TinyPixel/testmodel-3
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: TinyPixel/testmodel-3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 22:05:10 +08:00
commit 4a67df82d5
37 changed files with 94225 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.34.0.dev0",
"use_cache": true,
"vocab_size": 32000
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.34.0.dev0"
}

3
model-00001-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a15f9c995f3c54ea6660a1530a3217291bc8a3fcfe91596f73f10c9f0661c3c0
size 981485368

3
model-00002-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97dd87c31cb3c27684aaa624da9864d6444f163fb11aa066eb7dc7922a131134
size 966838864

3
model-00003-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d12a2d2d607f978f1e069f90655af4daea711e7a335c41ff922ea586f49fba28
size 966822256

3
model-00004-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38766a22c9750166f5ee41a60b0cd25844d6c345e3f6c8270d52e1830bb9829a
size 989907416

3
model-00005-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c3b4912c8b2c72db28cb95a21218eac69437d51af34aeaa6531d081732ef706
size 943753712

3
model-00006-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a5a7a0b8e11ac2422bc77dc72794c80b88465d1925fe98d9e05175136c5a5b5c
size 989890824

3
model-00007-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7668f4c7d9ee527a532a517daf0845e215f39d18b7bd35aae880061953e44270
size 966838888

3
model-00008-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:26060daa2db96d3843ce2b4bfddbf8ea6b1fbd92cfc5e2a06263f7ec01158d94
size 966822272

3
model-00009-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ffc6a563cb8d744fd6c0d7b552d2901f5cbd290947efcf4608e4d4ceaae5c8f2
size 989907440

3
model-00010-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8340eac43920f3d7332f411e0a302cf0be785f8885840fa1e25a8749c6850d24
size 943753720

3
model-00011-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:51813a3bfabb8f348a788deab6540ef7478656be912575824378251e3cb8c2ed
size 989890824

3
model-00012-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:926e245d282609ae0dfff161f6c02327b9efa9c5e99c262bda7436e0ed3e82d5
size 966838888

3
model-00013-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d13984d62394a56df65cf9195a7705583862a0c2479be4bb3e3c460eec2b892f
size 966822272

3
model-00014-of-00014.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:73c9cde346f232d99e1e96e27846386c9a49c8f77ae5b92d0e0f7efbb012f586
size 847292072

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 13476831232
},
"weight_map": {
"lm_head.weight": "model-00014-of-00014.safetensors",
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
"model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.11.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.12.input_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
"model.layers.14.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.input_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.16.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.18.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
"model.layers.19.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.20.input_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
"model.layers.21.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.input_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.23.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
"model.layers.24.input_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
"model.layers.26.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.input_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.28.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.input_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.30.input_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
"model.layers.31.input_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
"model.layers.4.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.6.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
"model.layers.7.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
"model.layers.9.input_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
"model.norm.weight": "model-00014-of-00014.safetensors"
}
}

3
pytorch_model-00001-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8113d00fcbc7256ff8fd1619b39f97c6b08b061b73a4f067e06127e02cb5e465
size 981489327

3
pytorch_model-00002-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2635aa55751d45627b1b71d6ec3d8ec8e7273f0504657d2bc17647140829c69d
size 966844269

3
pytorch_model-00003-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d0727007157a3b03df9ac509299464dfaa541588a0f16ba94dfa431c7deb048b
size 966827273

3
pytorch_model-00004-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7626704e9d518cc3f1edcee7683e85b28ed0d8693804a5686964e2cc093a8f97
size 989912603

3
pytorch_model-00005-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e3a2c78b1150ba18f3524da8758c1a084b67b46a84e07cc4f3899bfac36ade6a
size 943758939

3
pytorch_model-00006-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a09b2b6c7dba90b49349a8041a81b5ced2501156928d5220e32cbea473b34f5f
size 989895607

3
pytorch_model-00007-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ababd7f8432d930cee3c40aa3af900f8129ecd9f9401884a864a09c6a4c9eafc
size 966844269

3
pytorch_model-00008-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:df6930ba04a679118a76ed73b0e042f825f432312900794852cca3df7b0279d3
size 966827273

3
pytorch_model-00009-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:752222c09349bae70d4db06600c1f13c9b302a8f7ce593977891f3fd68143f5c
size 989912667

3
pytorch_model-00010-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d02277dc954ce5f5a7ce95b6d693d52af137e5d371797ad895748d2193a8394
size 943758939

3
pytorch_model-00011-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8bd613e5788d47dc3e64436a7babf6166c37f2edd4b0a5721bd77398c94ddbfa
size 989895607

3
pytorch_model-00012-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a9fbfa9c97f8ba453daedb681a9673c10f3305d652a54f33383c00682de40c5
size 966844269

3
pytorch_model-00013-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:495a4fb763c631aaaede7149aec59e6a4482170070c2babc4d95517e500d4878
size 966827273

3
pytorch_model-00014-of-00014.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6cb39baaadceba2422cba8287bd4b11e86530b49c25ece760935afc5f7b8cbe4
size 847295773

298
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 13476831232
},
"weight_map": {
"lm_head.weight": "pytorch_model-00014-of-00014.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
"model.norm.weight": "pytorch_model-00014-of-00014.bin"
}
}

6
special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<s>",
"eos_token": "</s>",
"pad_token": "</s>",
"unk_token": "<unk>"
}

93423
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
size 499723

44
tokenizer_config.json Normal file
View File

@@ -0,0 +1,44 @@
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": null,
"max_length": 1024,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": true
}