初始化项目，由ModelHub XC社区提供模型
Model: acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1 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
|
||||||
153
README.md
Normal file
153
README.md
Normal file
@@ -0,0 +1,153 @@
|
|||||||
|
---
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
license: apache-2.0
|
||||||
|
library_name: transformers
|
||||||
|
datasets:
|
||||||
|
- togethercomputer/RedPajama-Data-1T
|
||||||
|
- databricks/databricks-dolly-15k
|
||||||
|
- OpenAssistant/oasst1
|
||||||
|
- Muennighoff/natural-instructions
|
||||||
|
- Muennighoff/P3
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
model-index:
|
||||||
|
- name: RedPajama-INCITE-Chat-Instruct-3B-V1
|
||||||
|
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: 42.58
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
|
||||||
|
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: 67.48
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
|
||||||
|
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: 25.99
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
|
||||||
|
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: 33.62
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
|
||||||
|
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: 64.8
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
|
||||||
|
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: 0.91
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
---
|
||||||
|
|
||||||
|
<a href="https://www.buymeacoffee.com/acrastt" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
|
||||||
|
|
||||||
|
This is an experimental merge of models [RedPajama-INCITE-Chat-3B-V1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1) and [RedPajama-INCITE-Instruct-3B-V1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Instruct-3B-v1).</br>
|
||||||
|
This model is adaptive to prompt templates, but this template is recommended:
|
||||||
|
```
|
||||||
|
HUMAN: {prompt}
|
||||||
|
ASSISTANT:
|
||||||
|
```
|
||||||
|
Feel free to change HUMAN or ASSISTANT. It will not change much.</br>
|
||||||
|
GGML versions [here](https://huggingface.co/adadbbb/pajama_ggml) (Note that this is only compatible with [koboldcpp](https://github.com/LostRuins/koboldcpp)).
|
||||||
|
# [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_acrastt__RedPajama-INCITE-Chat-Instruct-3B-V1)
|
||||||
|
|
||||||
|
| Metric | Value |
|
||||||
|
|-----------------------|---------------------------|
|
||||||
|
| Avg. | 39.23 |
|
||||||
|
| ARC (25-shot) | 42.58 |
|
||||||
|
| HellaSwag (10-shot) | 67.48 |
|
||||||
|
| MMLU (5-shot) | 25.99 |
|
||||||
|
| TruthfulQA (0-shot) | 33.62 |
|
||||||
|
| Winogrande (5-shot) | 64.8 |
|
||||||
|
| GSM8K (5-shot) | 0.91 |
|
||||||
|
|
||||||
|
# [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_acrastt__RedPajama-INCITE-Chat-Instruct-3B-V1)
|
||||||
|
|
||||||
|
| Metric |Value|
|
||||||
|
|---------------------------------|----:|
|
||||||
|
|Avg. |39.23|
|
||||||
|
|AI2 Reasoning Challenge (25-Shot)|42.58|
|
||||||
|
|HellaSwag (10-Shot) |67.48|
|
||||||
|
|MMLU (5-Shot) |25.99|
|
||||||
|
|TruthfulQA (0-shot) |33.62|
|
||||||
|
|Winogrande (5-shot) |64.80|
|
||||||
|
|GSM8k (5-shot) | 0.91|
|
||||||
|
|
||||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "RedPajama-INCITE-Chat-3B-v1",
|
||||||
|
"architectures": [
|
||||||
|
"GPTNeoXForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 0,
|
||||||
|
"classifier_dropout": 0.1,
|
||||||
|
"eos_token_id": 0,
|
||||||
|
"hidden_act": "gelu",
|
||||||
|
"hidden_dropout": 0.0,
|
||||||
|
"hidden_size": 2560,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 10240,
|
||||||
|
"layer_norm_eps": 1e-05,
|
||||||
|
"max_position_embeddings": 2048,
|
||||||
|
"model_type": "gpt_neox",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rotary_emb_base": 10000,
|
||||||
|
"rotary_pct": 1.0,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.31.0",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_parallel_residual": false,
|
||||||
|
"vocab_size": 50432
|
||||||
|
}
|
||||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 0,
|
||||||
|
"eos_token_id": 0,
|
||||||
|
"transformers_version": "4.31.0"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:84a3eedddcc906dea61602d635d035e2aa5eab4a114ee5e733e1fe00f7ca5827
|
||||||
|
size 5551780832
|
||||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:114e606314db2fa18ace68968e41dbb9b7fe6dd3b35269347044e659f5b40f3a
|
||||||
|
size 5551868229
|
||||||
5
special_tokens_map.json
Normal file
5
special_tokens_map.json
Normal file
@@ -0,0 +1,5 @@
|
|||||||
|
{
|
||||||
|
"bos_token": "<|endoftext|>",
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"unk_token": "<|endoftext|>"
|
||||||
|
}
|
||||||
100529
tokenizer.json
Normal file
100529
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
9
tokenizer_config.json
Normal file
9
tokenizer_config.json
Normal file
@@ -0,0 +1,9 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"bos_token": "<|endoftext|>",
|
||||||
|
"clean_up_tokenization_spaces": true,
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"model_max_length": 2048,
|
||||||
|
"tokenizer_class": "GPTNeoXTokenizer",
|
||||||
|
"unk_token": "<|endoftext|>"
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user