModel](https://github.com/ModelCloud/GPTQModel).
|
||||
|
||||
```
|
||||
SPDX-License-Identifier: NonCommercial-ModelCloud
|
||||
Copyright (c) 2024–2025 ModelCloud.ai
|
||||
Released for non-profit use only.
|
||||
Commercial use requires permission from [@qubitium](https://x.com/qubitium).
|
||||
```
|
||||
|
||||
```py
|
||||
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
||||
|-------------------------------|------:|------|-----:|--------|---|-----:|---|-----:|
|
||||
|arc_challenge | 1|none | 0|acc |↑ |0.5828|± |0.0144|
|
||||
| | |none | 0|acc_norm|↑ |0.6007|± |0.0143|
|
||||
|mmlu (stem) | 2|none | |acc |↑ |0.6673|± |0.0080|
|
||||
| - abstract_algebra | 1|none | 0|acc |↑ |0.4200|± |0.0496|
|
||||
| - anatomy | 1|none | 0|acc |↑ |0.7185|± |0.0389|
|
||||
| - astronomy | 1|none | 0|acc |↑ |0.8553|± |0.0286|
|
||||
| - college_biology | 1|none | 0|acc |↑ |0.8681|± |0.0283|
|
||||
| - college_chemistry | 1|none | 0|acc |↑ |0.5300|± |0.0502|
|
||||
| - college_computer_science | 1|none | 0|acc |↑ |0.6300|± |0.0485|
|
||||
| - college_mathematics | 1|none | 0|acc |↑ |0.4800|± |0.0502|
|
||||
| - college_physics | 1|none | 0|acc |↑ |0.5686|± |0.0493|
|
||||
| - computer_security | 1|none | 0|acc |↑ |0.7800|± |0.0416|
|
||||
| - conceptual_physics | 1|none | 0|acc |↑ |0.7660|± |0.0277|
|
||||
| - electrical_engineering | 1|none | 0|acc |↑ |0.7379|± |0.0366|
|
||||
| - elementary_mathematics | 1|none | 0|acc |↑ |0.6296|± |0.0249|
|
||||
| - high_school_biology | 1|none | 0|acc |↑ |0.8710|± |0.0191|
|
||||
| - high_school_chemistry | 1|none | 0|acc |↑ |0.6453|± |0.0337|
|
||||
| - high_school_computer_science| 1|none | 0|acc |↑ |0.7800|± |0.0416|
|
||||
| - high_school_mathematics | 1|none | 0|acc |↑ |0.4481|± |0.0303|
|
||||
| - high_school_physics | 1|none | 0|acc |↑ |0.5166|± |0.0408|
|
||||
| - high_school_statistics | 1|none | 0|acc |↑ |0.6620|± |0.0323|
|
||||
| - machine_learning | 1|none | 0|acc |↑ |0.5714|± |0.0470|
|
||||
```
|
||||
132
config.json
Normal file
132
config.json
Normal file
@@ -0,0 +1,132 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"decoder_start_token_id": 128000,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 128001,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 27648,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 4096,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"no_bias": true,
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 64,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 128004,
|
||||
"quantization_config": {
|
||||
"bits": 4,
|
||||
"checkpoint_format": "gemm",
|
||||
"desc_act": false,
|
||||
"group_size": 32,
|
||||
"lm_head": false,
|
||||
"meta": {
|
||||
"act_group_aware": true,
|
||||
"damp_auto_increment": 0.01,
|
||||
"damp_percent": 0.05,
|
||||
"mse": 0.0,
|
||||
"quantizer": [
|
||||
"gptqmodel:5.1.0-dev"
|
||||
],
|
||||
"static_groups": false,
|
||||
"true_sequential": true,
|
||||
"uri": "https://github.com/modelcloud/gptqmodel",
|
||||
"v2": false,
|
||||
"v2_alpha": 0.25
|
||||
},
|
||||
"pack_dtype": "int32",
|
||||
"pack_impl": "cpu",
|
||||
"quant_method": "awq",
|
||||
"sym": true,
|
||||
"version": "gemm",
|
||||
"zero_point": true
|
||||
},
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"begin_suppress_tokens": [
|
||||
128000,
|
||||
128001
|
||||
],
|
||||
"bos_token_id": 128000,
|
||||
"decoder_start_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 128001,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:604a76a961b82ab7b1da1bbb5ce2164e7b0acfa0529316ad385c4b66281f1744
|
||||
size 4237562376
|
||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d5537d739d9a467295c6e9c2ee08e1d9688307c7dee3eb6b9a11c32dd6ac9db8
|
||||
size 4228336722
|
||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1509de8ca951fa7b194262a8aaf427d9005befc87645ab0c8fe1a59985c73b64
|
||||
size 4228336809
|
||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:25797d9560d75148a48202c11e5a2d772a6606f954217f5c6fbcd17fb457189f
|
||||
size 4228336809
|
||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:845c344811e5fafd283822a20a5362a9050d47cb4ce041767b5fb1af9be0003f
|
||||
size 3746397321
|
||||
1611
model.safetensors.index.json
Normal file
1611
model.safetensors.index.json
Normal file
File diff suppressed because it is too large
Load Diff
27
quantize_config.json
Normal file
27
quantize_config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"bits": 4,
|
||||
"group_size": 32,
|
||||
"desc_act": false,
|
||||
"sym": true,
|
||||
"lm_head": false,
|
||||
"quant_method": "awq",
|
||||
"checkpoint_format": "gemm",
|
||||
"pack_dtype": "int32",
|
||||
"meta": {
|
||||
"quantizer": [
|
||||
"gptqmodel:5.1.0-dev"
|
||||
],
|
||||
"uri": "https://github.com/modelcloud/gptqmodel",
|
||||
"damp_percent": 0.05,
|
||||
"damp_auto_increment": 0.01,
|
||||
"static_groups": false,
|
||||
"true_sequential": true,
|
||||
"mse": 0.0,
|
||||
"v2": false,
|
||||
"v2_alpha": 0.25,
|
||||
"act_group_aware": true
|
||||
},
|
||||
"pack_impl": "cpu",
|
||||
"zero_point": true,
|
||||
"version": "gemm"
|
||||
}
|
||||
17
special_tokens_map.json
Normal file
17
special_tokens_map.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|finetune_right_pad_id|>"
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
2063
tokenizer_config.json
Normal file
2063
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user