初始化项目，由ModelHub XC社区提供模型
Model: mobiuslabsgmbh/aanaphi2-v0.1 Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
67
README.md
Normal file
67
README.md
Normal file
@@ -0,0 +1,67 @@
|
||||
---
|
||||
license: mit
|
||||
train: false
|
||||
inference: false
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
*aanaphi2-v0.1* is a finetuned (SFT + DPO) chat model based on <a href="https://huggingface.co/microsoft/phi-2">Microsoft's Phi-2 base model</a> (2.8B parameters).
|
||||
|
||||
|
||||
|
||||
## Performance
|
||||
| Models | phi-2 | aanaphi2-v0.1 |
|
||||
|-------------------|------------------|------------------|
|
||||
| ARC (25-shot) | 61.09 | <b>63.74</b> |
|
||||
| HellaSwag (10-shot)| 75.11 | <b>78.30</b> |
|
||||
| MMLU (5-shot) | <b>58.11</b> | 57.70 |
|
||||
| TruthfulQA-MC2 | 44.47 | <b>51.56</b> |
|
||||
| Winogrande (5-shot)| <b>74.35</b> | 73.40 |
|
||||
| GSM8K (5-shot) | 54.81 | <b>58.61</b> |
|
||||
| Average | 61.33 | <b>63.89</b> |
|
||||
|
||||
|
||||
## Installation
|
||||
Make sure you have the latest version of the transformers library:
|
||||
```
|
||||
pip install pip --upgrade && pip install transformers --upgrade
|
||||
```
|
||||
|
||||
## Basic Usage
|
||||
``` Python
|
||||
#Load model
|
||||
import transformers, torch
|
||||
|
||||
#GPU runtime
|
||||
device = 'cuda'
|
||||
compute_dtype = torch.float16
|
||||
|
||||
##CPU runtime
|
||||
#device = 'cpu'
|
||||
#compute_dtype = torch.float32
|
||||
|
||||
cache_path = ''
|
||||
model_id = "mobiuslabsgmbh/aanaphi2-v0.1"
|
||||
model = transformers.AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=compute_dtype,
|
||||
cache_dir=cache_path,
|
||||
device_map=device)
|
||||
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id, cache_dir=cache_path)
|
||||
|
||||
#Set Prompt format
|
||||
instruction_template = "### Human: "
|
||||
response_template = "### Assistant: "
|
||||
def prompt_format(prompt):
|
||||
out = instruction_template + prompt + '\n' + response_template
|
||||
return out
|
||||
model.eval();
|
||||
|
||||
@torch.no_grad()
|
||||
def generate(prompt, max_length=1024):
|
||||
prompt_chat = prompt_format(prompt)
|
||||
inputs = tokenizer(prompt_chat, return_tensors="pt", return_attention_mask=True).to(device)
|
||||
outputs = model.generate(**inputs, max_length=max_length, eos_token_id= tokenizer.eos_token_id)
|
||||
text = tokenizer.batch_decode(outputs[:,:-1])[0]
|
||||
return text
|
||||
|
||||
#Generate
|
||||
print(generate('If A+B=C and B=C, what would be the value of A?'))
|
||||
```
|
||||
41
added_tokens.json
Normal file
41
added_tokens.json
Normal file
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"\t\t": 50294,
|
||||
"\t\t\t": 50293,
|
||||
"\t\t\t\t": 50292,
|
||||
"\t\t\t\t\t": 50291,
|
||||
"\t\t\t\t\t\t": 50290,
|
||||
"\t\t\t\t\t\t\t": 50289,
|
||||
"\t\t\t\t\t\t\t\t": 50288,
|
||||
"\t\t\t\t\t\t\t\t\t": 50287,
|
||||
" ": 50286,
|
||||
" ": 50285,
|
||||
" ": 50284,
|
||||
" ": 50283,
|
||||
" ": 50282,
|
||||
" ": 50281,
|
||||
" ": 50280,
|
||||
" ": 50279,
|
||||
" ": 50278,
|
||||
" ": 50277,
|
||||
" ": 50276,
|
||||
" ": 50275,
|
||||
" ": 50274,
|
||||
" ": 50273,
|
||||
" ": 50272,
|
||||
" ": 50271,
|
||||
" ": 50270,
|
||||
" ": 50269,
|
||||
" ": 50268,
|
||||
" ": 50267,
|
||||
" ": 50266,
|
||||
" ": 50265,
|
||||
" ": 50264,
|
||||
" ": 50263,
|
||||
" ": 50262,
|
||||
" ": 50261,
|
||||
" ": 50260,
|
||||
" ": 50259,
|
||||
" ": 50258,
|
||||
" ": 50257,
|
||||
"[PAD]": 50295
|
||||
}
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"architectures": [
|
||||
"PhiForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "gelu_new",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 10240,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "phi",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"partial_rotary_factor": 0.4,
|
||||
"qk_layernorm": false,
|
||||
"resid_pdrop": 0.1,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.37.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.37.2"
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4b76e53221ef36ad00434769e6ec7533148114b22cf290a60e659b672041a201
|
||||
size 4995584424
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a1af717cc6d58e685a8a191b0c9be96916911b7a32e2e1c67ec2d6734f1bfab3
|
||||
size 563832976
|
||||
460
model.safetensors.index.json
Normal file
460
model.safetensors.index.json
Normal file
@@ -0,0 +1,460 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5559367680
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.bias": "model-00002-of-00002.safetensors",
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.final_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"model.final_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
100656
tokenizer.json
Normal file
100656
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
337
tokenizer_config.json
Normal file
337
tokenizer_config.json
Normal file
@@ -0,0 +1,337 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"50256": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50257": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50270": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50271": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50272": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50273": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50274": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50275": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50276": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50277": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50278": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50279": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50280": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50281": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50282": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50283": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50284": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50285": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50286": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50287": {
|
||||
"content": "\t\t\t\t\t\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50288": {
|
||||
"content": "\t\t\t\t\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50289": {
|
||||
"content": "\t\t\t\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50290": {
|
||||
"content": "\t\t\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50291": {
|
||||
"content": "\t\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50292": {
|
||||
"content": "\t\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50293": {
|
||||
"content": "\t\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50294": {
|
||||
"content": "\t\t",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50295": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'### Human: ' + message['content'].strip() + '\n' }}{% elif message['role'] == 'assistant' %}{{'### Assistant: ' + message['content'].strip() + '\n'}}{% endif %}{% endfor %}",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"max_length": 512,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "[PAD]",
|
||||
"stride": 0,
|
||||
"tokenizer_class": "CodeGenTokenizer",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
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