初始化项目，由ModelHub XC社区提供模型
Model: KnutJaegersberg/Deacon-20B Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
138
README.md
Normal file
138
README.md
Normal file
@@ -0,0 +1,138 @@
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
datasets:
|
||||
- totally-not-an-llm/EverythingLM-data-V3
|
||||
pipeline_tag: text-generation
|
||||
model-index:
|
||||
- name: Deacon-20B
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: AI2 Reasoning Challenge (25-Shot)
|
||||
type: ai2_arc
|
||||
config: ARC-Challenge
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 60.75
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (10-Shot)
|
||||
type: hellaswag
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 10
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 81.74
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU (5-Shot)
|
||||
type: cais/mmlu
|
||||
config: all
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 60.7
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: TruthfulQA (0-shot)
|
||||
type: truthful_qa
|
||||
config: multiple_choice
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: mc2
|
||||
value: 58.49
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Winogrande (5-shot)
|
||||
type: winogrande
|
||||
config: winogrande_xl
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 76.8
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GSM8k (5-shot)
|
||||
type: gsm8k
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 29.19
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
|
||||
To understand the pun intended, lookup my 3b Deacon model.
|
||||
|
||||
Prompt Example:
|
||||
```
|
||||
### System:
|
||||
|
||||
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
|
||||
|
||||
### Instruction:
|
||||
|
||||
How do you fine tune a large language model?
|
||||
|
||||
### Response:
|
||||
```
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KnutJaegersberg__Deacon-20B)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |61.28|
|
||||
|AI2 Reasoning Challenge (25-Shot)|60.75|
|
||||
|HellaSwag (10-Shot) |81.74|
|
||||
|MMLU (5-Shot) |60.70|
|
||||
|TruthfulQA (0-shot) |58.49|
|
||||
|Winogrande (5-shot) |76.80|
|
||||
|GSM8k (5-shot) |29.19|
|
||||
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "/run/media/knut/HD/huggingface models/language models/LLMs/pretrained/40b/internlm-20b-llama/",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 60,
|
||||
"num_key_value_heads": 40,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.36.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 103168
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.36.2"
|
||||
}
|
||||
3
model-00001-of-00009.safetensors
Normal file
3
model-00001-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:198bb77447f73d1eda1f2081d3b75fc717839194f9f8fcd11d552f46d90b325b
|
||||
size 4967758248
|
||||
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 sha256:5b17e49f2c6a8e51d190975c6f6f06bb7effe45d58f85d39cd6fe1f76bc259b5
|
||||
size 4970422152
|
||||
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:c34ea42869f1527c21e39df069bf63148b20d9dffbb9476242dfc40318904d53
|
||||
size 4933701432
|
||||
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:cb8c83aa646953c3b6a1aae3bf7b0e8fe69102b5cb66d337cf93e42fadcefef8
|
||||
size 4933722144
|
||||
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:a293a16e4f73fa1d326598923414eb38625510d590ec894011239d38333d8271
|
||||
size 4933722136
|
||||
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 sha256:19ca287f2b2da2fbef16ddb959d813ce992c90a18501cd2ac24b2e420181ec71
|
||||
size 4970422184
|
||||
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:e38e3d38cd122ec3157e6fe8b8fd2a436f280158ed88c8e99824441ea3992d16
|
||||
size 4970422184
|
||||
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 sha256:63963d8141392700a48b88b8f5a08b5047533c96f5405b9e1267d65b4bca6cc7
|
||||
size 4440880344
|
||||
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 sha256:8b2932c9af6b5dd1459688db664ad0feadd81a1c1fe42d0f38c33ce5c8eb2773
|
||||
size 1056440448
|
||||
550
model.safetensors.index.json
Normal file
550
model.safetensors.index.json
Normal file
@@ -0,0 +1,550 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 40177428480
|
||||
},
|
||||
"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-00002-of-00009.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-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-00003-of-00009.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00004-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-00004-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-00004-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-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-00001-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-00007-of-00009.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00008-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-00001-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-00001-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-00008-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
|
||||
}
|
||||
}
|
||||
280822
tokenizer.json
Normal file
280822
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aab622d98c98677a1a51f969e25765154487bf3e85c7819db105db2fcacba83f
|
||||
size 1658691
|
||||
42
tokenizer_config.json
Normal file
42
tokenizer_config.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.last and message['role'] != 'user' %}{{ raise_exception('Most recent message must come from user!') }}{% endif %}{% if message['role'] == 'user' %}{{ '<|User|>:' + message['content'] + '<eoh>\n'}}{% elif message['role'] == 'assistant' %}{{ '<|Bot|>:' + message['content'] + '<eoa>\n'}}{% else %}{{ raise_exception('Only user and assistant roles are supported in this model!') }}{% endif %}{% endfor %}{{ '<|Bot|>:' }}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user