初始化项目，由ModelHub XC社区提供模型
Model: deepseek-ai/DeepSeek-Prover-V2-7B Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.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
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-000002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-000002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
21
LICENSE
Normal file
21
LICENSE
Normal file
@@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2023 DeepSeek
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
170
README.md
Normal file
170
README.md
Normal file
@@ -0,0 +1,170 @@
|
||||
<!-- markdownlint-disable first-line-h1 -->
|
||||
<!-- markdownlint-disable html -->
|
||||
<!-- markdownlint-disable no-duplicate-header -->
|
||||
|
||||
<div align="center">
|
||||
<img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
|
||||
</div>
|
||||
<hr>
|
||||
<div align="center" style="line-height: 1;">
|
||||
<a href="https://www.deepseek.com/" target="_blank" style="margin: 2px;">
|
||||
<img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
<a href="https://chat.deepseek.com/" target="_blank" style="margin: 2px;">
|
||||
<img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20V3-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
<a href="https://huggingface.co/deepseek-ai" target="_blank" style="margin: 2px;">
|
||||
<img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
<div align="center" style="line-height: 1;">
|
||||
<a href="https://discord.gg/Tc7c45Zzu5" target="_blank" style="margin: 2px;">
|
||||
<img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
<a href="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/qr.jpeg?raw=true" target="_blank" style="margin: 2px;">
|
||||
<img alt="Wechat" src="https://img.shields.io/badge/WeChat-DeepSeek%20AI-brightgreen?logo=wechat&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
<a href="https://twitter.com/deepseek_ai" target="_blank" style="margin: 2px;">
|
||||
<img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
<div align="center" style="line-height: 1;">
|
||||
<a href="https://github.com/deepseek-ai/DeepSeek-V3/blob/main/LICENSE-CODE" style="margin: 2px;">
|
||||
<img alt="Code License" src="https://img.shields.io/badge/Code_License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
<a href="https://github.com/deepseek-ai/DeepSeek-V3/blob/main/LICENSE-MODEL" style="margin: 2px;">
|
||||
<img alt="Model License" src="https://img.shields.io/badge/Model_License-Model_Agreement-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
## 1. Introduction
|
||||
|
||||
We introduce DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4, with initialization data collected through a recursive theorem proving pipeline powered by DeepSeek-V3. The cold-start training procedure begins by prompting DeepSeek-V3 to decompose complex problems into a series of subgoals. The proofs of resolved subgoals are synthesized into a chain-of-thought process, combined with DeepSeek-V3's step-by-step reasoning, to create an initial cold start for reinforcement learning. This process enables us to integrate both informal and formal mathematical reasoning into a unified model.
|
||||
|
||||
<p align="center">
|
||||
<img width="100%" src="https://github.com/deepseek-ai/DeepSeek-Prover-V2/blob/main/figures/performance.png?raw=true">
|
||||
</p>
|
||||
|
||||
## 2. Model Summary
|
||||
|
||||
---
|
||||
|
||||
**Synthesize Cold-Start Reasoning Data through Recursive Proof Search**
|
||||
|
||||
- To construct the cold-start dataset, we develop a simple yet effective pipeline for recursive theorem proving, utilizing DeepSeek-V3 as a unified tool for both subgoal decomposition and formalization. We prompt DeepSeek-V3 to decompose theorems into high-level proof sketches while simultaneously formalizing these proof steps in Lean 4, resulting in a sequence of subgoals.
|
||||
|
||||
- We use a smaller 7B model to handle the proof search for each subgoal, thereby reducing the associated computational burden. Once the decomposed steps of a challenging problem are resolved, we pair the complete step-by-step formal proof with the corresponding chain-of-thought from DeepSeek-V3 to create cold-start reasoning data.
|
||||
|
||||
---
|
||||
|
||||
**Reinforcement Learning with Synthetic Cold-Start Data**
|
||||
|
||||
- We curate a subset of challenging problems that remain unsolved by the 7B prover model in an end-to-end manner, but for which all decomposed subgoals have been successfully resolved. By composing the proofs of all subgoals, we construct a complete formal proof for the original problem. This proof is then appended to DeepSeek-V3's chain-of-thought, which outlines the corresponding lemma decomposition, thereby producing a cohesive synthesis of informal reasoning and subsequent formalization.
|
||||
|
||||
- After fine-tuning the prover model on the synthetic cold-start data, we perform a reinforcement learning stage to further enhance its ability to bridge informal reasoning with formal proof construction. Following the standard training objective for reasoning models, we use binary correct-or-incorrect feedback as the primary form of reward supervision.
|
||||
- The resulting model, DeepSeek-Prover-V2-671B, achieves state-of-the-art performance in neural theorem proving, reaching $88.9$% pass ratio on the MiniF2F-test and solving 49 out of 658 problems from PutnamBench. The proofs generated by DeepSeek-Prover-V2 for the miniF2F dataset are available for download as a [ZIP archive](https://github.com/deepseek-ai/DeepSeek-Prover-V2/blob/master/minif2f-solutions.zip).
|
||||
|
||||
---
|
||||
|
||||
## 3. ProverBench: Formalization of AIME and Textbook Problems
|
||||
|
||||
we introduce ProverBench, a benchmark dataset comprising 325 problems. Of these, 15 are formalized from number theory and algebra questions featured in the recent AIME competitions (AIME 24 and 25), offering authentic high-school competition-level challenges. The remaining 310 problems are drawn from curated textbook examples and educational tutorials, contributing a diverse and pedagogically grounded collection of formalized mathematical problems. This benchmark is designed to enable more comprehensive evaluation across both high-school competition problems and undergraduate-level mathematics.
|
||||
|
||||
<div align="center">
|
||||
|
||||
| Area | Count |
|
||||
| :---------------------: | :-------: |
|
||||
| AIME 24&25 | 15 |
|
||||
| Number Theory | 40 |
|
||||
| Elementary Algebra | 30 |
|
||||
| Linear Algebra | 50 |
|
||||
| Abstract Algebra | 40 |
|
||||
| Calculus | 90 |
|
||||
| Real Analysis | 30 |
|
||||
| Complex Analysis | 10 |
|
||||
| Functional Analysis | 10 |
|
||||
| Probability | 10 |
|
||||
| Total | 325 |
|
||||
|
||||
</div>
|
||||
|
||||
## 4. Model & Dataset Downloads
|
||||
|
||||
We release DeepSeek-Prover-V2 in two model sizes: 7B and 671B parameters. DeepSeek-Prover-V2-671B is trained on top of DeepSeek-V3-Base. DeepSeek-Prover-V2-7B is built upon DeepSeek-Prover-V1.5-Base and features an extended context length of up to 32K tokens.
|
||||
|
||||
<div align="center">
|
||||
|
||||
| **Model** | **Download** |
|
||||
| :-----------------------------: | :----------------------------------------------------------: |
|
||||
| DeepSeek-Prover-V2-7B | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-7B) |
|
||||
| DeepSeek-Prover-V2-671B | [🤗 HuggingFace](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-671B) |
|
||||
|
||||
</div>
|
||||
|
||||
<div align="center">
|
||||
|
||||
| **Dataset** | **Download** |
|
||||
| :-----------------------------: | :----------------------------------------------------------: |
|
||||
| DeepSeek-ProverBench | [🤗 HuggingFace](https://huggingface.co/datasets/deepseek-ai/DeepSeek-ProverBench) |
|
||||
|
||||
</div>
|
||||
|
||||
## 5. Quick Start
|
||||
|
||||
You can directly use [Huggingface's Transformers](https://github.com/huggingface/transformers) for model inference. DeepSeek-Prover-V2-671B shares the same architecture as DeepSeek-V3. For detailed information and supported features, please refer to [the DeepSeek-V3 documentation on Hugging Face](https://github.com/huggingface/transformers/blob/main/docs/source/en/model_doc/deepseek_v3.md).
|
||||
|
||||
The following is a basic example of generating a proof for a problem from the miniF2F dataset:
|
||||
````python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
import torch
|
||||
torch.manual_seed(30)
|
||||
|
||||
model_id = "DeepSeek-Prover-V2-7B" # or DeepSeek-Prover-V2-671B
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
|
||||
formal_statement = """
|
||||
import Mathlib
|
||||
import Aesop
|
||||
|
||||
set_option maxHeartbeats 0
|
||||
|
||||
open BigOperators Real Nat Topology Rat
|
||||
|
||||
/-- What is the positive difference between $120\%$ of 30 and $130\%$ of 20? Show that it is 10.-/
|
||||
theorem mathd_algebra_10 : abs ((120 : ℝ) / 100 * 30 - 130 / 100 * 20) = 10 := by
|
||||
sorry
|
||||
""".strip()
|
||||
|
||||
prompt = """
|
||||
Complete the following Lean 4 code:
|
||||
|
||||
```lean4
|
||||
{}
|
||||
```
|
||||
|
||||
Before producing the Lean 4 code to formally prove the given theorem, provide a detailed proof plan outlining the main proof steps and strategies.
|
||||
The plan should highlight key ideas, intermediate lemmas, and proof structures that will guide the construction of the final formal proof.
|
||||
""".strip()
|
||||
|
||||
chat = [
|
||||
{"role": "user", "content": prompt.format(formal_statement)},
|
||||
]
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
|
||||
inputs = tokenizer.apply_chat_template(chat, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
|
||||
|
||||
import time
|
||||
start = time.time()
|
||||
outputs = model.generate(inputs, max_new_tokens=8192)
|
||||
print(tokenizer.batch_decode(outputs))
|
||||
print(time.time() - start)
|
||||
````
|
||||
|
||||
## 6. License
|
||||
The use of DeepSeek-Prover-V2 models is subject to [the Model License](LICENSE-MODEL).
|
||||
|
||||
## 7. Contact
|
||||
|
||||
If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com).
|
||||
36
config.json
Normal file
36
config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 100000,
|
||||
"eos_token_id": 100001,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 65536,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 30,
|
||||
"num_key_value_heads": 32,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"beta_fast": 32,
|
||||
"beta_slow": 1,
|
||||
"factor": 16,
|
||||
"mscale": true,
|
||||
"original_max_position_embeddings": 4096,
|
||||
"type": "yarn"
|
||||
},
|
||||
"rope_theta": 10000,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.46.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 102400
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
3
model-00001-of-000002.safetensors
Normal file
3
model-00001-of-000002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f7eebe5f578ccfa90eea70b00c164adff6df2bdec511b9939c101234c3e3ae65
|
||||
size 8596557586
|
||||
3
model-00002-of-000002.safetensors
Normal file
3
model-00002-of-000002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7dd518c7ca44e82a7bda20f1959bd131b89f721c70fb3bc2e9ac0b53ad2c4ce9
|
||||
size 5224205544
|
||||
280
model.safetensors.index.json
Normal file
280
model.safetensors.index.json
Normal file
@@ -0,0 +1,280 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13820731392
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-000002.safetensors",
|
||||
"lm_head.weight": "model-00002-of-000002.safetensors"
|
||||
}
|
||||
}
|
||||
200009
tokenizer.json
Normal file
200009
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
35
tokenizer_config.json
Normal file
35
tokenizer_config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": true,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"sp_model_kwargs": {},
|
||||
"unk_token": null,
|
||||
"tokenizer_class": "LlamaTokenizerFast",
|
||||
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + message['content'] + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{message['content'] + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}"
|
||||
}
|
||||
Reference in New Issue
Block a user