初始化项目,由ModelHub XC社区提供模型
Model: bartowski/wavecoder-ultra-1.1-6.7b-AWQ Source: Original Platform
This commit is contained in:
commit
5102c29296
9 files changed
+64515
No files matched your search
@@ -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
|
||||
@@ -0,0 +1,97 @@
|
||||
---
|
||||
license: mit
|
||||
license_link: https://huggingface.co/microsoft/wavecoder-ultra-6.7b/blob/main/LICENSE
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
datasets:
|
||||
- humaneval
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- code
|
||||
metrics:
|
||||
- code_eval
|
||||
quantized_by: bartowski
|
||||
---
|
||||
|
||||
## 4-bit GEMM AWQ Quantizations of wavecoder-ultra-1.1-6.7b
|
||||
|
||||
Using <a href="https://github.com/casper-hansen/AutoAWQ/">AutoAWQ</a> release <a href="https://github.com/casper-hansen/AutoAWQ/releases/tag/v0.2.4">v0.2.4</a> for quantization.
|
||||
|
||||
Original model: https://huggingface.co/microsoft/wavecoder-ultra-6.7b
|
||||
|
||||
Note: They updated the model in place, no idea if there's actually any changes, but tagging this 1.1 just in case
|
||||
|
||||
## Prompt format
|
||||
|
||||
No chat template specified so default is used. This may be incorrect, check original model card for details.
|
||||
|
||||
```
|
||||
<|begin▁of▁sentence|>[INST] <<SYS>>
|
||||
{system_prompt}
|
||||
<</SYS>>
|
||||
|
||||
{prompt} [/INST] <|end▁of▁sentence|>
|
||||
```
|
||||
|
||||
## AWQ Parameters
|
||||
|
||||
- q_group_size: 128
|
||||
- w_bit: 4
|
||||
- zero_point: True
|
||||
- version: GEMM
|
||||
|
||||
## How to run
|
||||
|
||||
From the AutoAWQ repo [here](https://github.com/casper-hansen/AutoAWQ/blob/main/examples/generate.py)
|
||||
|
||||
First install autoawq pypi package:
|
||||
|
||||
```
|
||||
pip install autoawq
|
||||
```
|
||||
|
||||
Then run the following:
|
||||
|
||||
```
|
||||
from awq import AutoAWQForCausalLM
|
||||
from transformers import AutoTokenizer, TextStreamer
|
||||
|
||||
|
||||
quant_path = "models/wavecoder-ultra-1.1-6.7b-AWQ"
|
||||
|
||||
# Load model
|
||||
model = AutoAWQForCausalLM.from_quantized(quant_path, fuse_layers=True)
|
||||
tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
|
||||
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
|
||||
|
||||
prompt = "You're standing on the surface of the Earth. "\
|
||||
"You walk one mile south, one mile west and one mile north. "\
|
||||
"You end up exactly where you started. Where are you?"
|
||||
|
||||
chat = [
|
||||
{"role": "system", "content": "You are a concise assistant that helps answer questions."},
|
||||
{"role": "user", "content": prompt},
|
||||
]
|
||||
|
||||
# <|eot_id|> used for llama 3 models
|
||||
terminators = [
|
||||
tokenizer.eos_token_id,
|
||||
tokenizer.convert_tokens_to_ids("<|eot_id|>")
|
||||
]
|
||||
|
||||
tokens = tokenizer.apply_chat_template(
|
||||
chat,
|
||||
return_tensors="pt"
|
||||
).cuda()
|
||||
|
||||
# Generate output
|
||||
generation_output = model.generate(
|
||||
tokens,
|
||||
streamer=streamer,
|
||||
max_new_tokens=64,
|
||||
eos_token_id=terminators
|
||||
)
|
||||
```
|
||||
|
||||
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
||||
+39
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"_name_or_path": "/models/wavecoder-ultra-1.1-6.7b/",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 32013,
|
||||
"eos_token_id": 32014,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 16384,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pretraining_tp": 1,
|
||||
"quantization_config": {
|
||||
"bits": 4,
|
||||
"group_size": 128,
|
||||
"modules_to_not_convert": null,
|
||||
"quant_method": "awq",
|
||||
"version": "gemm",
|
||||
"zero_point": true
|
||||
},
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"factor": 4.0,
|
||||
"type": "linear"
|
||||
},
|
||||
"rope_theta": 100000,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.39.3",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32023
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 32013,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 32014,
|
||||
"transformers_version": "4.39.3"
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dfab4090b0b49aa8d58bc68aa4bbbba6e168e61dfceb78ff2265b9796b050eca
|
||||
size 3889768344
|
||||
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin▁of▁sentence|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end▁of▁sentence|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|end▁of▁sentence|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
+64095
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,207 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"32000": {
|
||||
"content": "õ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32001": {
|
||||
"content": "÷",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32002": {
|
||||
"content": "Á",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32003": {
|
||||
"content": "ý",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32004": {
|
||||
"content": "À",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32005": {
|
||||
"content": "ÿ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32006": {
|
||||
"content": "ø",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32007": {
|
||||
"content": "ú",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32008": {
|
||||
"content": "þ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32009": {
|
||||
"content": "ü",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32010": {
|
||||
"content": "ù",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32011": {
|
||||
"content": "ö",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32012": {
|
||||
"content": "û",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32013": {
|
||||
"content": "<|begin▁of▁sentence|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32014": {
|
||||
"content": "<|end▁of▁sentence|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32015": {
|
||||
"content": "<|fim▁hole|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32016": {
|
||||
"content": "<|fim▁begin|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32017": {
|
||||
"content": "<|fim▁end|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32018": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32019": {
|
||||
"content": "<|User|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32020": {
|
||||
"content": "<|Assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32021": {
|
||||
"content": "<|EOT|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32022": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<|begin▁of▁sentence|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|end▁of▁sentence|>",
|
||||
"legacy": true,
|
||||
"max_length": 2048,
|
||||
"model_max_length": 2048,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "<|end▁of▁sentence|>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"stride": 0,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in new issue
Block a user