HIT-TMG/Mixtral_13B_Chat_RAG-Reader
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Update config.json

Browse Source
This commit is contained in:
ai-modelscope
2025-01-07 09:13:48 +08:00
parent e0dc2bfd9a
commit 2a26bbe7f2
15 changed files with 719 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
.gitattributes vendored
View File

@@ -1,47 +1,41 @@
*.7z filter=lfs diff=lfs merge=lfs -text *.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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 *.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* 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 *.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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 *.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text
*.pb 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 *.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text
*.rar 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 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
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz 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 *.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text
model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text
model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text

170
README.md
View File

File diff suppressed because one or more lines are too long

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mixtral",
"num_attention_heads": 32,
"num_experts_per_tok": 2,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"num_local_experts": 2,
"output_router_logits": false,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"use_cache": true,
"vocab_size": 32000
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.37.2"
}

3
model-00001-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f89f64424b1556688cc343a84f31fd6872f64e3c62b1486fbc769e74768e623
size 4993525264

3
model-00002-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1dfa781f05c3b5fa4b1d72742f5c1d08e5e3905bac74f88f20d253ff1aa728da
size 4932724880

3
model-00003-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61f37f1ac4131dd96a3f4a61d243f261a9d740da039cf86eba9e431976a9d098
size 4966262528

3
model-00004-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:07c741be111ad45dac8ab097cdbc693333e6c0f8122812975e39d7d50e9be285
size 4966262528

3
model-00005-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a67e810bd25aca041aac6e7e32ef4bb0e7cc6d5cae071ef4d0654b47860d9881
size 4932741544

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1360cfdb604aa4b1b2671a3d57765d54afc8394f9751010fde570036ab90c482
size 966812872

426
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,426 @@
{
"metadata": {
"total_size": 25758277632
},
"weight_map": {
"lm_head.weight": "model-00006-of-00006.safetensors",
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
"model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
"model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
"model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
"model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
"model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
"model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
"model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
"model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
"model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
"model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
"model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
"model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
"model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors",
"model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors",
"model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors",
"model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors",
"model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors",
"model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors",
"model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
"model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
"model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
"model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
"model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
"model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
"model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.norm.weight": "model-00006-of-00006.safetensors"
}
}

35
special_tokens_map.json Normal file
View File

@@ -0,0 +1,35 @@
{
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

55
tokenizer_config.json Normal file
View File

@@ -0,0 +1,55 @@
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"max_length": null,
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": "<s>",
"pad_token_type_id": 0,
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"split_special_tokens": false,
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": false
}