liaaron1/llama-2-7b-liaaron1-bible-shards
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: liaaron1/llama-2-7b-liaaron1-bible-shards
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-17 19:43:42 +08:00
commit aba2e192e1
24 changed files with 94234 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

3
added_tokens.json Normal file
View File

@@ -0,0 +1,3 @@
{
"<pad>": 32000
}

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
"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": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 32000,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}

3
model-00001-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f48b9b2f7e780aa6b6d6a2fe0b40f2170c8ceadec7cc0c7fad7e2c2441d3d7ee
size 1981880192

3
model-00002-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:721c78aebd89f6d04c1ec860e5c0dd89285490dff7f22957feb15d43edb959b6
size 1990285992

3
model-00003-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:29259cc96e8297754b2c4aa1077478284e3512bdad6223033d00adb1ffed237a
size 1990286024

3
model-00004-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d51d125b90502f28907d3b9ddbf992f09e684d3f285f926b82e53fce9266ca3a
size 1990286040

3
model-00005-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf16fd1cf3f25f41e3b34639ee75850047f266289d141091420cc5cf3c7e3f3a
size 1933646320

3
model-00006-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cfb90610848ea63628ab032d05a5844469ae8543ff5e822f6bce7045e25c10cc
size 1933662928

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f6d799c2cfda75b0464cd94987ef50f12789d2682af8250e42b8f38d21db82a1
size 1656828656

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

@@ -0,0 +1,330 @@
{
"metadata": {
"total_size": 13476839424
},
"weight_map": {
"lm_head.weight": "model-00007-of-00007.safetensors",
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00004-of-00007.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00005-of-00007.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.27.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.28.self_attn.rotary_emb.inv_freq": "model-00006-of-00007.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.rotary_emb.inv_freq": "model-00007-of-00007.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00003-of-00007.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.norm.weight": "model-00007-of-00007.safetensors"
}
}

3
pytorch_model-00001-of-00007.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa302bd08095c5675f13cdecfb8e068fcbdf4a810af6e0740b9f4c8f9d612db9
size 1981890471

3
pytorch_model-00002-of-00007.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cd05db16f4cc85099acd02e64aad31217c99d6ba45a115f892a84ba866ca683b
size 1990297473

3
pytorch_model-00003-of-00007.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ccfd7727ad60912a07151b197b1b7cac55a22c0393bfb8d85c70b52b4fd13b5
size 1990297537

3
pytorch_model-00004-of-00007.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3f4f768990fa8626df9a2384583a0f4fd433e65e6fb094416908c450179d4ae5
size 1990297537

3
pytorch_model-00005-of-00007.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c133cf58ee71bd77522a130677dc743470f23b903ad520c84e8ff28850de52d0
size 1933657373

3
pytorch_model-00006-of-00007.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:318b15608ea08a8a7b64ff342a17df5ea03e601e96033990205c0d80044048f7
size 1933674433

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bc00ddcf3b4cf55701ee02d4aba37f2fdf5c335761d3153bf59bf1c966403ee3
size 1656837079

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-00007-of-00007.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
"model.norm.weight": "pytorch_model-00007-of-00007.bin"
}
}

24
special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"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
},
"pad_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

93400
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

32
tokenizer_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"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
},
"legacy": 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
}
}