TinyPixel/Llama-2-7B-bf16-sharded
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/Llama-2-7B-bf16-sharded
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-29 04:09:04 +08:00
commit c572943276
37 changed files with 94260 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

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "TheBloke/Llama-2-7B-fp16",
"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,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.31.0",
"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": "4.31.0"
}

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d26d97b872e951797d38a673a7bc3630d02239618a1aef6e5ba1aed9241f1d87
size 981486080

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78ec4a20d301bbbcb06d9bc22d96933e30e6793ee07a1c880e10c3ab6bdc8a2b
size 966839576

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:955816090ee4caa14a464a8a4f639c14e436ee09ac150cdc4694864b6ca77ba3
size 966823328

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8841d53ec848cf0083d15e8d2cd7cd220b9a881e341659d40faad3f9a6bf3a5f
size 989908136

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a7c56906e513b7cd2ed0cd1408d64cac20deaa4be6f3c3eeb8601b5f2e5820fa
size 943754784

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b81d182c57198591f24d37e19be2c935f2b35b1820b75efc7c83ca6cb59359a1
size 989891544

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a5fdeea93e935409d32c900667a8fd20ff2cb606befb1b38c98912ec2da27c8
size 966839600

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3907bc669726b560a534039e51f5d5dbecf293c09874c6096356cacbf8d16078
size 966823352

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:caf48ba5955bb45f7042e60305e0408e307310171ac2f39cb180e80ee71f17cb
size 989908160

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c203daa5eb46067bbc318d3644c9754258628aa5b5d78e96b08c9dc6202222e0
size 943754792

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ab56f960bb203e09066405bd07e817543c04e004923f307ce60d0a0f25c837c
size 989891544

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c712c593368a8ff995449085120751771aac2e18186ba7162b37a04a1b0f51d6
size 966839600

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e666b7cad7f3fd9066b4de82f03af1085275e3a7a2b1662ccae1ede87a082790
size 966823352

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4e0c9ff0eee538e4df0c038a7992a0616cc96c46b6d3b4f65120dd9f1b2935d7
size 847292432

330
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,330 @@
{
"metadata": {
"total_size": 13476839424
},
"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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "model-00008-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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "model-00013-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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "model-00003-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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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:cecff527a13be85bd9494606d235727ba3a580cb1b72a4c7a25091e1a2c78037
size 981490451

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:c1f862b840114b5417c0db22da76a59246f9e0bae0f954e8ffc3d99a64f3a460
size 966845457

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2caef04bbafd2d78e9ca4b7b9affc83d150a09c710cab08f8782052e3144e89f
size 966828991

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3cf62135a21660c7b72a297d35b125ec6529dac9b4d90759550d49dc5e87490f
size 989913791

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e8db5ef742b38fe3cb960d39df674db598d725015893e5c773d77dd44538428
size 943760657

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:ea0ae2bad0c7f54c4bfe2198daa543ecb358a1009128428a3f753689a7d244e3
size 989896795

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:e9cecb53231b0a6ba154131ae0720cdc51548f1a2092e5ad0bfaf0fb9fc45cf9
size 966845457

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:a40591b1059d6ddb6aaf24accaea075eefed0d3a4ccd1e4bc779a7a166abfa04
size 966829055

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5047dd8b500a75ac3d63ac63097bc51b56ca886c42bf24d61d2a79ad42962894
size 989913791

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:f22c8f64cf2c4883c9a8b26420286f4c4de7ebd5d0bdd7ea7d3ebde182eca069
size 943760657

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:bab4152ca24a32840d946dd7fc4a40b270dad6ce862c4c166f61a4187fc80df7
size 989896795

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:18aba7c72e730e213a08c1a52c4b6e4ea4118ae0f4af28dda77ce8f3603c0443
size 966845457

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:45751631c28af7b08b7f597efbed4024a09b61f9f17c3495f8198b694cb74545
size 966829055

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8f1c7a5259f4325f6c7eaf2641b1ca6f9996db734f7949719c822c98de5acb0f
size 847296367

330
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,330 @@
{
"metadata": {
"total_size": 13476839424
},
"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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "pytorch_model-00008-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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "pytorch_model-00013-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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "pytorch_model-00003-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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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"
}
}

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

93391
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

31
tokenizer_config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}