初始化项目，由ModelHub XC社区提供模型
Model: Minami-su/Qwen1.5-7B-Chat_llamafy Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal 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
|
||||
64
README.md
Normal file
64
README.md
Normal file
@@ -0,0 +1,64 @@
|
||||
---
|
||||
license: other
|
||||
license_name: qwen
|
||||
license_link: >-
|
||||
https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
|
||||
language:
|
||||
- en
|
||||
- zh
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
inference: false
|
||||
tags:
|
||||
- llama
|
||||
- qwen
|
||||
- qwen1.5
|
||||
- qwen2
|
||||
---
|
||||
This is the LLaMAfied version of [Qwen1.5-7B-Chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat) model by Alibaba Cloud.
|
||||
The original codebase can be found at: (https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_qwen.py).
|
||||
I have made modifications to make it compatible with qwen1.5.
|
||||
This model is converted with https://github.com/Minami-su/character_AI_open/blob/main/llamafy_qwen_v2.py
|
||||
|
||||
Usage:
|
||||
|
||||
```python
|
||||
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
|
||||
tokenizer = AutoTokenizer.from_pretrained("Minami-su/Qwen1.5-7B-Chat_llamafy")
|
||||
model = AutoModelForCausalLM.from_pretrained("Minami-su/Qwen1.5-7B-Chat_llamafy", torch_dtype="auto", device_map="auto")
|
||||
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "Who are you?"}
|
||||
]
|
||||
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
|
||||
inputs = inputs.to("cuda")
|
||||
generate_ids = model.generate(inputs,max_length=2048, streamer=streamer)
|
||||
|
||||
```
|
||||
|
||||
## Test
|
||||
load in 4bit
|
||||
```
|
||||
hf-causal (pretrained=Qwen1.5-7B-Chat), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
|
||||
| Task |Version| Metric |Value | |Stderr|
|
||||
|-------------|------:|--------|-----:|---|-----:|
|
||||
|arc_challenge| 0|acc |0.4155|± |0.0144|
|
||||
| | |acc_norm|0.4480|± |0.0145|
|
||||
|truthfulqa_mc| 1|mc1 |0.3513|± |0.0167|
|
||||
| | |mc2 |0.5165|± |0.0159|
|
||||
|winogrande | 0|acc |0.6330|± |0.0135|
|
||||
```
|
||||
load in 4bit
|
||||
```
|
||||
hf-causal (pretrained=Qwen1.5-7B-Chat_llamafy), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
|
||||
| Task |Version| Metric |Value | |Stderr|
|
||||
|-------------|------:|--------|-----:|---|-----:|
|
||||
|arc_challenge| 0|acc |0.4172|± |0.0144|
|
||||
| | |acc_norm|0.4488|± |0.0145|
|
||||
|truthfulqa_mc| 1|mc1 |0.3501|± |0.0167|
|
||||
| | |mc2 |0.5164|± |0.0159|
|
||||
|winogrande | 0|acc |0.6306|± |0.0136|
|
||||
```
|
||||
```
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": true,
|
||||
"attention_dropout": 0.0,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 4096,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_scaling": null,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.37.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
11
generation_config.json
Normal file
11
generation_config.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"repetition_penalty": 1.1,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.37.0"
|
||||
}
|
||||
151387
merges.txt
Normal file
151387
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model-00001-of-00008.bin
Normal file
3
pytorch_model-00001-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7a6c51619caffe77ea1e294a1a10497c563a55b18684937f5bd2653753449c4f
|
||||
size 1990464810
|
||||
3
pytorch_model-00002-of-00008.bin
Normal file
3
pytorch_model-00002-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a494c95534b083e5119f3b4b065061b0fd46f5e29affafc102e3be571e7fa084
|
||||
size 1967396412
|
||||
3
pytorch_model-00003-of-00008.bin
Normal file
3
pytorch_model-00003-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5076c332048d8bb109b633fcc8598ef6a427901b5f0dddc4abe734e70faae148
|
||||
size 1987150170
|
||||
3
pytorch_model-00004-of-00008.bin
Normal file
3
pytorch_model-00004-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:318bb3e54428eb560c9ca1e279b50ddf02f7e8800f1d3f4cc513b7772848e3d5
|
||||
size 1967387882
|
||||
3
pytorch_model-00005-of-00008.bin
Normal file
3
pytorch_model-00005-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:543e22cbb353c7bac8e46f8b543053a18382264152781cfaa6c8fe27882464de
|
||||
size 1953578404
|
||||
3
pytorch_model-00006-of-00008.bin
Normal file
3
pytorch_model-00006-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5407cbb5acf34777296f7b9210660017da611730f76063f352c020f292407c67
|
||||
size 1979952784
|
||||
3
pytorch_model-00007-of-00008.bin
Normal file
3
pytorch_model-00007-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ce7773b08390dff5976123d0c0dbf06e3725d10813a585ce10aa81633a3eaf16
|
||||
size 1933841706
|
||||
3
pytorch_model-00008-of-00008.bin
Normal file
3
pytorch_model-00008-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:68e5e7f2a70144140d17ec505543c35d951ed01a65e4930155372f46017dafdc
|
||||
size 1663282494
|
||||
426
pytorch_model.bin.index.json
Normal file
426
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,426 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 15442911232
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.self_attn.o_proj.bias": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.self_attn.o_proj.bias": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.1.self_attn.v_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.self_attn.o_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.self_attn.o_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.self_attn.o_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.self_attn.o_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.self_attn.o_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.self_attn.o_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.16.self_attn.o_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.17.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.17.self_attn.o_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.17.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.17.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.self_attn.o_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.self_attn.o_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.self_attn.k_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.self_attn.o_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.self_attn.q_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.self_attn.v_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.self_attn.o_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.self_attn.o_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.22.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.22.self_attn.o_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.22.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.22.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.self_attn.o_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.self_attn.o_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.self_attn.o_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.26.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.26.self_attn.o_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.26.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.26.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.k_proj.bias": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.o_proj.bias": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.q_proj.bias": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.v_proj.bias": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.self_attn.k_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.self_attn.o_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.self_attn.q_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.self_attn.v_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.k_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.o_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.q_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.v_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.self_attn.k_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.self_attn.o_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.self_attn.q_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.self_attn.v_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.k_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.o_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.q_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.v_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.k_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.o_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.q_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.v_proj.bias": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.self_attn.k_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.self_attn.o_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.self_attn.q_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.self_attn.v_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.self_attn.k_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.self_attn.o_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.self_attn.q_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.self_attn.v_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.self_attn.k_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.6.self_attn.o_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.6.self_attn.q_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.6.self_attn.v_proj.bias": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.o_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.o_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.o_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.norm.weight": "pytorch_model-00006-of-00008.bin"
|
||||
}
|
||||
}
|
||||
303111
tokenizer.json
Normal file
303111
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
40
tokenizer_config.json
Normal file
40
tokenizer_config.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
|
||||
"bos_token": null,
|
||||
"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|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user