初始化项目，由ModelHub XC社区提供模型
Model: pharaouk/fusedyi 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
|
||||
33
README.md
Normal file
33
README.md
Normal file
@@ -0,0 +1,33 @@
|
||||
---
|
||||
tags:
|
||||
- Mixtral
|
||||
- instruct
|
||||
- finetune
|
||||
- chatml
|
||||
- DPO
|
||||
- RLHF
|
||||
- gpt4
|
||||
- synthetic data
|
||||
- distillation
|
||||
model-index:
|
||||
- name: fusedYi
|
||||
results: []
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
|
||||
# Model Card for FusedYi
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
This is fused Yi-6B.
|
||||
I took a Yi, merged it with another Yi, and got a new Yi out of the Yis.
|
||||
Yi-ceptionized.
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
1.9 x Yi-6B
|
||||
|
||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<|endoftext|>": 64001,
|
||||
"<|startoftext|>": 64000
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "/root/",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"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": 11008,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 60,
|
||||
"num_key_value_heads": 4,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.36.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 64000
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.36.2"
|
||||
}
|
||||
3
model-00001-of-00009.safetensors
Normal file
3
model-00001-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f035ee34c9dba32117ac9dcfda6db9dbad41e8d521698b2c1f3295bd3dfd7281
|
||||
size 4840396528
|
||||
3
model-00002-of-00009.safetensors
Normal file
3
model-00002-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:06aaa921e4abceba9548c14a3e321e370e7825a47b48085de233b9dce76e9ebe
|
||||
size 4844657744
|
||||
3
model-00003-of-00009.safetensors
Normal file
3
model-00003-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c21c23b66dc4a950eddd35a2e88bfea424818f23f0777927a0e05b1a52feb0b
|
||||
size 4844657784
|
||||
3
model-00004-of-00009.safetensors
Normal file
3
model-00004-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4152319a01713b66cd764d61c34cdbba86614e1729cbdd7a79823b6a2d1bfc52
|
||||
size 4844657784
|
||||
3
model-00005-of-00009.safetensors
Normal file
3
model-00005-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c3cc4344faf9f332999e3d11ae8e485e6ec8c0f8d497bdec877fe769d63aeae3
|
||||
size 4844657784
|
||||
3
model-00006-of-00009.safetensors
Normal file
3
model-00006-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:48a71ca0d3e549043149e5165af8bc1ff8669322d682d273c8e421fbba4fec80
|
||||
size 4844657784
|
||||
3
model-00007-of-00009.safetensors
Normal file
3
model-00007-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0ca0132815a4ff99a124e778c38bf4aa10ed24ea5ff4ea19b4fc1bbf2feb46c7
|
||||
size 4844657784
|
||||
3
model-00008-of-00009.safetensors
Normal file
3
model-00008-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e631300710b72b37dc2674bae2e3886738f98fdf8e84cc5a5e39c6811438a581
|
||||
size 4844657784
|
||||
3
model-00009-of-00009.safetensors
Normal file
3
model-00009-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e89b3bb9e12cad526cd0a1d136a8c21d788aa12498b97f7450ec0778025dc7f6
|
||||
size 4869805816
|
||||
550
model.safetensors.index.json
Normal file
550
model.safetensors.index.json
Normal file
@@ -0,0 +1,550 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 43622744064
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00009-of-00009.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.norm.weight": "model-00009-of-00009.safetensors"
|
||||
}
|
||||
}
|
||||
35
special_tokens_map.json
Normal file
35
special_tokens_map.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|im_sep|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|startoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
174188
tokenizer.json
Normal file
174188
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
||||
size 1033105
|
||||
88
tokenizer_config.json
Normal file
88
tokenizer_config.json
Normal file
@@ -0,0 +1,88 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"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
|
||||
},
|
||||
"6": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<|im_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"64000": {
|
||||
"content": "<|startoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"64001": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|im_sep|>"
|
||||
],
|
||||
"bos_token": "<|startoftext|>",
|
||||
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"legacy": true,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<unk>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user