Commit
f00d26a
·
0 Parent(s):

Duplicate from MI-Materials-Intelligence/Recipe-Language-Model

Browse files

Co-authored-by: MI-Materials-Intelligence <MI-Materials-Intelligence@users.noreply.huggingface.co>

Files changed (44) hide show
  1. .gitattributes +37 -0
  2. Modelfile +14 -0
  3. README.md +112 -0
  4. added_tokens.json +28 -0
  5. chat_template.jinja +86 -0
  6. config.json +38 -0
  7. generation_config.json +13 -0
  8. merges.txt +0 -0
  9. model-00001-of-00031.safetensors +3 -0
  10. model-00002-of-00031.safetensors +3 -0
  11. model-00003-of-00031.safetensors +3 -0
  12. model-00004-of-00031.safetensors +3 -0
  13. model-00005-of-00031.safetensors +3 -0
  14. model-00006-of-00031.safetensors +3 -0
  15. model-00007-of-00031.safetensors +3 -0
  16. model-00008-of-00031.safetensors +3 -0
  17. model-00009-of-00031.safetensors +3 -0
  18. model-00010-of-00031.safetensors +3 -0
  19. model-00011-of-00031.safetensors +3 -0
  20. model-00012-of-00031.safetensors +3 -0
  21. model-00013-of-00031.safetensors +3 -0
  22. model-00014-of-00031.safetensors +3 -0
  23. model-00015-of-00031.safetensors +3 -0
  24. model-00016-of-00031.safetensors +3 -0
  25. model-00017-of-00031.safetensors +3 -0
  26. model-00018-of-00031.safetensors +3 -0
  27. model-00019-of-00031.safetensors +3 -0
  28. model-00020-of-00031.safetensors +3 -0
  29. model-00021-of-00031.safetensors +3 -0
  30. model-00022-of-00031.safetensors +3 -0
  31. model-00023-of-00031.safetensors +3 -0
  32. model-00024-of-00031.safetensors +3 -0
  33. model-00025-of-00031.safetensors +3 -0
  34. model-00026-of-00031.safetensors +3 -0
  35. model-00027-of-00031.safetensors +3 -0
  36. model-00028-of-00031.safetensors +3 -0
  37. model-00029-of-00031.safetensors +3 -0
  38. model-00030-of-00031.safetensors +3 -0
  39. model-00031-of-00031.safetensors +3 -0
  40. model.safetensors.index.json +0 -0
  41. special_tokens_map.json +31 -0
  42. tokenizer.json +3 -0
  43. tokenizer_config.json +240 -0
  44. vocab.json +0 -0
.gitattributes ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ qwen3_32b_v6-9/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Modelfile ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # ollama modelfile auto-generated by llamafactory
2
+
3
+ FROM .
4
+
5
+ TEMPLATE """{{ if .System }}<|im_start|>system
6
+ {{ .System }}<|im_end|>
7
+ {{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
8
+ {{ .Content }}<|im_end|>
9
+ <|im_start|>assistant
10
+ {{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
11
+ {{ end }}{{ end }}"""
12
+
13
+ PARAMETER stop "<|im_end|>"
14
+ PARAMETER num_ctx 4096
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Recipe Language Model (RLM)
2
+
3
+ ## 1. Overview
4
+
5
+ We introduce a domain-specific RLM developed through seven AI layers and interconnected robotic boxes to drive the evolution of physical AI for defining a new paradigm - Materials Intelligence.
6
+
7
+ ---
8
+
9
+ ## 2. Introduction
10
+
11
+ Materials innovation have been undergoing rapid development with the vast combinatorial exploration of recipes; however, the related research suffers from time-consuming trial-and-error synthesis and labour-intensive fabrication. As a promising alternative, robotics enables high-throughput experimentation and data collection; however, the resulting numerical datasets are often insufficiently analysed and fail to provide effective feedback for semantic recipe optimisation.
12
+
13
+ Here, we present a domain-specific RLM developed for an emerging scientific tool of robotic boxes (perovskite solar cell research as a demonstration). For iterative fine-tuning of the RLM, seven AI layers, including learning, generating, RecipeQA, fine-tuning, reasoning, evaluation, and optimisation, have been designed with a language agent. During the loops of seven AI layers, both numerical and semantic recipes were continuously learned and optimised for the RLM. Guided by this RLM, eleven robotic boxes executed the controllable synthesis, fabrication and characterisation of 50,764 samples. Simultaneously, more than 578 million tokens were generated and augmented to improve the ability to recommend a recipe and mechanistic reasoning, reaching a level comparable to that of an experienced researcher.
14
+
15
+ Therefore, the integration of the RLM with robotic boxes enables an AI and robotics discovery process in which specialised language modelling and modularised robotic hardware continuously improve one another, suggesting an evolution of physical AI for the Materials Intelligence.
16
+
17
+ ---
18
+
19
+ ## 3. Model Description
20
+
21
+ To train this domain-specific RLM, the workflow starts from encoded formulas and parameters as recipe inputs, proceeds through seven AI layers with the language agent, and produces in situ characterisation and device performance assessment as mechanistic outputs. The language agent encodes these machine-readable recipes into structured formulas and parameters sequences, which are translated into tokens for subsequent fine-tuning of the RLM and execution by the robotic boxes. As a result, the fine-tuned RLM incorporates the encoded recipes, robotics, and characterised results to form a closed recommendation–synthesis–fabrication–characterisation–mechanism loop for exploring the large space of the recipes and their underlying mechanisms.
22
+
23
+ ---
24
+
25
+ ## 4. Key Features
26
+
27
+ Acceleration of Materials Intelligence (MI): Simultaneously optimizes recipe recommendation (technical accuracy) and mechanistic reasoning (scientific understanding) for accelerating the discovery of MI recipes.
28
+
29
+ Evolution of Physical AI (PAI): Creates a synergy where the RLM enhances the robotic controllable fabrication, while the robotic outcomes continuously refine the RLM’s recipe and mechanism to drive the evolution of PAI.
30
+
31
+ ---
32
+
33
+ ## 5. Training Details
34
+
35
+ Seven AI layers Architecture has been designed for this RLM Training.
36
+
37
+
38
+ ### Learning
39
+
40
+ In the learning layer, the formulas and parameters are encoded and then tokenised into recipes as inputs.
41
+ Through atomic skills of data extraction, cleaning, and matching, these data are organised into standardised datasets, providing the basis for RLM training and iterative recipe refinement.
42
+
43
+ ---
44
+
45
+ ### Generating
46
+
47
+ In the generating layer, the tokenised recipes are comprised into the recipe report with fabrication details, mechanistic descriptions, an optimisation summary, and supporting information.
48
+ Through atomic skills of edge reporting (generation from single experimental data), single-variable reporting (generation from matched data with single variable), and characterization reporting (generation from matched data with in situ characterization), these processed data are converted into robotic recipe reports.
49
+
50
+ ---
51
+
52
+ ### RecipeQA
53
+
54
+ In the RecipeQA layer, the recipe reports are further converted into semantically structured question–answer pairs (RecipeQA).
55
+ The primary objective of this layer is to construct high-quality, domain-specific training corpora through key atomic skills of Report to QA (convert recipe reports into semantically structured RecipeQA) and Distillation (knowledge distillation for RecipeQA).
56
+
57
+ ---
58
+
59
+ ### Fine-tuning
60
+
61
+ In the fine-tuning layer, the base model (Qwen3-32B) together with the RecipeQA corpora are taken as the input of this layer.
62
+ Through low-rank adaptation (LoRA), the model is efficiently adapted to domain-specific recipe knowledge and transformed into a domain-specific RLM as output.
63
+
64
+ ---
65
+
66
+ ### Reasoning
67
+
68
+ In the reasoning layer, the fine-tuned domain-specific RLM to generate mechanistic interpretations, performance explanations, and recipe optimization suggestions from experimental records.
69
+ These reasoning results serve as an important bridge between trained model capability and practical scientific decision-making, and also provide candidate knowledge and reasoning evidence for the downstream Evaluation Layer and Optimization Layer.
70
+
71
+ ---
72
+
73
+ ### Evaluation
74
+
75
+ In the evaluation layer, the recipe recommendations and mechanistic reasoning are evaluated, in order to measure their effectiveness, reliability, and scientific validity.
76
+ Through key atomic skills of recipe recommendation and mechanistic reasoning, the aspects of recipe integrity, formula rationality, parameter rationality, experimental validation, domain knowledge, mechanism integrity, interpretation, comprehensiveness and coherence are systematically assessed.
77
+
78
+ ---
79
+
80
+ ### Optimization
81
+
82
+ In the optimization layer, the RLM to be optimised and preference pairs of positive and negative samples are taken as the input of this layer.
83
+ Through atomic skill of Direct Preference Optimisation (DPO), an optimised RLM is obtained as output.
84
+ This layer further aligns the model towards preference-consistent and high-performance recipe recommendation.
85
+
86
+ ---
87
+
88
+ ## 6. Intended Use
89
+
90
+ The RLM is designed as a domain-specific model to bridge the gap between numerical machine learning, semantic recipe, and the physical experimentation in materials research (herein perovskite solar cell research with complex formulas and complicatedparameters as a demonstration). By integrating seven AI layers and interconnected robotic systems, its intended use is to automate and evolve physical AI through the following potential applications:
91
+
92
+ Autonomous Experimental Planning: The RLM translates high-level research objectives into granular, robot-executable "recipes". It functions as a high-level planner that identifies necessary actions, objects, and sequences required for materials synthesis and fabrication.
93
+
94
+ Physical-AI Coevolution: It drives the "coevolution" of Large Language Models (LLMs) with physical models, refining the AI's ability to conduct domain-specific simulations while generating real-world data to steer broader Materials Intelligence.
95
+
96
+ Knowledge-to-Action Translation: The model leverages its seven AI layers architecture to transform textual knowledge from scientific literature into structured, actionable steps, overcoming the "erudite scholar" limitation where AI possess knowledge but lacks the capacity for physical interaction.
97
+
98
+ Self-Driving Labs Integration: It serves as the cognitive core for robotic boxes (embodied AI), enabling robots to interpret natural language prompts, reason over mechanistic context, and execute multi-step tasks like material characterization and performance verification.
99
+
100
+ ## 7. Citation
101
+
102
+ If you use this work, please cite:
103
+
104
+ ```bibtex
105
+ @article{chen2026rlm,
106
+ title={Agentic Robotic Boxes for Perovskite Solar Cell Fabrication with Recipe Language Model},
107
+ author={Chen, Zijian and Yu, Wenjin and Wu, Chuang and Chen, Feibei and Wang, Zixuan and Zhou, Chao and You, Yimeng and Li, Shaojie and Zhu, Qiyuan and Ma, Ning and Sun, Yao and Li, Donghui and Fanady, Billy and Jiang, Shengchou and Yan, Zhongliang and Zhou, Shumin and Li, Liang and Hsieh, Chang-Yu and Bai, Yang and Xiao, Lixin and Chung, Chi-yung and Chan, Ching-chuen and Cui, Zhanfeng and Gr{\"a}tzel, Michael and Zhao, Haitao},
108
+ journal={Engineering},
109
+ year={2026},
110
+ doi={10.1016/j.eng.2026.04.002}
111
+ }
112
+ ```
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- 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>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n<think>\n' }}
86
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 151645,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 6144,
16
+ "max_position_embeddings": 262144,
17
+ "max_window_layers": 48,
18
+ "mlp_only_layers": [],
19
+ "model_type": "qwen3_moe",
20
+ "moe_intermediate_size": 768,
21
+ "norm_topk_prob": true,
22
+ "num_attention_heads": 32,
23
+ "num_experts": 128,
24
+ "num_experts_per_tok": 8,
25
+ "num_hidden_layers": 48,
26
+ "num_key_value_heads": 4,
27
+ "output_router_logits": false,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_scaling": null,
30
+ "rope_theta": 10000000,
31
+ "router_aux_loss_coef": 0.001,
32
+ "sliding_window": null,
33
+ "tie_word_embeddings": false,
34
+ "transformers_version": "4.56.0",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "vocab_size": 151936
38
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.56.0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eed1f5946e50b351214e06e8872f4a1592264c301b08bd1314f907e0418fc04
3
+ size 1998123464
model-00002-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf196521b5f068ffdd13f183ce3fbe3d6727d3bd25b0f38751076037e14c1d3
3
+ size 1998147512
model-00003-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72c50fc42d718d7653ac1e34ac8bfd9633422f97a953941f00c631ef50ce73d
3
+ size 1998680096
model-00004-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9101ef83dc9d67b15f47b6b8de999d5d5846849074d774b2b342abb1c715d096
3
+ size 1998147560
model-00005-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f255bb427877e50e6ad721fff22f0ff4440e870fdd36ac6de28b213333ef1a03
3
+ size 1998680048
model-00006-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1156c11ccb5ac1286acf44532e560471efdbeed192c8f2910d7d769d4b69cf29
3
+ size 1998680096
model-00007-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34dee7759964e71e0a737e4b5e11176c09a796ea4f2b2dc63eb6f39ddee769e4
3
+ size 1998147808
model-00008-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e659a16d8a43298181faa3de7a2125d99599d6efadd23f80bea05d713a2e83d3
3
+ size 1998680728
model-00009-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea71f0177d3f8abe3d38feacec7128fb6e531258f5cc975b29e85add7efa6f8
3
+ size 1998148200
model-00010-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349d0cbf5c9a53e5166b80328a53c94ac644e3ab2246b825aded79585a75660c
3
+ size 1998680664
model-00011-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:340c9ec95bfc3230022b765d9f656406dc0f5b1d76941d2667182e04b1b5ffdf
3
+ size 1998680728
model-00012-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b635adee6cb34f1451ce6c5ca9eee8d467c5ea871b00c02bf55ff60988fb422
3
+ size 1998148144
model-00013-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2224bd5300f0fd42eeecc427a4df436a8c785b3d89f0e671ffbcfe174f4cc287
3
+ size 1998680728
model-00014-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498e91ca08cc043939c006ff0e7eff9bbc126772d7a189bce660d3f50c83a431
3
+ size 1998148208
model-00015-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db18a81dda8438aa4053fccf328324155fb742921cfebf86e9a857c29b9cb453
3
+ size 1998680656
model-00016-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e62592865845dc9141d3ae0118f1ef8fa8efbad9a76446a872a22caa85663b5
3
+ size 1998680728
model-00017-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157cd400d084a300572c83beebbd4d285908f346dec752091c9a78389fb787e5
3
+ size 1998148144
model-00018-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f879e0a5d4dcd5ed483071433f88d80d7c42ff34b477877d789447a66628c36b
3
+ size 1998680728
model-00019-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03c2e001d0213754d33907a0b7663ba38a4c5a21484892fe53e70e0e575a5ac6
3
+ size 1998148208
model-00020-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86324dc2cf6d8c6d3f5c8b5f5be0eabf0aba0e5dc362997d6e3e5047fc84795e
3
+ size 1998680656
model-00021-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ee8fd3b5c564aa32a0318ec6cce285f46b087966085cd00b20173517c19f5e
3
+ size 1998680728
model-00022-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d8041befe31a8fa5a7b75f83535458aadbd78d47ede8692c6473b519e9b2b5d
3
+ size 1998148144
model-00023-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0000c5b214a5315a5e94d813c3f1a322150273a885332b49d8cb3895685b5e73
3
+ size 1998680728
model-00024-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f874a078be9eb4382e24cdf0bf33b730d57da19b686cce18604ba673dea870
3
+ size 1998148216
model-00025-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e14a3198c393d05eba4f3bb43bd004a8f27e66c6e624b8954037caaed6d5ce
3
+ size 1998680648
model-00026-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e46c480d5fa992a5f8e84ad13521ed816e039ace99c73d3528401d57be55d39
3
+ size 1998680728
model-00027-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8725da98e48ad0aa4089dcae2cbbda6209bfe748192d629b22c22e540617d3
3
+ size 1998148144
model-00028-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279f41eb4b83da6946a47c7da4a13a5d710cd0c43a6c428574719ad5768a5c5f
3
+ size 1998680728
model-00029-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1badafdfea770aa082b89d3b743c7b57f5183ca4ad7a68f8e82316fdb27001c1
3
+ size 1995010792
model-00030-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb28fa6022ea0cbe69d86e5e0a10a7c923963efe39e24377b8ed2c63c15e6ce
3
+ size 1998672224
model-00031-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30b71b68e9215ff45d4c192b9b190bd7d60810a2937d88f9a03f39c4df0b4dc
3
+ size 1116241256
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 1010000,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "left",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff