初始化项目，由ModelHub XC社区提供模型
Model: vihangd/smartyplats-1.1b-v1 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
|
||||
11
README.md
Normal file
11
README.md
Normal file
@@ -0,0 +1,11 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
---
|
||||
<p><h1> SmartyPlats-1.1b V1 </h1></p>
|
||||
An experimental finetune of TinyLLaMA 1T with QLoRA
|
||||
|
||||
<h2> Datasets </h2>
|
||||
Trained on alpca style datasets
|
||||
|
||||
<p><h2> Prompt Template </h2></p>
|
||||
Uses alpaca style prompt template
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 5632,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 22,
|
||||
"num_key_value_heads": 4,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.35.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"max_length": 2048,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.35.0.dev0"
|
||||
}
|
||||
3
pytorch_model-00001-of-00006.bin
Normal file
3
pytorch_model-00001-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4055cef3499f62d796b53a8410bede33f9c8c9864a6453f79a91a9df329abda9
|
||||
size 395347554
|
||||
3
pytorch_model-00002-of-00006.bin
Normal file
3
pytorch_model-00002-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dba8cc3fbfea5feec2159b6374fab929865953fa9461bddeba8cee0f5bec6e57
|
||||
size 394311500
|
||||
3
pytorch_model-00003-of-00006.bin
Normal file
3
pytorch_model-00003-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a6a7129889c65f2b372d853aaaefe15c866273d804e0382a850acf31430cde24
|
||||
size 398513658
|
||||
3
pytorch_model-00004-of-00006.bin
Normal file
3
pytorch_model-00004-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c6984c4c426c803eee1da43b8cd016f2d115cdfb83f7b495ab3853b810236c89
|
||||
size 394311564
|
||||
3
pytorch_model-00005-of-00006.bin
Normal file
3
pytorch_model-00005-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:759126be07dc0aeeeec3732ec18f1f99c82ba0b76584457fed80583a00a219ef
|
||||
size 398513658
|
||||
3
pytorch_model-00006-of-00006.bin
Normal file
3
pytorch_model-00006-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d9c2778ac3abce0e6f730cd8251b91f364f4f8232b460b87048ebb6c4ecb3f67
|
||||
size 219169136
|
||||
208
pytorch_model.bin.index.json
Normal file
208
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 2200096768
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"model.norm.weight": "pytorch_model-00006-of-00006.bin"
|
||||
}
|
||||
}
|
||||
93391
tokenizer.json
Normal file
93391
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
35
tokenizer_config.json
Normal file
35
tokenizer_config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user