初始化项目，由ModelHub XC社区提供模型
Model: ericzzz/falcon-rw-1b-chat 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
|
||||
194
README.md
Normal file
194
README.md
Normal file
@@ -0,0 +1,194 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- text-generation-inference
|
||||
datasets:
|
||||
- HuggingFaceH4/ultrachat_200k
|
||||
- openchat/openchat_sharegpt4_dataset
|
||||
- Open-Orca/SlimOrca
|
||||
inference: false
|
||||
model-index:
|
||||
- name: falcon-rw-1b-chat
|
||||
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: 35.58
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
|
||||
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: 61.12
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
|
||||
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: 24.51
|
||||
name: accuracy
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
|
||||
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: 39.62
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
|
||||
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: 61.72
|
||||
name: accuracy
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
|
||||
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: 1.67
|
||||
name: accuracy
|
||||
source:
|
||||
url: >-
|
||||
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-chat
|
||||
name: Open LLM Leaderboard
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
# 🌟 Falcon-RW-1B-Chat
|
||||
|
||||
**Falcon-RW-1B-Chat is a conversational model with 1 billion parameters.** It's a further refinement of the [Falcon-RW-1B-Instruct-OpenOrca](https://huggingface.co/ericzzz/falcon-rw-1b-instruct-openorca), trained on selected data from the [HuggingFaceH4/ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) and [openchat/openchat_sharegpt4_dataset](https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset) datasets.
|
||||
|
||||
**✨Try it out at our [Tiny Chat](https://huggingface.co/spaces/ericzzz/tiny-chat) space running on free-tier hardware!✨**
|
||||
|
||||
The underlying Falcon-RW-1B-Instruct-OpenOrca model is built on the [Falcon-RW-1B](https://huggingface.co/tiiuae/falcon-rw-1b), a causal decoder-only model. It has been instruction-finetuned using the [Open-Orca/SlimOrca](https://huggingface.co/datasets/Open-Orca/SlimOrca) dataset.
|
||||
|
||||
**🎯 Purpose**
|
||||
|
||||
The Falcon-RW-1B-Chat aims to add conversational capabilities to the Falcon-RW-1B-Instruct-OpenOrca model. This initiative is driven by the need for a smaller, open-source, instruction-finetuned, ready-to-use model, suitable for users with limited computational resources, like lower-end consumer GPUs.
|
||||
|
||||
## [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_ericzzz__falcon-rw-1b-chat)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |37.37|
|
||||
|AI2 Reasoning Challenge (25-Shot)|35.58|
|
||||
|HellaSwag (10-Shot) |61.12|
|
||||
|MMLU (5-Shot) |24.51|
|
||||
|TruthfulQA (0-shot) |39.62|
|
||||
|Winogrande (5-shot) |61.72|
|
||||
|GSM8k (5-shot) | 1.67|
|
||||
|
||||
## 📖 Example Code
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
model_name = "ericzzz/falcon-rw-1b-chat"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name, device_map="auto", torch_dtype=torch.bfloat16
|
||||
)
|
||||
|
||||
chat_history = [
|
||||
{"role": "user", "content": "Hello!"},
|
||||
{"role": "assistant", "content": "Hello! How can I assist you today?"},
|
||||
{"role": "user", "content": "Explain what AI is."},
|
||||
]
|
||||
|
||||
input_ids = tokenizer.apply_chat_template(
|
||||
chat_history, tokenize=True, add_generation_prompt=True, return_tensors="pt"
|
||||
).to(model.device)
|
||||
output_tokens = model.generate(
|
||||
input_ids,
|
||||
do_sample=True,
|
||||
temperature=0.7,
|
||||
repetition_penalty=1.05,
|
||||
max_new_tokens=200,
|
||||
)
|
||||
output_text = tokenizer.decode(
|
||||
output_tokens[0][len(input_ids[0]) :], skip_special_tokens=True
|
||||
)
|
||||
|
||||
print(output_text)
|
||||
```
|
||||
|
||||
## ⚠️ Limitations
|
||||
|
||||
This model may generate inaccurate or misleading information and is prone to hallucination, creating plausible but false narratives. It lacks the ability to discern factual content from fiction and may inadvertently produce biased, harmful or offensive content. Its understanding of complex, nuanced queries is limited. Users should be aware of this and verify any information obtained from the model.
|
||||
|
||||
The model is provided 'as is' without any warranties, and the creators are not liable for any damages arising from its use. Users are responsible for their interactions with the model.
|
||||
|
||||
## 📬 Contact
|
||||
|
||||
For further inquiries or feedback, please contact at eric.fu96@aol.com.
|
||||
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_name_or_path": "./falcon-rw-1b-chat/epoch-1",
|
||||
"alibi": true,
|
||||
"apply_residual_connection_post_layernorm": false,
|
||||
"architectures": [
|
||||
"FalconForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bias": true,
|
||||
"bos_token_id": 11,
|
||||
"eos_token_id": 11,
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "falcon",
|
||||
"multi_query": false,
|
||||
"new_decoder_architecture": false,
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 24,
|
||||
"num_kv_heads": 32,
|
||||
"parallel_attn": false,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.35.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 50304
|
||||
}
|
||||
5
generation_config.json
Normal file
5
generation_config.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "4.35.2"
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c0bd4f9853ce19847e82725375c5d58d4e804497bb6294e00e5516a0061127f9
|
||||
size 2623284688
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
100305
tokenizer.json
Normal file
100305
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
20
tokenizer_config.json
Normal file
20
tokenizer_config.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"50256": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"chat_template": "{% for message in messages %}{% if loop.index > 1 and loop.previtem['role'] != 'assistant' %}{{ ' ' }}{% endif %}{% if message['role'] == 'system' %}{{ '[SYS] ' + message['content'].strip() }}{% elif message['role'] == 'user' %}{{ '[INST] ' + message['content'].strip() }}{% elif message['role'] == 'assistant' %}{{ '[RESP] ' + message['content'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ ' [RESP] ' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1024,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user