初始化项目，由ModelHub XC社区提供模型
Model: Locutusque/llama-3-neural-chat-v1-8b 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
|
||||
206
README.md
Normal file
206
README.md
Normal file
@@ -0,0 +1,206 @@
|
||||
---
|
||||
license: other
|
||||
library_name: transformers
|
||||
base_model: meta-llama/Meta-Llama-3-8B
|
||||
datasets:
|
||||
- mlabonne/orpo-dpo-mix-40k
|
||||
- Open-Orca/SlimOrca-Dedup
|
||||
- jondurbin/airoboros-3.2
|
||||
- microsoft/orca-math-word-problems-200k
|
||||
- m-a-p/Code-Feedback
|
||||
- MaziyarPanahi/WizardLM_evol_instruct_V2_196k
|
||||
model-index:
|
||||
- name: llama-3-neural-chat-v1-8b
|
||||
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: 60.84
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
|
||||
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: 84.13
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
|
||||
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: 64.69
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
|
||||
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: 56.34
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
|
||||
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: 78.22
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
|
||||
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: 54.81
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/llama-3-neural-chat-v1-8b
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
# llama-3-neural-chat-v1-8b
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
I fine-tuned llama-3 8B on an approach similar to Intel's neural chat language model. I have slightly modified the data sources so it is stronger in coding, math, and writing. I use both SFT and DPO.
|
||||
|
||||
- **Developed by:** Locutusque
|
||||
- **Model type:** Built with Meta Llama 3
|
||||
- **Language(s) (NLP):** Many?
|
||||
- **License:** Llama 3 license https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE
|
||||
|
||||
## Quants
|
||||
|
||||
### EXL2 [@bartowski](https://huggingface.co/bartowski/)
|
||||
|
||||
- https://huggingface.co/bartowski/llama-3-neural-chat-v1-8b-exl2
|
||||
|
||||
### GGUF [@bartowski](https://huggingface.co/bartowski/)
|
||||
|
||||
- https://huggingface.co/bartowski/llama-3-neural-chat-v1-8b-GGUF
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
This model has great performance in writing and coding.
|
||||
|
||||
## Training Data
|
||||
- Open-Orca/SlimOrca-Dedup
|
||||
- jondurbin/airoboros-3.2
|
||||
- microsoft/orca-math-word-problems-200k
|
||||
- m-a-p/Code-Feedback
|
||||
- MaziyarPanahi/WizardLM_evol_instruct_V2_196k
|
||||
- mlabonne/orpo-dpo-mix-40k
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
Conversational AI.
|
||||
|
||||
## Evaluations
|
||||
|
||||
| Tasks |Version| Filter |n-shot| Metric |Value | |Stderr|
|
||||
|---------------------------------|-------|----------------|-----:|-----------|-----:|---|-----:|
|
||||
|truthfulqa_mc2 | 2|none | 0|acc |0.5627|± |0.0154|
|
||||
|gsm8k | 3|strict-match | 5|exact_match|0.5481|± |0.0137|
|
||||
| | |flexible-extract| 5|exact_match|0.5557|± |0.0137|
|
||||
|agieval_nous |N/A |none | 0|acc |0.3763|± |0.0093|
|
||||
| | |none | 0|acc_norm |0.3665|± |0.0093|
|
||||
| - agieval_aqua_rat | 1|none | 0|acc |0.2087|± |0.0255|
|
||||
| | |none | 0|acc_norm |0.2047|± |0.0254|
|
||||
| - agieval_logiqa_en | 1|none | 0|acc |0.3456|± |0.0187|
|
||||
| | |none | 0|acc_norm |0.3594|± |0.0188|
|
||||
| - agieval_lsat_ar | 1|none | 0|acc |0.1826|± |0.0255|
|
||||
| | |none | 0|acc_norm |0.1783|± |0.0253|
|
||||
| - agieval_lsat_lr | 1|none | 0|acc |0.3549|± |0.0212|
|
||||
| | |none | 0|acc_norm |0.3451|± |0.0211|
|
||||
| - agieval_lsat_rc | 1|none | 0|acc |0.5242|± |0.0305|
|
||||
| | |none | 0|acc_norm |0.5130|± |0.0305|
|
||||
| - agieval_sat_en | 1|none | 0|acc |0.6650|± |0.0330|
|
||||
| | |none | 0|acc_norm |0.6505|± |0.0333|
|
||||
| - agieval_sat_en_without_passage| 1|none | 0|acc |0.4175|± |0.0344|
|
||||
| | |none | 0|acc_norm |0.3738|± |0.0338|
|
||||
| - agieval_sat_math | 1|none | 0|acc |0.4227|± |0.0334|
|
||||
| | |none | 0|acc_norm |0.3682|± |0.0326|
|
||||
# [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_Locutusque__llama-3-neural-chat-v1-8b)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |66.50|
|
||||
|AI2 Reasoning Challenge (25-Shot)|60.84|
|
||||
|HellaSwag (10-Shot) |84.13|
|
||||
|MMLU (5-Shot) |64.69|
|
||||
|TruthfulQA (0-shot) |56.34|
|
||||
|Winogrande (5-shot) |78.22|
|
||||
|GSM8k (5-shot) |54.81|
|
||||
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "Locutusque/Llama-3-Orca-1.0-8B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.40.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"transformers_version": "4.40.0"
|
||||
}
|
||||
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 sha256:3868d734fa2e1c314de8335724968645877c81a7fe5e8ac48c277c1118a9e087
|
||||
size 1973455376
|
||||
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:c110d8b96a08a7d2f0b7ba97a6ece208c6b9fb6c81f4ffc82cadb7093e1f0df3
|
||||
size 1895895336
|
||||
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 sha256:027bd3f090f54e9e6a00159c2cd84e66e0bd5adadc661d6de8ca15197d7912c7
|
||||
size 1979798040
|
||||
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 sha256:7a5cf43cb41757ea4115c232dee7e2bba34404032b2a7d2001e6c3274c0c2bcb
|
||||
size 1946227368
|
||||
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 sha256:329bf6b024f182730fa2bb969f05cecb2fe7030a4f88f4c44250972a151d9ecb
|
||||
size 1979798064
|
||||
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:b1aab177c4ba62fd884e8316b885ee324ec309ecf078a4019cba7afd3b572c12
|
||||
size 1946227368
|
||||
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 sha256:5537c5dae5ca321e5b558896e9950aa4a8c1cedb60c758c2c97ecf97037c1595
|
||||
size 1979798064
|
||||
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 sha256:64afa3e3f3d2e4ba897748b319f0f928b3092c1e675669fd81164e55688c2046
|
||||
size 1308683424
|
||||
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:f5421f075f97b341605ce2fe1fa4503703900e31e05349143d05a2f9ffcd9765
|
||||
size 1050673280
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060522496
|
||||
},
|
||||
"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-00003-of-00009.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-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-00002-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-00006-of-00009.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.norm.weight": "model-00008-of-00009.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
410518
tokenizer.json
Normal file
410518
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 sha256:82e9d31979e92ab929cd544440f129d9ecd797b69e327f80f17e1c50d5551b55
|
||||
size 2183982
|
||||
2072
tokenizer_config.json
Normal file
2072
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user