初始化项目，由ModelHub XC社区提供模型
Model: tiiuae/Falcon-E-3B-Base-prequantized Source: Original Platform
This commit is contained in:
ModelHub XC
50
.gitattributes
vendored
Normal file
50
.gitattributes
vendored
Normal file
@@ -0,0 +1,50 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
218
README.md
Normal file
218
README.md
Normal file
@@ -0,0 +1,218 @@
|
||||
---
|
||||
library_name: transformers
|
||||
tags:
|
||||
- bitnet
|
||||
- falcon-e
|
||||
- edge
|
||||
license: other
|
||||
license_name: falcon-llm-license
|
||||
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
|
||||
---
|
||||
|
||||
|
||||
|
||||
# Table of Contents
|
||||
|
||||
0. [TL;DR](#TL;DR)
|
||||
1. [Model Details](#model-details)
|
||||
2. [Training Details](#training-details)
|
||||
3. [Usage](#usage)
|
||||
4. [Evaluation](#evaluation)
|
||||
5. [Citation](#citation)
|
||||
|
||||
This is simply the mirror of https://huggingface.co/tiiuae/Falcon-E-3B-Base - branch `prequantized`
|
||||
|
||||
# TL;DR
|
||||
|
||||
# Model Details
|
||||
|
||||
## Model Description
|
||||
|
||||
- **Developed by:** [https://www.tii.ae](https://www.tii.ae)
|
||||
- **Model type:** Causal decoder-only / Base version
|
||||
- **Architecture:** Pure-transformer - 1.58bit version
|
||||
- **Language(s) (NLP):** English
|
||||
- **License:** Falcon-LLM License
|
||||
|
||||
# Training details
|
||||
|
||||
For more details about the training protocol of this model, please refer to the [Falcon-E technical blogpost](https://falcon-lm.github.io/blog/falcon-edge/).
|
||||
|
||||
# Usage
|
||||
|
||||
Currently to use this model you can either rely on Hugging Face transformers library or [BitNet](https://github.com/microsoft/BitNet) library. There are multiple ways to interact with the model depending on your target usage. For each of the Falcon-E series model, you have three variants: the BitNet model, the prequantized checkpoint for fine-tuning and the `bfloat16` version of the BitNet model.
|
||||
|
||||
### Inference
|
||||
|
||||
#### 🤗 transformers
|
||||
|
||||
In case you want to perform inference on the BitNet checkpoint run:
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_id = "tiiuae/Falcon-E-1B-Base"
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
torch_dtype=torch.bfloat16,
|
||||
).to("cuda")
|
||||
|
||||
# Perform text generation
|
||||
```
|
||||
|
||||
If you want to rather use the classic `bfloat16` version, you can run:
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_id = "tiiuae/Falcon-E-1B-Base"
|
||||
revision = "bfloat16"
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
torch_dtype=torch.bfloat16,
|
||||
revision=revision,
|
||||
).to("cuda")
|
||||
|
||||
# Perform text generation
|
||||
```
|
||||
|
||||
|
||||
#### BitNet
|
||||
|
||||
```
|
||||
git clone https://github.com/microsoft/BitNet && cd BitNet
|
||||
pip install -r requirements.txt
|
||||
python setup_env.py --hf-repo tiiuae/Falcon-E-1B-Base -q i2_s
|
||||
python run_inference.py -m models/Falcon-E-1B-Base/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv
|
||||
```
|
||||
|
||||
#### Apply mlx-lm
|
||||
|
||||
```
|
||||
pip install -U mlx-lm
|
||||
```
|
||||
|
||||
Then:
|
||||
```
|
||||
mlx_lm.generate --model tiiuae/Falcon-E-3B-Instruct --prompt "Implement bubble sort" --max-tokens 100 --temp 0.1
|
||||
```
|
||||
|
||||
|
||||
### Fine-tuning
|
||||
|
||||
For fine-tuning the model, you should load the `prequantized` revision of the model and use the `onebitllms` Python package:
|
||||
|
||||
```diff
|
||||
import torch
|
||||
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
from trl import SFTTrainer
|
||||
+ from onebitllms import replace_linear_with_bitnet_linear, quantize_to_1bit
|
||||
|
||||
model_id = "tiiuae/Falcon-E-1B-Base"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id, revision="prequantized")
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
torch_dtype=torch.bfloat16,
|
||||
+ revision="prequantized"
|
||||
)
|
||||
+ model = replace_linear_with_bitnet_linear(model)
|
||||
|
||||
trainer = SFTTrainer(
|
||||
model,
|
||||
...
|
||||
)
|
||||
|
||||
trainer.train()
|
||||
|
||||
+ quantize_to_1bit(output_directory)
|
||||
```
|
||||
|
||||
# Evaluation
|
||||
|
||||
We report in the following table our internal pipeline benchmarks:
|
||||
|
||||
**Note evaluation results are normalized score from former Hugging Face leaderboard v2 tasks**
|
||||
|
||||
<details>
|
||||
<summary class="bold"> For 1B scale models and below </summary>
|
||||
|
||||
| Model | Nb Params | Mem Footprint | IFEVAL | Math-Hard | GPQA | MuSR | BBH | MMLU-Pro | Avg. |
|
||||
| -------- | ------- | ------- | ------- | ------ | ----- | ----- | ----- | ------ | ---- |
|
||||
| Qwen-2.5-0.5B | 0.5B | 1GB | 16.27 | 3.93 | 0.0 | 2.08 | 6.95 | 10.06 | 6.55 |
|
||||
| SmolLM2-360M | 0.36B | 720MB | 21.15 | 1.21 | 0.0 | 7.73 | 5.54 | 1.88 | 6.25 |
|
||||
| Qwen-2.5-1.5B | 1.5B | 3.1GB | 26.74 | 9.14 | 16.66 | 5.27 | 20.61 | 4.7 | 13.85 |
|
||||
| Llama-3.2-1B | 1.24B | 2.47GB | 14.78 | 1.21 | 4.37 | 2.56 | 2.26 | 0 | 4.2 |
|
||||
| SmolLM2-1.7B | 1.7B | 3.4GB | 24.4 | 2.64 | 9.3 | 4.6 | 12.64 | 3.91 | 9.58 |
|
||||
| Falcon-3-1B-Base | 1.5B | 3GB | 24.28 | 3.32 | 11.34 | 9.71 | 6.76 | 3.91 | 9.89 |
|
||||
| Hymba-1.5B-Base | 1.5B | 3GB | 22.95 | 1.36 | 7.69 | 5.18 | 10.25 | 0.78 | 8.04 |
|
||||
| Falcon-E-1B-Base | 1.8B | **635MB** | 32.9 | 10.97 | 2.8 | 3.65 | 12.28 | 17.82 | 13.40 |
|
||||
|
||||
</details>
|
||||
|
||||
|
||||
<details>
|
||||
<summary class="bold"> For 3B scale models </summary>
|
||||
|
||||
| Model | Nb Params | Mem Footprint | IFEVAL | Math-Hard | GPQA | MuSR | BBH | MMLU-Pro | Avg. |
|
||||
| -------- | ------- | ------- | ------- | ------ | ----- | ----- | ----- | ------ | ---- |
|
||||
| Falcon-3-3B-Base | 3B | 6.46GB | 15.74 | 11.78 | 21.58 | 6.27 | 18.09 | 6.26 | 15.74 |
|
||||
| Qwen2.5-3B | 3B | 6.17GB | 26.9 | 14.8 | 24.3 | 11.76 | 24.48 | 6.38 | 18.1 |
|
||||
| Falcon-E-3B-Base | 3B | **999MB** | 36.67 | 13.45 | 8.67 | 4.14 | 19.83 | 27.16 | 18.32 |
|
||||
|
||||
</details>
|
||||
|
||||
Below are the results for instruction fine-tuned models:
|
||||
|
||||
<details>
|
||||
<summary class="bold"> For 1B scale models and below </summary>
|
||||
|
||||
| Model | Nb Params | Mem Footprint | IFEVAL | Math-Hard | GPQA | MuSR | BBH | MMLU-Pro | Avg. |
|
||||
| -------- | ------- | ------- | ------- | ------ | ----- | ----- | ----- | ------ | ---- |
|
||||
| Qwen-2.5-0.5B-Instruct | 500M | 1GB | 30.71 | 0 | 8.43 | 0.94 | 7.75 | 0 | 6.59 |
|
||||
| SmolLM2-360M-Instruct | 360M | 720MB | 38.42 | 1.51 | 4.17 | 2.77 | 1.3 | 0.67 | 8.14 |
|
||||
| Qwen-2.5-1.5B-Instruct | 1.5B | 3.1GB | 44.76 | 22.05 | 19.81 | 3.19 | 19.99 | 0.78 | 18.43 |
|
||||
| SmolLM2-1.7B | 1.7B | 3.4GB | 53.68 | 5.82 | 10.92 | 4.1 | 11.71 | 0 | 15.02 |
|
||||
| Falcon-3-1B-Instruct | 1.5B | 3GB | 55.57 | 6.34 | 12.96 | 10.56 | 9.32 | 2.24 | 16.16 |
|
||||
| Hymba-1.5B-Instruct | 1.5B | 3GB | 60.09 | 2.72 | 4.59 | 1.05 | 11.56 | 5.515 | 14.19 |
|
||||
| Falcon-E-1B-Instruct | 1.8B | **635MB** | 54.35 | 9.12 | 16.5 | 2.51 | 19.42 | 9.64 | 18.59 |
|
||||
|
||||
</details>
|
||||
|
||||
|
||||
<details>
|
||||
<summary class="bold"> For 3B scale models </summary>
|
||||
|
||||
| Model | Nb Params | Mem Footprint | IFEVAL | Math-Hard | GPQA | MuSR | BBH | MMLU-Pro | Avg. |
|
||||
| -------- | ------- | ------- | ------- | ------ | ----- | ----- | ----- | ------ | ---- |
|
||||
| Falcon-3-3B-Instruct | 3B | 6.46GB | 69.77 | 25 | 26.29 | 11.13 | 22.28 | 5.15 | 26.6 |
|
||||
| Qwen2.5-3B-Instruct | 3B | 6.17GB | 64.75 | 36.78 | 25.8 | 7.57 | 25.05 | 3.02 | 27.16 |
|
||||
| Falcon-E-3B-Instruct | 3B | **999MB** | 60.97 | 15.3 | 23.59 | 2.12 | 26.45 | 7.45 | 22.64666667 |
|
||||
|
||||
</details>
|
||||
|
||||
|
||||
## Useful links
|
||||
|
||||
- View [our release blogpost](https://falcon-lm.github.io/blog/falcon-edge/).
|
||||
- Learn more about [`onebitllms` library](https://github.com/tiiuae/onebitllms).
|
||||
- Feel free to join [our discord server](https://discord.gg/fwXpMyGc) if you have any questions or to interact with our researchers and developers.
|
||||
|
||||
## Citation
|
||||
|
||||
If the Falcon-E family of models were helpful to your work, feel free to give us a cite.
|
||||
|
||||
```
|
||||
@misc{tiionebitllms,
|
||||
title = {Falcon-E, a series of powerful, universal and fine-tunable 1.58bit language models.},
|
||||
author = {Falcon-LLM Team},
|
||||
month = {April},
|
||||
url = {https://falcon-lm.github.io/blog/falcon-edge},
|
||||
year = {2025}
|
||||
}
|
||||
```
|
||||
90
chat_template.jinja
Normal file
90
chat_template.jinja
Normal file
@@ -0,0 +1,90 @@
|
||||
{# ================= SYSTEM PROMPT ================= #}
|
||||
{%- if messages and messages[0]['role'] == 'system' %}
|
||||
{%- set system_msg = messages[0]['content'] %}
|
||||
{%- set remaining_messages = messages[1:] %}
|
||||
{%- elif messages and messages[0]['role'] == 'developer' %}
|
||||
{%- set system_msg = messages[0]['content'] %}
|
||||
{%- set remaining_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set system_msg = "You are Falcon, a helpful AI assistant created by Technology Innovation Institute (TII)." %}
|
||||
{%- set remaining_messages = messages %}
|
||||
{%- endif %}
|
||||
{%- if tools %}
|
||||
<|im_start|>system
|
||||
{{ system_msg }}
|
||||
# Tools
|
||||
You may call one or more functions to assist with the user query.
|
||||
<tools>
|
||||
{%- for tool in tools %}
|
||||
{{ tool | tojson }}
|
||||
{%- endfor %}
|
||||
</tools>
|
||||
<|im_end|>
|
||||
{%- else %}
|
||||
<|im_start|>system
|
||||
{{ system_msg }}
|
||||
<|im_end|>
|
||||
{%- endif %}
|
||||
{# ================= FIND LAST USER QUERY ================= #}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=remaining_messages|length - 1) %}
|
||||
{%- for message in remaining_messages %}
|
||||
{%- if message.role == "user" %}
|
||||
{%- set ns.last_query_index = loop.index0 %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{# ================= RENDER MESSAGES ================= #}
|
||||
{%- for message in remaining_messages %}
|
||||
{# ---- Normalize content to string ---- #}
|
||||
{%- set content = message.get('content', '') %}
|
||||
{%- set reasoning_content = message.get('reasoning_content', none) %}
|
||||
{%- if content is string %}
|
||||
{%- set content_str = content %}
|
||||
{%- elif content is not none %}
|
||||
{%- set ns_content = namespace(text='') %}
|
||||
{%- for item in content if item.type == 'text' %}
|
||||
{%- set ns_content.text = ns_content.text ~ item.text %}
|
||||
{%- endfor %}
|
||||
{%- set content_str = ns_content.text %}
|
||||
{%- endif %}
|
||||
{# ================= USER ================= #}
|
||||
{%- if message.role in ['user', 'human'] %}
|
||||
|
||||
<|im_start|>user
|
||||
{{ content_str }}<|im_end|>
|
||||
{%- elif message.role in ['assistant', 'gpt', 'function_call'] %}
|
||||
|
||||
<|im_start|>assistant
|
||||
{%- if reasoning_content is string %}
|
||||
{{ "\n<think>" ~ reasoning_content ~ "</think>" }}
|
||||
{%- endif %}
|
||||
|
||||
{{ content_str }}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
|
||||
<tool_call>
|
||||
{"name": "{{ tool_call.name }}", "arguments": {{ tool_call.arguments if tool_call.arguments is string else (tool_call.arguments | tojson) }}}
|
||||
</tool_call>
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
<|im_end|>
|
||||
{%- elif message.role == 'tool' %}
|
||||
|
||||
<|im_start|>user
|
||||
<tool_response>
|
||||
{{ content_str }}
|
||||
</tool_response><|im_end|>
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{# ================= GENERATION PROMPT ================= #}
|
||||
{%- if add_generation_prompt %}
|
||||
|
||||
<|im_start|>assistant
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- "\n<think></think>" }}
|
||||
{%- endif %}
|
||||
|
||||
{%- endif %}
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 11,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13312,
|
||||
"max_position_embeddings": 32768,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": null,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.5.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
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": 11,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d5bf4792081fb265f2e4c0b17c3b8ea22c8a267a12847e37eaca99d3a5d58ff0
|
||||
size 6107206592
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bebbcd0f6c0f52383e4e919d5b24d4585e0203fd010e61999ce339cf4ba2cbef
|
||||
size 2351345
|
||||
8
tokenizer_config.json
Normal file
8
tokenizer_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"backend": "tokenizers",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|end_of_text|>",
|
||||
"is_local": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"tokenizer_class": "TokenizersBackend"
|
||||
}
|
||||
Reference in New Issue
Block a user