Goekdeniz-Guelmez/Hyperion-2.1-Mistral-7B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Goekdeniz-Guelmez/Hyperion-2.1-Mistral-7B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-23 18:57:05 +08:00
commit 948d86787b
32 changed files with 91674 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
.gitattributes vendored Normal file
View File

@@ -0,0 +1,49 @@
*.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
hyperion-2.1-mistral-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
hyperion-2.1-mistral-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

14
README.md Normal file
View File

@@ -0,0 +1,14 @@
---
library_name: transformers
license: apache-2.0
datasets:
- Locutusque/hyperion-v2.0
language:
- en
---
# Description
Further fine-tuned Locutusque/Hyperion-2.0-Mistral-7B at a higher learning rate. This was done to see if performance increased. Read Locutusque/Hyperion-2.0-Mistral-7B's model card for more information. Slight performance gain was observed. More checkpoints will be released in the future.
# Disclaimer
This model is very compliant. It will respond to any request without refusal. If you intend to deploy this model at an enterprise level, I would recommend aligning this model using DPO.

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "Locutusque/Hyperion-2.0-Mistral-7B",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 32000
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.38.2"
}

3
hyperion-2.1-mistral-7b.Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:607b35cfd899e9c3bed9033778c380edd31e7a8fb39aa364c252317117a8d0f1
size 2719241984

3
hyperion-2.1-mistral-7b.Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:030174c5d76491aab1e8f4eea94a27736d06b73148ac2de590f956f707709a04
size 3822024448

3
hyperion-2.1-mistral-7b.Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0378e4ea4244100861bc2512f22c07ee7fbac54c2d13f5e9814a4159ca999f4
size 3518985984

3
hyperion-2.1-mistral-7b.Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d3c03c93047a788dd327c43a813c7c8642d11187e45bfac5ed37ca6eea1a252d
size 3164567296

3
hyperion-2.1-mistral-7b.Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:300b50d6e163da96147fa738046190ad58dc437400684664afda5cf9b8a53a8a
size 4108916480

3
hyperion-2.1-mistral-7b.Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d3e9a52e96d5aeb68459c29a3994597524720048329bca7ceff2f66ae97ce955
size 4553316096

3
hyperion-2.1-mistral-7b.Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:60fc531514a14cd16fbd952420f123adcc0b1e259f1fa45d821a1749e22a7b76
size 4368439040

3
hyperion-2.1-mistral-7b.Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c52d1e7e82ed00d49e90dc58f1f31475e2ba3a485db94d375be2f48756d8b168
size 4140373760

3
hyperion-2.1-mistral-7b.Q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c35b97539da990b279ad106e4b4f9f530c908175249a98174934136df897cc6b
size 4997715712

3
hyperion-2.1-mistral-7b.Q5_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97cc4dd4fcd0a503ab8ffb9f06eae80cdc931905e25745c26efb566310b11534
size 5442115328

3
hyperion-2.1-mistral-7b.Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ed66b00a4311ef5cf793d66dcec176de82aeecd1d7a86788d207837cff15b22
size 5131409152

3
hyperion-2.1-mistral-7b.Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:32d84689312239a8d44fef8e2d53dcba3b431e8b37a01ffa17c5dca847120a3a
size 4997715712

3
hyperion-2.1-mistral-7b.Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:69b4a90a94cde5e7e56f64da5bfbcb45eb426d6332735ec438ae6933d5160067
size 5942064896

3
hyperion-2.1-mistral-7b.Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5c59c3aa2ade003cef8074021b5e9a03c5304d7e5bcb5373d59b1a3edc3ff434
size 7695857408

3
hyperion-2.1-mistral-7b.fp16.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eb695b22b11c1e6af01f5e120f70b30f60b06eff76936eea2197c66a8deac772
size 14484731584

3
model-00001-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c1769ee7ed8794108647d766c96fb721f07f46c5ba45cc7a00dbdfb317ca5d7e
size 1889587040

3
model-00002-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6866aa45507eed9f06db669901dc7cbdd5e26e90f8d29b0ec9e0294b647bc15e
size 1946243936

3
model-00003-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7b795c38fbc9a17da6069c2b86518c71df201c07a099bd92cd31823cd531ddd7
size 1979781432

3
model-00004-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a07acbbb2c8c5debe7456a1a38d7f212af48018353ae2354726a7b5e51ae6a36
size 1946243984

3
model-00005-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17bb0862d6ac9e2ca5ca93e6200af3e283693ae681542bb5e3749e33a875556e
size 1979781448

3
model-00006-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d22c45985c1a6833ac722ee969735d99e1f8015234123efb4d98301f1eee742
size 1946243984

3
model-00007-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cba2b0e157cf094d981cd403f5072e0b0038226024433ebecd6c0babafb86174
size 1979781448

3
model-00008-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:27e5152ac8dbfde7854f91ff031957a835dc200b0ce3a829e9e0faeb4b2e4818
size 815834680

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 14483464192
},
"weight_map": {
"lm_head.weight": "model-00008-of-00008.safetensors",
"model.embed_tokens.weight": "model-00001-of-00008.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.30.input_layernorm.weight": "model-00008-of-00008.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.norm.weight": "model-00008-of-00008.safetensors"
}
}

24
special_tokens_map.json Normal file
View File

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

91136
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

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

Binary file not shown.

49
tokenizer_config.json Normal file
View File

@@ -0,0 +1,49 @@
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"max_length": 512,
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": "</s>",
"pad_token_type_id": 0,
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": false
}