初始化项目，由ModelHub XC社区提供模型
Model: cloudyu/19B_MATH_DPO Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
14
README.md
Normal file
14
README.md
Normal file
@@ -0,0 +1,14 @@
|
||||
---
|
||||
license: other
|
||||
tags:
|
||||
- dpo
|
||||
- moe
|
||||
---
|
||||
|
||||
this is a DPO fine-tuned MoE model with about 19B parameter.
|
||||
|
||||
|
||||
```
|
||||
DPO Trainer
|
||||
TRL supports the DPO Trainer for training language models from preference data, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023.
|
||||
```
|
||||
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"_name_or_path": "cloudyu/Mixtral_11Bx2_MoE_19B",
|
||||
"architectures": [
|
||||
"MixtralForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"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": 4096,
|
||||
"model_type": "mixtral",
|
||||
"num_attention_heads": 32,
|
||||
"num_experts_per_tok": 2,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"num_local_experts": 2,
|
||||
"output_router_logits": false,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"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
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 2,
|
||||
"transformers_version": "4.37.2"
|
||||
}
|
||||
3
model-00001-of-00008.safetensors
Normal file
3
model-00001-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0ffc5c09890c5abb6a84897ef0c1ddc9cf518b1ef1f4a2628a514a293ed48457
|
||||
size 4993525264
|
||||
3
model-00002-of-00008.safetensors
Normal file
3
model-00002-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dcc0e28a2cc55d8115f6f20f171633c5d39beddcaa3af6c5f1d3494ebf67f593
|
||||
size 4932724880
|
||||
3
model-00003-of-00008.safetensors
Normal file
3
model-00003-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e15fdf2e0417d575649c29df7bd212f40d6deb57eb819a44572dd210fde051be
|
||||
size 4966262528
|
||||
3
model-00004-of-00008.safetensors
Normal file
3
model-00004-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1de07f3a1b8a74aa1f07110aac3bc976ee1aaafe3423cc5bf79597ad7c3f7f75
|
||||
size 4966262528
|
||||
3
model-00005-of-00008.safetensors
Normal file
3
model-00005-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3ac9d5ba247c10816af891ddee19dd3dd5801092a13f32063f4affb2a61d1cb5
|
||||
size 4932741544
|
||||
3
model-00006-of-00008.safetensors
Normal file
3
model-00006-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:772ba46d3181f6e37c83f7c3bfaccb5585d933798909b7256d52f8ebc2266ebc
|
||||
size 4966262528
|
||||
3
model-00007-of-00008.safetensors
Normal file
3
model-00007-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:396b00b56389e456942646b63f3388ae1ab4c62e5becb242c356274337b1e7c5
|
||||
size 4966262528
|
||||
3
model-00008-of-00008.safetensors
Normal file
3
model-00008-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:79799e4e9c78fa728712eea4f9b538236d39260171b70e84c8e1fa35b9d03ef6
|
||||
size 3651304448
|
||||
634
model.safetensors.index.json
Normal file
634
model.safetensors.index.json
Normal file
@@ -0,0 +1,634 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 38375268352
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00008-of-00008.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.43.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.norm.weight": "model-00008-of-00008.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
47
tokenizer_config.json
Normal file
47
tokenizer_config.json
Normal file
@@ -0,0 +1,47 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"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": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
|
||||
"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": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user