初始化项目，由ModelHub XC社区提供模型
Model: netcat420/MFANN3b 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
|
||||
26
README.md
Normal file
26
README.md
Normal file
@@ -0,0 +1,26 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: mit
|
||||
datasets:
|
||||
- netcat420/MFANN
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- netcat420/MFANN3b-SFT
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
FULL RELEASE!!!
|
||||
|
||||
introducing MFANN (Makhi's fully autonomous neural network) a family of COT models fine-tuned on a modified Alpaca training regiment involving defining a "thought-process" in the dataset in each sample, allowing the model to generate reasoning tokens before the model generates output (yes this has been in the works MUCH longer than o1 has been out!)
|
||||
|
||||
this is the smaller 3b model based on phi-2
|
||||
|
||||
the 8b model based on an abliterated llama 3.1 8b will be coming in the next few days!! stay tuned!!
|
||||
|
||||
If you would like to support me and keep this project going well into the future (or even free me up from the horrors of little caesars so i can work on this more lmfao) please consider donating to my patreon!! https://www.patreon.com/c/MakhiBurroughs all members get to vote on what gets done next with MFANN, addtional perks are currently in the works!
|
||||
|
||||
|
||||
system prompt:
|
||||
|
||||
Instruct: {instruction} Output:
|
||||
40
added_tokens.json
Normal file
40
added_tokens.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"\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
|
||||
}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_name_or_path": "liminerity/merge6",
|
||||
"architectures": [
|
||||
"PhiForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 50256,
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": 50256,
|
||||
"hidden_act": "gelu_new",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 10240,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 131072,
|
||||
"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": "bfloat16",
|
||||
"transformers_version": "4.38.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "4.46.3"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ee0ae228d8e42442eff2661bd313ccf4e49452cf1b1b66f24793b6f7fb654bfa
|
||||
size 4982355512
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:815f56613f19ab669c02a56cbe1d3a9d47412ca6144e98c8e93427904666a816
|
||||
size 4982541984
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:11b0b72c0d5120ac185811ce9ca73aa69ed58a81e101c8a3019cae39a3237408
|
||||
size 1153887616
|
||||
460
model.safetensors.index.json
Normal file
460
model.safetensors.index.json
Normal file
@@ -0,0 +1,460 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 11118735360
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.bias": "model-00003-of-00003.safetensors",
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.final_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.final_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.fc1.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
250648
tokenizer.json
Normal file
250648
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
324
tokenizer_config.json
Normal file
324
tokenizer_config.json
Normal file
@@ -0,0 +1,324 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 131072,
|
||||
"return_token_type_ids": false,
|
||||
"tokenizer_class": "CodeGenTokenizer",
|
||||
"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