初始化项目，由ModelHub XC社区提供模型
Model: tiiuae/Falcon-H1R-7B Source: Original Platform
This commit is contained in:
ModelHub XC
8
.eval_results/gpqa.yaml
Normal file
8
.eval_results/gpqa.yaml
Normal file
@@ -0,0 +1,8 @@
|
||||
- dataset:
|
||||
id: Idavidrein/gpqa
|
||||
task_id: gpqa_diamond
|
||||
value: 61.3
|
||||
date: '2026-01-15'
|
||||
source:
|
||||
url: https://huggingface.co/tiiuae/Falcon-H1R-7B
|
||||
name: Model Card
|
||||
7
.eval_results/hle.yaml
Normal file
7
.eval_results/hle.yaml
Normal file
@@ -0,0 +1,7 @@
|
||||
- dataset:
|
||||
id: cais/hle
|
||||
value: 11.1
|
||||
date: '2026-01-15'
|
||||
source:
|
||||
url: https://huggingface.co/tiiuae/Falcon-H1R-7B
|
||||
name: Model Card
|
||||
7
.eval_results/mmlu_pro.yaml
Normal file
7
.eval_results/mmlu_pro.yaml
Normal file
@@ -0,0 +1,7 @@
|
||||
- dataset:
|
||||
id: TIGER-Lab/MMLU-Pro
|
||||
value: 72.1
|
||||
date: '2026-01-15'
|
||||
source:
|
||||
url: https://huggingface.co/tiiuae/Falcon-H1R-7B
|
||||
name: Model Card
|
||||
53
.gitattributes
vendored
Normal file
53
.gitattributes
vendored
Normal file
@@ -0,0 +1,53 @@
|
||||
*.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
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
451
README.md
Normal file
451
README.md
Normal file
@@ -0,0 +1,451 @@
|
||||
---
|
||||
base_model:
|
||||
- tiiuae/Falcon-H1-7B-Base
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
license: other
|
||||
license_name: falcon-llm-license
|
||||
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
|
||||
tags:
|
||||
- falcon-h1r
|
||||
---
|
||||
|
||||
<img src="https://huggingface.co/datasets/tiiuae/reasoning-images/resolve/main/falcon-h1r-logo.png" alt="drawing" width="800"/>
|
||||
|
||||
# Falcon-H1R-7B
|
||||
|
||||
This repository presents **Falcon-H1R-7B**, a reasoning-specialized model introduced in the paper [Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling](https://huggingface.co/papers/2601.02346).
|
||||
|
||||
Built on top of [Falcon-H1-7B-Base](https://huggingface.co/tiiuae/Falcon-H1-7B-Base), it was trained via cold-start supervised fine-tuning with long reasoning traces and further enhanced by scaling RL with GRPO. The model demonstrates outstanding performance across various benchmark evaluations, including mathematics, programming, instruction following, and general logic.
|
||||
|
||||
## Model Description
|
||||
|
||||
- **Developed by:** [Technology Innovation Institute](https://www.tii.ae)
|
||||
- **Model type:** Causal decoder-only
|
||||
- **Architecture:** Hybrid (Transformers + Mamba2) architecture
|
||||
- **Language(s):** English, Multilingual
|
||||
- **License:** [Falcon-LLM License](https://falconllm.tii.ae/falcon-terms-and-conditions.html)
|
||||
|
||||
## Training details
|
||||
|
||||
For more details about the training protocol of this model, please refer to the [Falcon-H1R technical blogpost](https://falcon-lm.github.io/blog/falcon-h1r-7b) and [Technical Report](https://github.com/tiiuae/falcon-h1r/blob/main/tech_report.pdf).
|
||||
|
||||
# Usage
|
||||
|
||||
Currently to use this model, you can either rely on Hugging Face `transformers`, `vLLM` or `SGLang` library.
|
||||
|
||||
## Inference
|
||||
|
||||
Make sure to install the latest version of `transformers` or `vLLM` or `SGLang`.
|
||||
|
||||
```bash
|
||||
pip install transformers
|
||||
pip install mamba-ssm[causal-conv1d]
|
||||
```
|
||||
|
||||
For vLLM, make sure to install `vllm=0.11.0`:
|
||||
|
||||
```bash
|
||||
pip install "vllm>=0.11.0"
|
||||
```
|
||||
|
||||
## Sampling Parameters
|
||||
|
||||
We recommend using a **temperature** of **0.6** and **top-p** as **0.95** with max new tokens up to 65536.
|
||||
For supported frameworks, you can adjust the repetition_penalty and presence_penalty parameters to reduce endless repetitions.
|
||||
For reasoning tasks with continuous batching and requiring higher max new tokens, we recommend to use TP=2.
|
||||
|
||||
## 🤗 Transformers
|
||||
|
||||
Refer to the snippet below to run H1R models using 🤗 transformers.
|
||||
Model will generate think content wrapped in a `<think>...</think>` block, followed by the final response.
|
||||
|
||||
<details>
|
||||
<summary> Click to expand </summary>
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
model_id = "tiiuae/Falcon-H1R-7B"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", dtype="auto")
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": "What is the derivative of x^2?"},
|
||||
]
|
||||
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
|
||||
|
||||
outputs = model.generate(
|
||||
inputs.to(model.device),
|
||||
max_new_tokens=65536,
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
do_sample=True,
|
||||
)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
</details>
|
||||
|
||||
## vLLM
|
||||
|
||||
For vLLM, simply start a server by executing the command below:
|
||||
|
||||
<details>
|
||||
<summary> Click to expand </summary>
|
||||
<br>
|
||||
|
||||
```python
|
||||
vllm serve tiiuae/Falcon-H1R-7B \
|
||||
--tensor-parallel-size 1 \
|
||||
--data-parallel-size 1 \
|
||||
--reasoning-parser deepseek_r1
|
||||
```
|
||||
<br>
|
||||
Additional flags:
|
||||
|
||||
* You can reduce `--max-model-len` to preserve memory. Default value is `262144` which is quite large but not necessary for most scenarios.
|
||||
* For function calling, append `--enable-auto-tool-choice` and `--tool-call-parser hermes` to the vllm serve command.
|
||||
|
||||
|
||||
vLLM client execution code:
|
||||
```python
|
||||
from openai import OpenAI
|
||||
import json
|
||||
|
||||
client = OpenAI(
|
||||
base_url="http://localhost:8000/v1",
|
||||
api_key="EMPTY",
|
||||
)
|
||||
|
||||
completion = client.chat.completions.create(
|
||||
model="tiiuae/Falcon-H1R-7B",
|
||||
messages=[
|
||||
{"role": "user", "content": "If the product of two numbers is 360 and their GCD is 6, what is their LCM?"},
|
||||
],
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
max_tokens=65536
|
||||
)
|
||||
|
||||
msg = completion.choices[0].message
|
||||
|
||||
print(json.dumps({
|
||||
"reasoning": msg.reasoning_content,
|
||||
"answer": msg.content
|
||||
}, indent=2))
|
||||
```
|
||||
</details>
|
||||
|
||||
## SGLang
|
||||
|
||||
For SGLang, simply start a server by executing the command below:
|
||||
|
||||
<details>
|
||||
<summary> Click to expand </summary>
|
||||
<br>
|
||||
|
||||
```python
|
||||
python -m sglang.launch_server \
|
||||
--model tiiuae/Falcon-H1R-7B \
|
||||
--tensor-parallel-size 1 \
|
||||
--reasoning-parser deepseek-r1
|
||||
```
|
||||
<br>
|
||||
|
||||
SGLang client execution code:
|
||||
```python
|
||||
from openai import OpenAI
|
||||
import json
|
||||
|
||||
client = OpenAI(
|
||||
base_url="http://localhost:30000/v1",
|
||||
api_key="EMPTY",
|
||||
)
|
||||
|
||||
completion = client.chat.completions.create(
|
||||
model="tiiuae/Falcon-H1R-7B",
|
||||
messages=[
|
||||
{"role": "user", "content": "How many solutions in integers satisfy ∣x∣+∣y∣=20?"},
|
||||
],
|
||||
max_tokens=65536,
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
)
|
||||
|
||||
msg = completion.choices[0].message
|
||||
|
||||
print(json.dumps({
|
||||
"reasoning": msg.reasoning_content,
|
||||
"answer": msg.content
|
||||
}, indent=2))
|
||||
```
|
||||
</details>
|
||||
<br>
|
||||
|
||||
# Evaluation
|
||||
|
||||
Falcon-H1R achieves state of art results in reasoning benchmarks.
|
||||
|
||||
<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;">
|
||||
<colgroup>
|
||||
<col style="width: 6%;">
|
||||
<col style="width: 6%;">
|
||||
<col style="background-color: rgba(80, 15, 213, 0.5); width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
</colgroup>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Category</th>
|
||||
<th>Benchmark</th>
|
||||
<th>Falcon-H1R-7B</th>
|
||||
<th>Qwen3-8B</th>
|
||||
<th>DeepSeek-R1-0528-Qwen3-8B</th>
|
||||
<th>Phi-4-Reasoning-Plus-14B</th>
|
||||
<th>Apriel-1.5-15b-Thinker</th>
|
||||
<th>GPT-OSS-20B</th>
|
||||
<th>Qwen3-32B</th>
|
||||
<th>Nemotron-H-47B-Reasoning</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td rowspan="5">MATH</td>
|
||||
<td>AIME24</td>
|
||||
<td><b>88.1</b></td>
|
||||
<td>77.9</td>
|
||||
<td>83.3</td>
|
||||
<td>77.2</td>
|
||||
<td>86.2</td>
|
||||
<td>83.3</td>
|
||||
<td>79.4</td>
|
||||
<td>64.6</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>AIME25</td>
|
||||
<td>83.1</td>
|
||||
<td>65.8</td>
|
||||
<td>75.8</td>
|
||||
<td>71.2</td>
|
||||
<td>80.0</td>
|
||||
<td><b>84.4</b></td>
|
||||
<td>71.0</td>
|
||||
<td>51.4</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>HMMT25</td>
|
||||
<td><b>64.9</b></td>
|
||||
<td>41.0</td>
|
||||
<td>54.3</td>
|
||||
<td>47.7</td>
|
||||
<td>61.0</td>
|
||||
<td>64.8</td>
|
||||
<td>49.8</td>
|
||||
<td>34.2</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>AMO-BENCH</td>
|
||||
<td><b>36.3</b></td>
|
||||
<td>14.1</td>
|
||||
<td>23.3</td>
|
||||
<td>15.0</td>
|
||||
<td>22.2</td>
|
||||
<td>26.0</td>
|
||||
<td>21.3</td>
|
||||
<td>7.0</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MATH500</td>
|
||||
<td><b>97.4</b></td>
|
||||
<td>97.4</td>
|
||||
<td>96.8</td>
|
||||
<td>95.4</td>
|
||||
<td>97.2</td>
|
||||
<td>94.8</td>
|
||||
<td>96.8</td>
|
||||
<td>91.4</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="2">Code</td>
|
||||
<td>LCBv5-v6</td>
|
||||
<td>68.6</td>
|
||||
<td>53.0</td>
|
||||
<td>57.2</td>
|
||||
<td>53.1</td>
|
||||
<td>53.0</td>
|
||||
<td><b>72.0</b></td>
|
||||
<td>61.0</td>
|
||||
<td>47.4</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>SciCode (sub/main)</td>
|
||||
<td>28.3 / 3.9</td>
|
||||
<td>28.3 / 6.7</td>
|
||||
<td>22.2 / 2.6</td>
|
||||
<td>29.8 / 7.2</td>
|
||||
<td>31.9 / 8.2</td>
|
||||
<td>34.9 / 6.2</td>
|
||||
<td>36.4 / 9.2</td>
|
||||
<td>26.1 / 4.6</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="4">General</td>
|
||||
<td>GPQA-D</td>
|
||||
<td>61.3</td>
|
||||
<td>61.2</td>
|
||||
<td>61.4</td>
|
||||
<td><b>67.9</b></td>
|
||||
<td>68.2</td>
|
||||
<td>61.2</td>
|
||||
<td>67.3</td>
|
||||
<td>56.8</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MMLU-Pro</td>
|
||||
<td>72.1</td>
|
||||
<td>63.5</td>
|
||||
<td>69.1</td>
|
||||
<td><b>79.2</b></td>
|
||||
<td>76.5</td>
|
||||
<td>75.6</td>
|
||||
<td>73.9</td>
|
||||
<td>78.6</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>HLE</td>
|
||||
<td>11.1</td>
|
||||
<td>4.2</td>
|
||||
<td>5.6</td>
|
||||
<td>5.9</td>
|
||||
<td>12.0</td>
|
||||
<td>9.8</td>
|
||||
<td>8.3</td>
|
||||
<td>4.4</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>IFBench</td>
|
||||
<td>53.4</td>
|
||||
<td>35.3</td>
|
||||
<td>29.2</td>
|
||||
<td>51.7</td>
|
||||
<td>55.8</td>
|
||||
<td>69.4</td>
|
||||
<td>35.4</td>
|
||||
<td>34.3</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="2">Agentic Workflows</td>
|
||||
<td>𝜏²-Bench Telecom</td>
|
||||
<td>25.4</td>
|
||||
<td>27.8</td>
|
||||
<td></td>
|
||||
<td></td>
|
||||
<td>68.4</td>
|
||||
<td>60.2</td>
|
||||
<td>29.8</td>
|
||||
<td>11.4</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Terminal-Bench Hard</td>
|
||||
<td>4.9</td>
|
||||
<td>2.1</td>
|
||||
<td>1.4</td>
|
||||
<td>2.1</td>
|
||||
<td>9.9</td>
|
||||
<td>9.9</td>
|
||||
<td>2.8</td>
|
||||
<td>1.4</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
TTS represents test time scaling results on few of the benchmarks that we evaluated via [DeepConf](https://github.com/facebookresearch/deepconf). Note that AMO-Bench* is limited to the parser-verifiable subset which comprises 39 problems.
|
||||
|
||||
<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;">
|
||||
<colgroup>
|
||||
<col style="width: 6%;">
|
||||
<col style="background-color: rgba(80, 15, 213, 0.5); width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
<col style="width: 5%;">
|
||||
</colgroup>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Benchmark</th>
|
||||
<th>Falcon-H1R-7B</th>
|
||||
<th>Qwen3-8B</th>
|
||||
<th>DeepSeek-R1-0528-Qwen3-8B</th>
|
||||
<th>Nemotron-H-8B</th>
|
||||
<th>Phi-4-Reasoning-Plus-14B</th>
|
||||
<th>Qwen3-32B</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td>AIME24</td>
|
||||
<td><b>96.7</b></td>
|
||||
<td>80.0</td>
|
||||
<td>90.0</td>
|
||||
<td>53.3</td>
|
||||
<td>86.7</td>
|
||||
<td>86.7</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>AIME25</td>
|
||||
<td><b>96.7</b></td>
|
||||
<td>80.0</td>
|
||||
<td>82.8</td>
|
||||
<td>43.3</td>
|
||||
<td>83.3</td>
|
||||
<td>86.7</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>GPQA-D</td>
|
||||
<td>70.2</td>
|
||||
<td>60.9</td>
|
||||
<td>59.9</td>
|
||||
<td>61.1</td>
|
||||
<td><b>73.2</b></td>
|
||||
<td>70.1</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>AMO-Bench*</td>
|
||||
<td><b>35.9</b></td>
|
||||
<td>15.4</td>
|
||||
<td>25.6</td>
|
||||
<td>7.7</td>
|
||||
<td>20.5</td>
|
||||
<td>28.2</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
# Useful links
|
||||
|
||||
- View [our release blogpost](https://falcon-lm.github.io/blog/falcon-h1r-7b).
|
||||
- View [our technical report](https://huggingface.co/papers/2601.02346).
|
||||
- Feel free to join [our discord server](https://discord.gg/Cbek57PrZE) if you have any questions or to interact with our researchers and developers.
|
||||
|
||||
# Citation
|
||||
|
||||
If the Falcon-H1R family of reasoning models is helpful to your work, feel free to give us a cite.
|
||||
|
||||
```
|
||||
@misc{falcon-h1r,
|
||||
title={Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling},
|
||||
author={Falcon LLM Team and Iheb Chaabane and Puneesh Khanna and Suhail Mohmad and Slim Frikha and Shi Hu and Abdalgader Abubaker and Reda Alami and Mikhail Lubinets and Mohamed El Amine Seddik and Hakim Hacid},
|
||||
year={2026},
|
||||
eprint={2601.02346},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.AI},
|
||||
url={https://arxiv.org/abs/2601.02346},
|
||||
}
|
||||
```
|
||||
101
chat_template.jinja
Normal file
101
chat_template.jinja
Normal file
@@ -0,0 +1,101 @@
|
||||
{# --- System Prompt Handling --- #}
|
||||
{%- if messages and messages[0]['role'] == 'system' %}
|
||||
{% 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). To answer the user's question, you first think about the reasoning process and then provide the user with the answer. The reasoning process is enclosed within <think> </think> tags, i.e., <think> reasoning process here </think> answer here." %}
|
||||
{%- 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. You are provided with function signatures within <tools></tools> XML tags.
|
||||
<tools>
|
||||
{%- for tool in tools %}
|
||||
{{- "" }}
|
||||
{{ tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "" }}
|
||||
</tools>
|
||||
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
||||
<tool_call>
|
||||
{"name": <function-name>, "arguments": <args-json-object>}
|
||||
</tool_call>
|
||||
<|im_end|>
|
||||
|
||||
{%- else %}
|
||||
<|im_start|>system
|
||||
{{ system_msg }}
|
||||
<|im_end|>
|
||||
{%- endif %}
|
||||
|
||||
{# --- Render remaining messages --- #}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}{%- for message in remaining_messages %}
|
||||
{%- set content = message.get('content','') %}
|
||||
{%- if message['role'] == 'user' %}
|
||||
{{- '<|im_start|>' + message['role'] + '\n' + content + '<|im_end|>\n' }}
|
||||
{%- elif message['role'] == 'assistant' %}
|
||||
{{- '<|im_start|>' + message.role + '\n' }}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- content + '\n' }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- content + '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tools and 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>\n' }}
|
||||
{{- '{"name": "'+ tool_call.name + '", "arguments":' }}
|
||||
{%- if tool_call.arguments is string -%}
|
||||
{{ tool_call.arguments }}
|
||||
{%- else -%}
|
||||
{{ tool_call.arguments | tojson }}
|
||||
{%- endif -%}
|
||||
{{- '}' }}
|
||||
{{- '\n</tool_call>\n' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{%- if not loop.last %}
|
||||
{{- '<|im_end|>' + '\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_end|>' }}
|
||||
{%- endif %}
|
||||
{%- elif message['role'] == 'tool' %}
|
||||
{# Tool responses treated as user messages #}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' + message['content'] + '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{# --- Add generation prompt after last message if requested --- #}
|
||||
{%- if loop.last and add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
64
config.json
Normal file
64
config.json
Normal file
@@ -0,0 +1,64 @@
|
||||
{
|
||||
"architectures": [
|
||||
"FalconH1ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attention_in_multiplier": 1.0,
|
||||
"attention_out_multiplier": 0.10416666666666669,
|
||||
"attn_layer_indices": null,
|
||||
"bos_token_id": 1,
|
||||
"embedding_multiplier": 5.656854249492381,
|
||||
"eos_token_id": 11,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"key_multiplier": 0.030690398488999456,
|
||||
"lm_head_multiplier": 0.013020833333333334,
|
||||
"mamba_chunk_size": 128,
|
||||
"mamba_conv_bias": true,
|
||||
"mamba_d_conv": 4,
|
||||
"mamba_d_head": 128,
|
||||
"mamba_d_ssm": 3072,
|
||||
"mamba_d_state": 256,
|
||||
"mamba_expand": 2,
|
||||
"mamba_n_groups": 1,
|
||||
"mamba_n_heads": 24,
|
||||
"mamba_norm_before_gate": false,
|
||||
"mamba_proj_bias": false,
|
||||
"mamba_rms_norm": true,
|
||||
"mamba_use_mlp": true,
|
||||
"max_position_embeddings": 262144,
|
||||
"mlp_bias": false,
|
||||
"mlp_expansion_factor": 8,
|
||||
"mlp_multipliers": [
|
||||
0.2946278254943948,
|
||||
0.032552083333333336
|
||||
],
|
||||
"model_type": "falcon_h1",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 44,
|
||||
"num_key_value_heads": 2,
|
||||
"num_logits_to_keep": 1,
|
||||
"pad_token_id": 0,
|
||||
"projectors_bias": false,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 100000000000,
|
||||
"ssm_in_multiplier": 0.4166666666666667,
|
||||
"ssm_multipliers": [
|
||||
0.3535533905932738,
|
||||
0.25,
|
||||
0.1767766952966369,
|
||||
0.5,
|
||||
0.3535533905932738
|
||||
],
|
||||
"ssm_out_multiplier": 0.11785113019775792,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.52.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 130048
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": [11, 228],
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.52.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:00b87b467d198ebf4535e7974bafeeb15d5d6efe1b6008e0abde6fa5abf27cf8
|
||||
size 4994379808
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bf5946ebb3d9033edf2ce34d0fc8ecad440b8a1c41e90487ffc0e7c04b49b583
|
||||
size 4947500624
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d7f5f76284ae04eb345b039bd197ebf054bd4786a8a80f62e94fbc5385e626c1
|
||||
size 4957150528
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3d70264d6010ea081f313e8e0a5096269e6fd0baeea70e2afecb2ac6ae74d70
|
||||
size 272351040
|
||||
758
model.safetensors.index.json
Normal file
758
model.safetensors.index.json
Normal file
@@ -0,0 +1,758 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 15171297472
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.final_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mamba.out_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.10.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mamba.A_log": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mamba.A_log": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mamba.A_log": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.feed_forward.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.15.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.mamba.A_log": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.19.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mamba.conv1d.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.2.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.mamba.conv1d.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.20.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.mamba.out_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.21.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mamba.A_log": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.mamba.D": "model-00004-of-00004.safetensors",
|
||||
"model.layers.22.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.mamba.dt_bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.24.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.mamba.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.24.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mamba.A_log": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mamba.dt_bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.32.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.32.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.32.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.32.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.32.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.32.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.32.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.32.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.33.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.34.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.34.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.34.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.35.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.36.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.36.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.36.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.36.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.mamba.D": "model-00001-of-00004.safetensors",
|
||||
"model.layers.36.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.36.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.36.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.36.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.37.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.37.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.37.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.37.mamba.dt_bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.37.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.37.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.37.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.38.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.38.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.38.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.38.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.38.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.38.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.38.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.38.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.39.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.39.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.39.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.39.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.39.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.39.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.39.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.39.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.39.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.39.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.40.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.40.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.40.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.40.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.40.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.40.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.40.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.41.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.41.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.41.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.41.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.41.mamba.conv1d.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.41.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.42.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.42.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.mamba.A_log": "model-00002-of-00004.safetensors",
|
||||
"model.layers.42.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.42.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.42.mamba.dt_bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.42.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.42.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.42.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.feed_forward.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.43.feed_forward.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.43.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.43.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.43.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.43.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.43.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.43.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.mamba.A_log": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.mamba.norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mamba.A_log": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mamba.in_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.6.mamba.norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.mamba.D": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.feed_forward.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mamba.A_log": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.mamba.dt_bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.feed_forward.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mamba.A_log": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mamba.D": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mamba.dt_bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mamba.norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
862
special_tokens_map.json
Normal file
862
special_tokens_map.json
Normal file
@@ -0,0 +1,862 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|pad|>",
|
||||
">>ABSTRACT<<",
|
||||
">>INTRODUCTION<<",
|
||||
">>SUMMARY<<",
|
||||
">>COMMENT<<",
|
||||
">>ANSWER<<",
|
||||
">>QUESTION<<",
|
||||
">>DOMAIN<<",
|
||||
">>PREFIX<<",
|
||||
">>SUFFIX<<",
|
||||
">>MIDDLE<<",
|
||||
"<|finetune_right_pad_id|>",
|
||||
"<|start_header_id|>",
|
||||
"<|end_header_id|>",
|
||||
"<|eom_id|>",
|
||||
"<|eot_id|>",
|
||||
"<|begin_of_text|>",
|
||||
">>TITLE<<",
|
||||
"<schema>",
|
||||
"</schema>",
|
||||
"<scratch_pad>",
|
||||
"</scratch_pad>",
|
||||
"<explanation>",
|
||||
"</explanation>",
|
||||
"<file_sep>",
|
||||
"<repo_name>",
|
||||
"<|im_end|>",
|
||||
"<|im_start|>",
|
||||
">>UNUSED_119<<",
|
||||
">>UNUSED_120<<",
|
||||
"<|system|>",
|
||||
">>UNUSED_218<<",
|
||||
">>UNUSED_219<<",
|
||||
">>UNUSED_220<<",
|
||||
">>UNUSED_221<<",
|
||||
">>UNUSED_222<<",
|
||||
">>UNUSED_223<<",
|
||||
">>UNUSED_224<<",
|
||||
">>UNUSED_225<<",
|
||||
">>UNUSED_226<<",
|
||||
">>UNUSED_227<<",
|
||||
">>UNUSED_228<<",
|
||||
">>UNUSED_229<<",
|
||||
">>UNUSED_230<<",
|
||||
">>UNUSED_231<<",
|
||||
">>UNUSED_232<<",
|
||||
">>UNUSED_233<<",
|
||||
">>UNUSED_234<<",
|
||||
">>UNUSED_235<<",
|
||||
">>UNUSED_236<<",
|
||||
">>UNUSED_237<<",
|
||||
">>UNUSED_238<<",
|
||||
">>UNUSED_239<<",
|
||||
">>UNUSED_240<<",
|
||||
">>UNUSED_241<<",
|
||||
">>UNUSED_242<<",
|
||||
">>UNUSED_243<<",
|
||||
">>UNUSED_244<<",
|
||||
">>UNUSED_245<<",
|
||||
">>UNUSED_246<<",
|
||||
">>UNUSED_247<<",
|
||||
">>UNUSED_248<<",
|
||||
">>UNUSED_249<<",
|
||||
">>UNUSED_250<<",
|
||||
">>UNUSED_251<<",
|
||||
">>UNUSED_252<<",
|
||||
">>UNUSED_253<<",
|
||||
">>UNUSED_254<<",
|
||||
">>UNUSED_255<<",
|
||||
">>UNUSED_256<<",
|
||||
">>UNUSED_257<<",
|
||||
">>UNUSED_258<<",
|
||||
">>UNUSED_259<<",
|
||||
">>UNUSED_260<<",
|
||||
">>UNUSED_261<<",
|
||||
">>UNUSED_262<<",
|
||||
">>UNUSED_263<<",
|
||||
">>UNUSED_264<<",
|
||||
">>UNUSED_265<<",
|
||||
">>UNUSED_266<<",
|
||||
">>UNUSED_267<<",
|
||||
">>UNUSED_268<<",
|
||||
">>UNUSED_269<<",
|
||||
">>UNUSED_270<<",
|
||||
">>UNUSED_271<<",
|
||||
">>UNUSED_272<<",
|
||||
">>UNUSED_273<<",
|
||||
">>UNUSED_274<<",
|
||||
">>UNUSED_275<<",
|
||||
">>UNUSED_276<<",
|
||||
">>UNUSED_277<<",
|
||||
">>UNUSED_278<<",
|
||||
">>UNUSED_279<<",
|
||||
">>UNUSED_280<<",
|
||||
">>UNUSED_281<<",
|
||||
">>UNUSED_282<<",
|
||||
">>UNUSED_283<<",
|
||||
">>UNUSED_284<<",
|
||||
">>UNUSED_285<<",
|
||||
">>UNUSED_286<<",
|
||||
">>UNUSED_287<<",
|
||||
">>UNUSED_288<<",
|
||||
">>UNUSED_289<<",
|
||||
">>UNUSED_290<<",
|
||||
">>UNUSED_291<<",
|
||||
">>UNUSED_292<<",
|
||||
">>UNUSED_293<<",
|
||||
">>UNUSED_294<<",
|
||||
">>UNUSED_295<<",
|
||||
">>UNUSED_296<<",
|
||||
">>UNUSED_297<<",
|
||||
">>UNUSED_298<<",
|
||||
">>UNUSED_299<<",
|
||||
">>UNUSED_300<<",
|
||||
">>UNUSED_301<<",
|
||||
">>UNUSED_302<<",
|
||||
">>UNUSED_303<<",
|
||||
">>UNUSED_304<<",
|
||||
">>UNUSED_305<<",
|
||||
">>UNUSED_306<<",
|
||||
">>UNUSED_307<<",
|
||||
">>UNUSED_308<<",
|
||||
">>UNUSED_309<<",
|
||||
">>UNUSED_310<<",
|
||||
">>UNUSED_311<<",
|
||||
">>UNUSED_312<<",
|
||||
">>UNUSED_313<<",
|
||||
">>UNUSED_314<<",
|
||||
">>UNUSED_315<<",
|
||||
">>UNUSED_316<<",
|
||||
">>UNUSED_317<<",
|
||||
">>UNUSED_318<<",
|
||||
">>UNUSED_319<<",
|
||||
">>UNUSED_320<<",
|
||||
">>UNUSED_321<<",
|
||||
">>UNUSED_322<<",
|
||||
">>UNUSED_323<<",
|
||||
">>UNUSED_324<<",
|
||||
">>UNUSED_325<<",
|
||||
">>UNUSED_326<<",
|
||||
">>UNUSED_327<<",
|
||||
">>UNUSED_328<<",
|
||||
">>UNUSED_329<<",
|
||||
">>UNUSED_330<<",
|
||||
">>UNUSED_331<<",
|
||||
">>UNUSED_332<<",
|
||||
">>UNUSED_333<<",
|
||||
">>UNUSED_334<<",
|
||||
">>UNUSED_335<<",
|
||||
">>UNUSED_336<<",
|
||||
">>UNUSED_337<<",
|
||||
">>UNUSED_338<<",
|
||||
">>UNUSED_339<<",
|
||||
">>UNUSED_340<<",
|
||||
">>UNUSED_341<<",
|
||||
">>UNUSED_342<<",
|
||||
">>UNUSED_343<<",
|
||||
">>UNUSED_344<<",
|
||||
">>UNUSED_345<<",
|
||||
">>UNUSED_346<<",
|
||||
">>UNUSED_347<<",
|
||||
">>UNUSED_348<<",
|
||||
">>UNUSED_349<<",
|
||||
">>UNUSED_350<<",
|
||||
">>UNUSED_351<<",
|
||||
">>UNUSED_352<<",
|
||||
">>UNUSED_353<<",
|
||||
">>UNUSED_354<<",
|
||||
">>UNUSED_355<<",
|
||||
">>UNUSED_356<<",
|
||||
">>UNUSED_357<<",
|
||||
">>UNUSED_358<<",
|
||||
">>UNUSED_359<<",
|
||||
">>UNUSED_360<<",
|
||||
">>UNUSED_361<<",
|
||||
">>UNUSED_362<<",
|
||||
">>UNUSED_363<<",
|
||||
">>UNUSED_364<<",
|
||||
">>UNUSED_365<<",
|
||||
">>UNUSED_366<<",
|
||||
">>UNUSED_367<<",
|
||||
">>UNUSED_368<<",
|
||||
">>UNUSED_369<<",
|
||||
">>UNUSED_370<<",
|
||||
">>UNUSED_371<<",
|
||||
">>UNUSED_372<<",
|
||||
">>UNUSED_373<<",
|
||||
">>UNUSED_374<<",
|
||||
">>UNUSED_375<<",
|
||||
">>UNUSED_376<<",
|
||||
">>UNUSED_377<<",
|
||||
">>UNUSED_378<<",
|
||||
">>UNUSED_379<<",
|
||||
">>UNUSED_380<<",
|
||||
">>UNUSED_381<<",
|
||||
">>UNUSED_382<<",
|
||||
">>UNUSED_383<<",
|
||||
">>UNUSED_384<<",
|
||||
">>UNUSED_385<<",
|
||||
">>UNUSED_386<<",
|
||||
">>UNUSED_387<<",
|
||||
">>UNUSED_388<<",
|
||||
">>UNUSED_389<<",
|
||||
">>UNUSED_390<<",
|
||||
">>UNUSED_391<<",
|
||||
">>UNUSED_392<<",
|
||||
">>UNUSED_393<<",
|
||||
">>UNUSED_394<<",
|
||||
">>UNUSED_395<<",
|
||||
">>UNUSED_396<<",
|
||||
">>UNUSED_397<<",
|
||||
">>UNUSED_398<<",
|
||||
">>UNUSED_399<<",
|
||||
">>UNUSED_400<<",
|
||||
">>UNUSED_401<<",
|
||||
">>UNUSED_402<<",
|
||||
">>UNUSED_403<<",
|
||||
">>UNUSED_404<<",
|
||||
">>UNUSED_405<<",
|
||||
">>UNUSED_406<<",
|
||||
">>UNUSED_407<<",
|
||||
">>UNUSED_408<<",
|
||||
">>UNUSED_409<<",
|
||||
">>UNUSED_410<<",
|
||||
">>UNUSED_411<<",
|
||||
">>UNUSED_412<<",
|
||||
">>UNUSED_413<<",
|
||||
">>UNUSED_414<<",
|
||||
">>UNUSED_415<<",
|
||||
">>UNUSED_416<<",
|
||||
">>UNUSED_417<<",
|
||||
">>UNUSED_418<<",
|
||||
">>UNUSED_419<<",
|
||||
">>UNUSED_420<<",
|
||||
">>UNUSED_421<<",
|
||||
">>UNUSED_422<<",
|
||||
">>UNUSED_423<<",
|
||||
">>UNUSED_424<<",
|
||||
">>UNUSED_425<<",
|
||||
">>UNUSED_426<<",
|
||||
">>UNUSED_427<<",
|
||||
">>UNUSED_428<<",
|
||||
">>UNUSED_429<<",
|
||||
">>UNUSED_430<<",
|
||||
">>UNUSED_431<<",
|
||||
">>UNUSED_432<<",
|
||||
">>UNUSED_433<<",
|
||||
">>UNUSED_434<<",
|
||||
">>UNUSED_435<<",
|
||||
">>UNUSED_436<<",
|
||||
">>UNUSED_437<<",
|
||||
">>UNUSED_438<<",
|
||||
">>UNUSED_439<<",
|
||||
">>UNUSED_440<<",
|
||||
">>UNUSED_441<<",
|
||||
">>UNUSED_442<<",
|
||||
">>UNUSED_443<<",
|
||||
">>UNUSED_444<<",
|
||||
">>UNUSED_445<<",
|
||||
">>UNUSED_446<<",
|
||||
">>UNUSED_447<<",
|
||||
">>UNUSED_448<<",
|
||||
">>UNUSED_449<<",
|
||||
">>UNUSED_450<<",
|
||||
">>UNUSED_451<<",
|
||||
">>UNUSED_452<<",
|
||||
">>UNUSED_453<<",
|
||||
">>UNUSED_454<<",
|
||||
">>UNUSED_455<<",
|
||||
">>UNUSED_456<<",
|
||||
">>UNUSED_457<<",
|
||||
">>UNUSED_458<<",
|
||||
">>UNUSED_459<<",
|
||||
">>UNUSED_460<<",
|
||||
">>UNUSED_461<<",
|
||||
">>UNUSED_462<<",
|
||||
">>UNUSED_463<<",
|
||||
">>UNUSED_464<<",
|
||||
">>UNUSED_465<<",
|
||||
">>UNUSED_466<<",
|
||||
">>UNUSED_467<<",
|
||||
">>UNUSED_468<<",
|
||||
">>UNUSED_469<<",
|
||||
">>UNUSED_470<<",
|
||||
">>UNUSED_471<<",
|
||||
">>UNUSED_472<<",
|
||||
">>UNUSED_473<<",
|
||||
">>UNUSED_474<<",
|
||||
">>UNUSED_475<<",
|
||||
">>UNUSED_476<<",
|
||||
">>UNUSED_477<<",
|
||||
">>UNUSED_478<<",
|
||||
">>UNUSED_479<<",
|
||||
">>UNUSED_480<<",
|
||||
">>UNUSED_481<<",
|
||||
">>UNUSED_482<<",
|
||||
">>UNUSED_483<<",
|
||||
">>UNUSED_484<<",
|
||||
">>UNUSED_485<<",
|
||||
">>UNUSED_486<<",
|
||||
">>UNUSED_487<<",
|
||||
">>UNUSED_488<<",
|
||||
">>UNUSED_489<<",
|
||||
">>UNUSED_490<<",
|
||||
">>UNUSED_491<<",
|
||||
">>UNUSED_492<<",
|
||||
">>UNUSED_493<<",
|
||||
">>UNUSED_494<<",
|
||||
">>UNUSED_495<<",
|
||||
">>UNUSED_496<<",
|
||||
">>UNUSED_497<<",
|
||||
">>UNUSED_498<<",
|
||||
">>UNUSED_499<<",
|
||||
">>UNUSED_500<<",
|
||||
">>UNUSED_501<<",
|
||||
">>UNUSED_502<<",
|
||||
">>UNUSED_503<<",
|
||||
">>UNUSED_504<<",
|
||||
">>UNUSED_505<<",
|
||||
">>UNUSED_506<<",
|
||||
">>UNUSED_507<<",
|
||||
">>UNUSED_508<<",
|
||||
">>UNUSED_509<<",
|
||||
">>UNUSED_510<<",
|
||||
">>UNUSED_511<<",
|
||||
">>UNUSED_512<<",
|
||||
">>UNUSED_513<<",
|
||||
">>UNUSED_514<<",
|
||||
">>UNUSED_515<<",
|
||||
">>UNUSED_516<<",
|
||||
">>UNUSED_517<<",
|
||||
">>UNUSED_518<<",
|
||||
">>UNUSED_519<<",
|
||||
">>UNUSED_520<<",
|
||||
">>UNUSED_521<<",
|
||||
">>UNUSED_522<<",
|
||||
">>UNUSED_523<<",
|
||||
">>UNUSED_524<<",
|
||||
">>UNUSED_525<<",
|
||||
">>UNUSED_526<<",
|
||||
">>UNUSED_527<<",
|
||||
">>UNUSED_528<<",
|
||||
">>UNUSED_529<<",
|
||||
">>UNUSED_530<<",
|
||||
">>UNUSED_531<<",
|
||||
">>UNUSED_532<<",
|
||||
">>UNUSED_533<<",
|
||||
">>UNUSED_534<<",
|
||||
">>UNUSED_535<<",
|
||||
">>UNUSED_536<<",
|
||||
">>UNUSED_537<<",
|
||||
">>UNUSED_538<<",
|
||||
">>UNUSED_539<<",
|
||||
">>UNUSED_540<<",
|
||||
">>UNUSED_541<<",
|
||||
">>UNUSED_542<<",
|
||||
">>UNUSED_543<<",
|
||||
">>UNUSED_544<<",
|
||||
">>UNUSED_545<<",
|
||||
">>UNUSED_546<<",
|
||||
">>UNUSED_547<<",
|
||||
">>UNUSED_548<<",
|
||||
">>UNUSED_549<<",
|
||||
">>UNUSED_550<<",
|
||||
">>UNUSED_551<<",
|
||||
">>UNUSED_552<<",
|
||||
">>UNUSED_553<<",
|
||||
">>UNUSED_554<<",
|
||||
">>UNUSED_555<<",
|
||||
">>UNUSED_556<<",
|
||||
">>UNUSED_557<<",
|
||||
">>UNUSED_558<<",
|
||||
">>UNUSED_559<<",
|
||||
">>UNUSED_560<<",
|
||||
">>UNUSED_561<<",
|
||||
">>UNUSED_562<<",
|
||||
">>UNUSED_563<<",
|
||||
">>UNUSED_564<<",
|
||||
">>UNUSED_565<<",
|
||||
">>UNUSED_566<<",
|
||||
">>UNUSED_567<<",
|
||||
">>UNUSED_568<<",
|
||||
">>UNUSED_569<<",
|
||||
">>UNUSED_570<<",
|
||||
">>UNUSED_571<<",
|
||||
">>UNUSED_572<<",
|
||||
">>UNUSED_573<<",
|
||||
">>UNUSED_574<<",
|
||||
">>UNUSED_575<<",
|
||||
">>UNUSED_576<<",
|
||||
">>UNUSED_577<<",
|
||||
">>UNUSED_578<<",
|
||||
">>UNUSED_579<<",
|
||||
">>UNUSED_580<<",
|
||||
">>UNUSED_581<<",
|
||||
">>UNUSED_582<<",
|
||||
">>UNUSED_583<<",
|
||||
">>UNUSED_584<<",
|
||||
">>UNUSED_585<<",
|
||||
">>UNUSED_586<<",
|
||||
">>UNUSED_587<<",
|
||||
">>UNUSED_588<<",
|
||||
">>UNUSED_589<<",
|
||||
">>UNUSED_590<<",
|
||||
">>UNUSED_591<<",
|
||||
">>UNUSED_592<<",
|
||||
">>UNUSED_593<<",
|
||||
">>UNUSED_594<<",
|
||||
">>UNUSED_595<<",
|
||||
">>UNUSED_596<<",
|
||||
">>UNUSED_597<<",
|
||||
">>UNUSED_598<<",
|
||||
">>UNUSED_599<<",
|
||||
">>UNUSED_600<<",
|
||||
">>UNUSED_601<<",
|
||||
">>UNUSED_602<<",
|
||||
">>UNUSED_603<<",
|
||||
">>UNUSED_604<<",
|
||||
">>UNUSED_605<<",
|
||||
">>UNUSED_606<<",
|
||||
">>UNUSED_607<<",
|
||||
">>UNUSED_608<<",
|
||||
">>UNUSED_609<<",
|
||||
">>UNUSED_610<<",
|
||||
">>UNUSED_611<<",
|
||||
">>UNUSED_612<<",
|
||||
">>UNUSED_613<<",
|
||||
">>UNUSED_614<<",
|
||||
">>UNUSED_615<<",
|
||||
">>UNUSED_616<<",
|
||||
">>UNUSED_617<<",
|
||||
">>UNUSED_618<<",
|
||||
">>UNUSED_619<<",
|
||||
">>UNUSED_620<<",
|
||||
">>UNUSED_621<<",
|
||||
">>UNUSED_622<<",
|
||||
">>UNUSED_623<<",
|
||||
">>UNUSED_624<<",
|
||||
">>UNUSED_625<<",
|
||||
">>UNUSED_626<<",
|
||||
">>UNUSED_627<<",
|
||||
">>UNUSED_628<<",
|
||||
">>UNUSED_629<<",
|
||||
">>UNUSED_630<<",
|
||||
">>UNUSED_631<<",
|
||||
">>UNUSED_632<<",
|
||||
">>UNUSED_633<<",
|
||||
">>UNUSED_634<<",
|
||||
">>UNUSED_635<<",
|
||||
">>UNUSED_636<<",
|
||||
">>UNUSED_637<<",
|
||||
">>UNUSED_638<<",
|
||||
">>UNUSED_639<<",
|
||||
">>UNUSED_640<<",
|
||||
">>UNUSED_641<<",
|
||||
">>UNUSED_642<<",
|
||||
">>UNUSED_643<<",
|
||||
">>UNUSED_644<<",
|
||||
">>UNUSED_645<<",
|
||||
">>UNUSED_646<<",
|
||||
">>UNUSED_647<<",
|
||||
">>UNUSED_648<<",
|
||||
">>UNUSED_649<<",
|
||||
">>UNUSED_650<<",
|
||||
">>UNUSED_651<<",
|
||||
">>UNUSED_652<<",
|
||||
">>UNUSED_653<<",
|
||||
">>UNUSED_654<<",
|
||||
">>UNUSED_655<<",
|
||||
">>UNUSED_656<<",
|
||||
">>UNUSED_657<<",
|
||||
">>UNUSED_658<<",
|
||||
">>UNUSED_659<<",
|
||||
">>UNUSED_660<<",
|
||||
">>UNUSED_661<<",
|
||||
">>UNUSED_662<<",
|
||||
">>UNUSED_663<<",
|
||||
">>UNUSED_664<<",
|
||||
">>UNUSED_665<<",
|
||||
">>UNUSED_666<<",
|
||||
">>UNUSED_667<<",
|
||||
">>UNUSED_668<<",
|
||||
">>UNUSED_669<<",
|
||||
">>UNUSED_670<<",
|
||||
">>UNUSED_671<<",
|
||||
">>UNUSED_672<<",
|
||||
">>UNUSED_673<<",
|
||||
">>UNUSED_674<<",
|
||||
">>UNUSED_675<<",
|
||||
">>UNUSED_676<<",
|
||||
">>UNUSED_677<<",
|
||||
">>UNUSED_678<<",
|
||||
">>UNUSED_679<<",
|
||||
">>UNUSED_680<<",
|
||||
">>UNUSED_681<<",
|
||||
">>UNUSED_682<<",
|
||||
">>UNUSED_683<<",
|
||||
">>UNUSED_684<<",
|
||||
">>UNUSED_685<<",
|
||||
">>UNUSED_686<<",
|
||||
">>UNUSED_687<<",
|
||||
">>UNUSED_688<<",
|
||||
">>UNUSED_689<<",
|
||||
">>UNUSED_690<<",
|
||||
">>UNUSED_691<<",
|
||||
">>UNUSED_692<<",
|
||||
">>UNUSED_693<<",
|
||||
">>UNUSED_694<<",
|
||||
">>UNUSED_695<<",
|
||||
">>UNUSED_696<<",
|
||||
">>UNUSED_697<<",
|
||||
">>UNUSED_698<<",
|
||||
">>UNUSED_699<<",
|
||||
">>UNUSED_700<<",
|
||||
">>UNUSED_701<<",
|
||||
">>UNUSED_702<<",
|
||||
">>UNUSED_703<<",
|
||||
">>UNUSED_704<<",
|
||||
">>UNUSED_705<<",
|
||||
">>UNUSED_706<<",
|
||||
">>UNUSED_707<<",
|
||||
">>UNUSED_708<<",
|
||||
">>UNUSED_709<<",
|
||||
">>UNUSED_710<<",
|
||||
">>UNUSED_711<<",
|
||||
">>UNUSED_712<<",
|
||||
">>UNUSED_713<<",
|
||||
">>UNUSED_714<<",
|
||||
">>UNUSED_715<<",
|
||||
">>UNUSED_716<<",
|
||||
">>UNUSED_717<<",
|
||||
">>UNUSED_718<<",
|
||||
">>UNUSED_719<<",
|
||||
">>UNUSED_720<<",
|
||||
">>UNUSED_721<<",
|
||||
">>UNUSED_722<<",
|
||||
">>UNUSED_723<<",
|
||||
">>UNUSED_724<<",
|
||||
">>UNUSED_725<<",
|
||||
">>UNUSED_726<<",
|
||||
">>UNUSED_727<<",
|
||||
">>UNUSED_728<<",
|
||||
">>UNUSED_729<<",
|
||||
">>UNUSED_730<<",
|
||||
">>UNUSED_731<<",
|
||||
">>UNUSED_732<<",
|
||||
">>UNUSED_733<<",
|
||||
">>UNUSED_734<<",
|
||||
">>UNUSED_735<<",
|
||||
">>UNUSED_736<<",
|
||||
">>UNUSED_737<<",
|
||||
">>UNUSED_738<<",
|
||||
">>UNUSED_739<<",
|
||||
">>UNUSED_740<<",
|
||||
">>UNUSED_741<<",
|
||||
">>UNUSED_742<<",
|
||||
">>UNUSED_743<<",
|
||||
">>UNUSED_744<<",
|
||||
">>UNUSED_745<<",
|
||||
">>UNUSED_746<<",
|
||||
">>UNUSED_747<<",
|
||||
">>UNUSED_748<<",
|
||||
">>UNUSED_749<<",
|
||||
">>UNUSED_750<<",
|
||||
">>UNUSED_751<<",
|
||||
">>UNUSED_752<<",
|
||||
">>UNUSED_753<<",
|
||||
">>UNUSED_754<<",
|
||||
">>UNUSED_755<<",
|
||||
">>UNUSED_756<<",
|
||||
">>UNUSED_757<<",
|
||||
">>UNUSED_758<<",
|
||||
">>UNUSED_759<<",
|
||||
">>UNUSED_760<<",
|
||||
">>UNUSED_761<<",
|
||||
">>UNUSED_762<<",
|
||||
">>UNUSED_763<<",
|
||||
">>UNUSED_764<<",
|
||||
">>UNUSED_765<<",
|
||||
">>UNUSED_766<<",
|
||||
">>UNUSED_767<<",
|
||||
">>UNUSED_768<<",
|
||||
">>UNUSED_769<<",
|
||||
">>UNUSED_770<<",
|
||||
">>UNUSED_771<<",
|
||||
">>UNUSED_772<<",
|
||||
">>UNUSED_773<<",
|
||||
">>UNUSED_774<<",
|
||||
">>UNUSED_775<<",
|
||||
">>UNUSED_776<<",
|
||||
">>UNUSED_777<<",
|
||||
">>UNUSED_778<<",
|
||||
">>UNUSED_779<<",
|
||||
">>UNUSED_780<<",
|
||||
">>UNUSED_781<<",
|
||||
">>UNUSED_782<<",
|
||||
">>UNUSED_783<<",
|
||||
">>UNUSED_784<<",
|
||||
">>UNUSED_785<<",
|
||||
">>UNUSED_786<<",
|
||||
">>UNUSED_787<<",
|
||||
">>UNUSED_788<<",
|
||||
">>UNUSED_789<<",
|
||||
">>UNUSED_790<<",
|
||||
">>UNUSED_791<<",
|
||||
">>UNUSED_792<<",
|
||||
">>UNUSED_793<<",
|
||||
">>UNUSED_794<<",
|
||||
">>UNUSED_795<<",
|
||||
">>UNUSED_796<<",
|
||||
">>UNUSED_797<<",
|
||||
">>UNUSED_798<<",
|
||||
">>UNUSED_799<<",
|
||||
">>UNUSED_800<<",
|
||||
">>UNUSED_801<<",
|
||||
">>UNUSED_802<<",
|
||||
">>UNUSED_803<<",
|
||||
">>UNUSED_804<<",
|
||||
">>UNUSED_805<<",
|
||||
">>UNUSED_806<<",
|
||||
">>UNUSED_807<<",
|
||||
">>UNUSED_808<<",
|
||||
">>UNUSED_809<<",
|
||||
">>UNUSED_810<<",
|
||||
">>UNUSED_811<<",
|
||||
">>UNUSED_812<<",
|
||||
">>UNUSED_813<<",
|
||||
">>UNUSED_814<<",
|
||||
">>UNUSED_815<<",
|
||||
">>UNUSED_816<<",
|
||||
">>UNUSED_817<<",
|
||||
">>UNUSED_818<<",
|
||||
">>UNUSED_819<<",
|
||||
">>UNUSED_820<<",
|
||||
">>UNUSED_821<<",
|
||||
">>UNUSED_822<<",
|
||||
">>UNUSED_823<<",
|
||||
">>UNUSED_824<<",
|
||||
">>UNUSED_825<<",
|
||||
">>UNUSED_826<<",
|
||||
">>UNUSED_827<<",
|
||||
">>UNUSED_828<<",
|
||||
">>UNUSED_829<<",
|
||||
">>UNUSED_830<<",
|
||||
">>UNUSED_831<<",
|
||||
">>UNUSED_832<<",
|
||||
">>UNUSED_833<<",
|
||||
">>UNUSED_834<<",
|
||||
">>UNUSED_835<<",
|
||||
">>UNUSED_836<<",
|
||||
">>UNUSED_837<<",
|
||||
">>UNUSED_838<<",
|
||||
">>UNUSED_839<<",
|
||||
">>UNUSED_840<<",
|
||||
">>UNUSED_841<<",
|
||||
">>UNUSED_842<<",
|
||||
">>UNUSED_843<<",
|
||||
">>UNUSED_844<<",
|
||||
">>UNUSED_845<<",
|
||||
">>UNUSED_846<<",
|
||||
">>UNUSED_847<<",
|
||||
">>UNUSED_848<<",
|
||||
">>UNUSED_849<<",
|
||||
">>UNUSED_850<<",
|
||||
">>UNUSED_851<<",
|
||||
">>UNUSED_852<<",
|
||||
">>UNUSED_853<<",
|
||||
">>UNUSED_854<<",
|
||||
">>UNUSED_855<<",
|
||||
">>UNUSED_856<<",
|
||||
">>UNUSED_857<<",
|
||||
">>UNUSED_858<<",
|
||||
">>UNUSED_859<<",
|
||||
">>UNUSED_860<<",
|
||||
">>UNUSED_861<<",
|
||||
">>UNUSED_862<<",
|
||||
">>UNUSED_863<<",
|
||||
">>UNUSED_864<<",
|
||||
">>UNUSED_865<<",
|
||||
">>UNUSED_866<<",
|
||||
">>UNUSED_867<<",
|
||||
">>UNUSED_868<<",
|
||||
">>UNUSED_869<<",
|
||||
">>UNUSED_870<<",
|
||||
">>UNUSED_871<<",
|
||||
">>UNUSED_872<<",
|
||||
">>UNUSED_873<<",
|
||||
">>UNUSED_874<<",
|
||||
">>UNUSED_875<<",
|
||||
">>UNUSED_876<<",
|
||||
">>UNUSED_877<<",
|
||||
">>UNUSED_878<<",
|
||||
">>UNUSED_879<<",
|
||||
">>UNUSED_880<<",
|
||||
">>UNUSED_881<<",
|
||||
">>UNUSED_882<<",
|
||||
">>UNUSED_883<<",
|
||||
">>UNUSED_884<<",
|
||||
">>UNUSED_885<<",
|
||||
">>UNUSED_886<<",
|
||||
">>UNUSED_887<<",
|
||||
">>UNUSED_888<<",
|
||||
">>UNUSED_889<<",
|
||||
">>UNUSED_890<<",
|
||||
">>UNUSED_891<<",
|
||||
">>UNUSED_892<<",
|
||||
">>UNUSED_893<<",
|
||||
">>UNUSED_894<<",
|
||||
">>UNUSED_895<<",
|
||||
">>UNUSED_896<<",
|
||||
">>UNUSED_897<<",
|
||||
">>UNUSED_898<<",
|
||||
">>UNUSED_899<<",
|
||||
">>UNUSED_900<<",
|
||||
">>UNUSED_901<<",
|
||||
">>UNUSED_902<<",
|
||||
">>UNUSED_903<<",
|
||||
">>UNUSED_904<<",
|
||||
">>UNUSED_905<<",
|
||||
">>UNUSED_906<<",
|
||||
">>UNUSED_907<<",
|
||||
">>UNUSED_908<<",
|
||||
">>UNUSED_909<<",
|
||||
">>UNUSED_910<<",
|
||||
">>UNUSED_911<<",
|
||||
">>UNUSED_912<<",
|
||||
">>UNUSED_913<<",
|
||||
">>UNUSED_914<<",
|
||||
">>UNUSED_915<<",
|
||||
">>UNUSED_916<<",
|
||||
">>UNUSED_917<<",
|
||||
">>UNUSED_918<<",
|
||||
">>UNUSED_919<<",
|
||||
">>UNUSED_920<<",
|
||||
">>UNUSED_921<<",
|
||||
">>UNUSED_922<<",
|
||||
">>UNUSED_923<<",
|
||||
">>UNUSED_924<<",
|
||||
">>UNUSED_925<<",
|
||||
">>UNUSED_926<<",
|
||||
">>UNUSED_927<<",
|
||||
">>UNUSED_928<<",
|
||||
">>UNUSED_929<<",
|
||||
">>UNUSED_930<<",
|
||||
">>UNUSED_931<<",
|
||||
">>UNUSED_932<<",
|
||||
">>UNUSED_933<<",
|
||||
">>UNUSED_934<<",
|
||||
">>UNUSED_935<<",
|
||||
">>UNUSED_936<<",
|
||||
">>UNUSED_937<<",
|
||||
">>UNUSED_938<<",
|
||||
">>UNUSED_939<<",
|
||||
">>UNUSED_940<<",
|
||||
">>UNUSED_941<<",
|
||||
">>UNUSED_942<<",
|
||||
">>UNUSED_943<<",
|
||||
">>UNUSED_944<<",
|
||||
">>UNUSED_945<<",
|
||||
">>UNUSED_946<<",
|
||||
">>UNUSED_947<<",
|
||||
">>UNUSED_948<<",
|
||||
">>UNUSED_949<<",
|
||||
">>UNUSED_950<<",
|
||||
">>UNUSED_951<<",
|
||||
">>UNUSED_952<<",
|
||||
">>UNUSED_953<<",
|
||||
">>UNUSED_954<<",
|
||||
">>UNUSED_955<<",
|
||||
">>UNUSED_956<<",
|
||||
">>UNUSED_957<<",
|
||||
">>UNUSED_958<<",
|
||||
">>UNUSED_959<<",
|
||||
">>UNUSED_960<<",
|
||||
">>UNUSED_961<<",
|
||||
">>UNUSED_962<<",
|
||||
">>UNUSED_963<<",
|
||||
">>UNUSED_964<<",
|
||||
">>UNUSED_965<<",
|
||||
">>UNUSED_966<<",
|
||||
">>UNUSED_967<<",
|
||||
">>UNUSED_968<<",
|
||||
">>UNUSED_969<<",
|
||||
">>UNUSED_970<<",
|
||||
">>UNUSED_971<<",
|
||||
">>UNUSED_972<<",
|
||||
">>UNUSED_973<<",
|
||||
">>UNUSED_974<<",
|
||||
">>UNUSED_975<<",
|
||||
">>UNUSED_976<<",
|
||||
">>UNUSED_977<<",
|
||||
">>UNUSED_978<<",
|
||||
">>UNUSED_979<<",
|
||||
">>UNUSED_980<<",
|
||||
">>UNUSED_981<<",
|
||||
">>UNUSED_982<<",
|
||||
">>UNUSED_983<<",
|
||||
">>UNUSED_984<<",
|
||||
">>UNUSED_985<<",
|
||||
">>UNUSED_986<<",
|
||||
">>UNUSED_987<<",
|
||||
">>UNUSED_988<<",
|
||||
">>UNUSED_989<<",
|
||||
">>UNUSED_990<<",
|
||||
">>UNUSED_991<<",
|
||||
">>UNUSED_992<<",
|
||||
">>UNUSED_993<<",
|
||||
">>UNUSED_994<<",
|
||||
">>UNUSED_995<<",
|
||||
">>UNUSED_996<<",
|
||||
">>UNUSED_997<<",
|
||||
">>UNUSED_998<<",
|
||||
">>UNUSED_999<<",
|
||||
">>UNUSED_1000<<",
|
||||
">>UNUSED_1001<<",
|
||||
">>UNUSED_1002<<",
|
||||
">>UNUSED_1003<<",
|
||||
">>UNUSED_1004<<",
|
||||
">>UNUSED_1005<<",
|
||||
">>UNUSED_1006<<",
|
||||
">>UNUSED_1007<<",
|
||||
">>UNUSED_1008<<",
|
||||
">>UNUSED_1009<<",
|
||||
">>UNUSED_1010<<",
|
||||
">>UNUSED_1011<<",
|
||||
">>UNUSED_1012<<",
|
||||
">>UNUSED_1013<<",
|
||||
">>UNUSED_1014<<",
|
||||
">>UNUSED_1015<<",
|
||||
">>UNUSED_1016<<",
|
||||
">>UNUSED_1017<<",
|
||||
">>UNUSED_1018<<",
|
||||
">>UNUSED_1019<<",
|
||||
">>UNUSED_1020<<",
|
||||
">>UNUSED_1021<<",
|
||||
">>UNUSED_1022<<",
|
||||
">>UNUSED_1023<<"
|
||||
],
|
||||
"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": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a1a906251e685c2ff1fbb0ab2e36d9d1b276e6283a7a9a3e721c5b1923c017c0
|
||||
size 10534300
|
||||
9140
tokenizer_config.json
Normal file
9140
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user