初始化项目，由ModelHub XC社区提供模型
Model: AlekseyKorshuk/vicuna-7b Source: Original Platform
This commit is contained in:
ModelHub XC
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
*.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
|
||||
*.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
|
||||
46
README.md
Normal file
46
README.md
Normal file
@@ -0,0 +1,46 @@
|
||||
---
|
||||
license: other
|
||||
---
|
||||
# Vicuna 7B without "ethics" filtering
|
||||
|
||||
This repository contains an alternative version of the [Vicuna 7B model](https://huggingface.co/lmsys/vicuna-7b-delta-v0).
|
||||
|
||||
This model was natively fine-tuned using ShareGPT data, but without the "ethics" filtering used for the original Vicuna.
|
||||
|
||||
[A GPTQ quantised 4-bit version is available here](https://huggingface.co/TheBloke/vicuna-AlekseyKorshuk-7B-GPTQ-4bit-128g).
|
||||
|
||||
# Original Vicuna Model Card
|
||||
|
||||
## Model details
|
||||
|
||||
**Model type:**
|
||||
Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
|
||||
It is an auto-regressive language model, based on the transformer architecture.
|
||||
|
||||
**Model date:**
|
||||
Vicuna was trained between March 2023 and April 2023.
|
||||
|
||||
**Organizations developing the model:**
|
||||
The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
|
||||
|
||||
**Paper or resources for more information:**
|
||||
https://vicuna.lmsys.org/
|
||||
|
||||
**License:**
|
||||
Apache License 2.0
|
||||
|
||||
**Where to send questions or comments about the model:**
|
||||
https://github.com/lm-sys/FastChat/issues
|
||||
|
||||
## Intended use
|
||||
**Primary intended uses:**
|
||||
The primary use of Vicuna is research on large language models and chatbots.
|
||||
|
||||
**Primary intended users:**
|
||||
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
|
||||
|
||||
## Training dataset
|
||||
70K conversations collected from ShareGPT.com.
|
||||
|
||||
## Evaluation dataset
|
||||
A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.
|
||||
23
config.json
Normal file
23
config.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"_name_or_path": "./",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 1,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_sequence_length": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"pad_token_id": -1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.28.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32001
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 1,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.28.0.dev0"
|
||||
}
|
||||
3
pytorch_model-00001-of-00014.bin
Normal file
3
pytorch_model-00001-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:77d715580dfc4bf1fe0ae1498f27e7192ad3ff0df924a69c4e80d72b51b146ba
|
||||
size 981498195
|
||||
3
pytorch_model-00002-of-00014.bin
Normal file
3
pytorch_model-00002-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:583ac5dba64145de72674674eef88cb1319441bd0b870ebc80ced4dede6faa80
|
||||
size 966844881
|
||||
3
pytorch_model-00003-of-00014.bin
Normal file
3
pytorch_model-00003-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:74152c3c79834987e4db5ca3725c322cdbb1bafdc09031f1fca74be02b185dfa
|
||||
size 966828351
|
||||
3
pytorch_model-00004-of-00014.bin
Normal file
3
pytorch_model-00004-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cc6f5d634872863709cd26c36ace46d176f944c9e54b2e5f7714fe4031631fae
|
||||
size 989913279
|
||||
3
pytorch_model-00005-of-00014.bin
Normal file
3
pytorch_model-00005-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:50952fbaf255d762b314e0b020d43b6c98a43852d35ce00ce9c8be8600a14baf
|
||||
size 943760017
|
||||
3
pytorch_model-00006-of-00014.bin
Normal file
3
pytorch_model-00006-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:590339279709ca4214c7dfbeb656fe88aa800f6cc6716cf7e3298dfc118d811d
|
||||
size 989896283
|
||||
3
pytorch_model-00007-of-00014.bin
Normal file
3
pytorch_model-00007-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9f98247078330aa2b31165495937ea497c9d748c7c1e00ef684237a2c1bce11f
|
||||
size 966844945
|
||||
3
pytorch_model-00008-of-00014.bin
Normal file
3
pytorch_model-00008-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7a3a411a165123be9633e4c609e5c217e401ff5ae0e85e7f2e45e0929f814f48
|
||||
size 966828351
|
||||
3
pytorch_model-00009-of-00014.bin
Normal file
3
pytorch_model-00009-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:837aafee1064964aeaac76672ef4ae0d60b198edf32c2238f158401a2d2854ad
|
||||
size 989913279
|
||||
3
pytorch_model-00010-of-00014.bin
Normal file
3
pytorch_model-00010-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:719e00fc3845ba66234d162f8e96b7f5b52b9a3a813298bb07b1fc0429bab1a7
|
||||
size 943760017
|
||||
3
pytorch_model-00011-of-00014.bin
Normal file
3
pytorch_model-00011-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5d54dc19eaae3f7a6af8c02f817f8fe5694fda5e212827038a4873a4db01dac2
|
||||
size 989896283
|
||||
3
pytorch_model-00012-of-00014.bin
Normal file
3
pytorch_model-00012-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5bdb5adb4575e1834f811db7fb17ac75344655c3ef3bdbc448e89af16dd2aa66
|
||||
size 966844945
|
||||
3
pytorch_model-00013-of-00014.bin
Normal file
3
pytorch_model-00013-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ac682d1962f4cc89b0ad57471ea140c0d098779805967584b8d40614aded26b8
|
||||
size 966828351
|
||||
3
pytorch_model-00014-of-00014.bin
Normal file
3
pytorch_model-00014-of-00014.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:27e38603cdbdc7612e822396e10ae71c5b1bc458a21ea8a102b3d6689e99a7ad
|
||||
size 847304239
|
||||
330
pytorch_model.bin.index.json
Normal file
330
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,330 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13476851712
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
|
||||
"model.norm.weight": "pytorch_model-00014-of-00014.bin"
|
||||
}
|
||||
}
|
||||
6
special_tokens_map.json
Normal file
6
special_tokens_map.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token": "</s>",
|
||||
"eos_token": "</s>",
|
||||
"pad_token": "[PAD]",
|
||||
"unk_token": "</s>"
|
||||
}
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
9
tokenizer_config.json
Normal file
9
tokenizer_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"bos_token": "",
|
||||
"eos_token": "",
|
||||
"model_max_length": 2048,
|
||||
"padding_side": "right",
|
||||
"special_tokens_map_file": "models/decapoda-research_llama-7b-hf/special_tokens_map.json",
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": ""
|
||||
}
|
||||
Reference in New Issue
Block a user