初始化项目，由ModelHub XC社区提供模型
Model: nbeerbower/Mistral-Small-Gutenberg-Doppel-22B Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
doppel-header filter=lfs diff=lfs merge=lfs -text
|
||||
22
README.md
Normal file
22
README.md
Normal file
@@ -0,0 +1,22 @@
|
||||
---
|
||||
license: other
|
||||
license_name: mrl
|
||||
license_link: https://mistral.ai/licenses/MRL-0.1.md
|
||||
library_name: transformers
|
||||
base_model:
|
||||
- mistralai/Mistral-Small-Instruct-2409
|
||||
datasets:
|
||||
- jondurbin/gutenberg-dpo-v0.1
|
||||
- nbeerbower/gutenberg2-dpo
|
||||
---
|
||||
|
||||
|
||||
# Mistral-Small-Gutenberg-Doppel-22B
|
||||
|
||||
[mistralai/Mistral-Small-Instruct-2409](https://huggingface.co/mistralai/Mistral-Small-Instruct-2409) finetuned on [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) and [nbeerbower/gutenberg2-dpo](https://huggingface.co/datasets/nbeerbower/gutenberg2-dpo).
|
||||
|
||||
### Method
|
||||
|
||||
ORPO tuned with an A40 on RunPod (plz sponsor me) for 3 epochs.
|
||||
|
||||
[Fine-tune Llama 3 with ORPO](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html)
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "mistralai/Mistral-Small-Instruct-2409",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 6144,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 16384,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 48,
|
||||
"num_hidden_layers": 56,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.44.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
3
doppel-header
Normal file
3
doppel-header
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:236d00460ad2109c34beb0ce62fefd75b2c547ef54706dafa9173f08c90e33f8
|
||||
size 1388371
|
||||
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": "4.44.2"
|
||||
}
|
||||
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 sha256:5ce1318480ef0e0010dfaf0bd6c65eb0499ac9102f7b3d45017fe6a3e35f028b
|
||||
size 4882298776
|
||||
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 sha256:1efd3dd186fc0f9f9d1810b80963f6d68b99194626bc5d1362eb54d956c13560
|
||||
size 4983012160
|
||||
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 sha256:086f5848e973c5c0bfddf42735cdacad961c38f2fe2b75498bbe8159ee11cd2e
|
||||
size 4957821336
|
||||
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:ea3e2793cfe568fa06af58d11857b4236ba0c13023a9cb205c1c90f9d6e2797c
|
||||
size 4882323744
|
||||
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 sha256:2cdc138e2c9350e417172598b6b00b479dd2ad86cf89683343c65b0b4beafb25
|
||||
size 4983012192
|
||||
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 sha256:046a9cf5cbf20f82127b5335413001bd936cdda02ebbc711e2dd059326e7ffe4
|
||||
size 4957821336
|
||||
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 sha256:06ca695738b0361ebb2c5ce6485c29985479e7d3261d202b65be9c09ccc4ebf8
|
||||
size 4882323744
|
||||
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 sha256:43e696099ce0a7a56a561e12e5a8d9c429100db5f9f8bb4985b166a75f15cf34
|
||||
size 4983012192
|
||||
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:b289b27833dfb85205ed77806f8816660097dc753fbb20b8140f8a3775af57bc
|
||||
size 4982999056
|
||||
514
model.safetensors.index.json
Normal file
514
model.safetensors.index.json
Normal file
@@ -0,0 +1,514 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 44494565376
|
||||
},
|
||||
"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-00003-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-00003-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-00004-of-00009.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-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-00004-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-00004-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-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-00005-of-00009.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-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-00005-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-00005-of-00009.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-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-00005-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-00005-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-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-00006-of-00009.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-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-00006-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-00006-of-00009.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-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-00006-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-00006-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-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-00007-of-00009.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00007-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-00007-of-00009.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00007-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-00007-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-00007-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00007-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-00008-of-00009.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00008-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-00008-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-00008-of-00009.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00008-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-00008-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-00008-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00008-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-00001-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-00009-of-00009.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00009-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-00009-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-00009-of-00009.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00009-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-00009-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-00009-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00009-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.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"
|
||||
}
|
||||
}
|
||||
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
|
||||
}
|
||||
}
|
||||
98793
tokenizer.json
Normal file
98793
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
6187
tokenizer_config.json
Normal file
6187
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user