Hugging Face's logo

MerlinSafety
/
Pluto

Image-Text-to-Text
Safetensors
GGUF
English
qwen3_5
code
reasoning
distillation
reinforcement-learning
long-context
claude-code
openai-codex
quantum-entropy
merlin-research
conversational
Model card Files
xet
 Community
1
squ11z1 commited on
Commit
37a9e99
·
verified ·
1 Parent(s): e8d6742

Delete 8bit

Browse files
Files changed (11) hide show
  1. 8bit/README.md +0 -24
  2. 8bit/chat_template.jinja +0 -154
  3. 8bit/config.json +0 -124
  4. 8bit/generation_config.json +0 -6
  5. 8bit/model-00001-of-00003.safetensors +0 -3
  6. 8bit/model-00002-of-00003.safetensors +0 -3
  7. 8bit/model-00003-of-00003.safetensors +0 -3
  8. 8bit/model.safetensors.index.json +0 -0
  9. 8bit/processor_config.json +0 -60
  10. 8bit/tokenizer.json +0 -3
  11. 8bit/tokenizer_config.json +0 -32
8bit/README.md DELETED
@@ -1,24 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- base_model: Qwen/Qwen3.5-9B-Base
4
- tags:
5
- - qwen3_5
6
- - lora
7
- - reasoning
8
- - merlin-research
9
- - pluto
10
- - quantum-entropy
11
- ---
12
-
13
- # MerlinSafety/Pluto-Qwen3.5-9B
14
-
15
- This repository contains the **quantized export from pluto_merged** artifact for **Pluto**, a personalized Qwen3.5-9B model by **Merlin Research**.
16
-
17
- Training notes:
18
-
19
- - Base model: `Qwen/Qwen3.5-9B-Base`
20
- - Personalization: the model is instructed and reinforced to identify itself as **Pluto** by **Merlin Research**
21
- - Training data: local `messages` SFT dataset
22
- - Quantum entropy usage: raw IBM quantum bitstrings were used as a stochastic source for seeds, dataset shuffle, split, and crop jitter
23
-
24
- This entropy source was used as an external stochastic controller, not as fake supervised labels.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8bit/chat_template.jinja DELETED
@@ -1,154 +0,0 @@
1
- {%- set image_count = namespace(value=0) %}
2
- {%- set video_count = namespace(value=0) %}
3
- {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
- {%- if content is string %}
5
- {{- content }}
6
- {%- elif content is iterable and content is not mapping %}
7
- {%- for item in content %}
8
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
- {%- if is_system_content %}
10
- {{- raise_exception('System message cannot contain images.') }}
11
- {%- endif %}
12
- {%- if do_vision_count %}
13
- {%- set image_count.value = image_count.value + 1 %}
14
- {%- endif %}
15
- {%- if add_vision_id %}
16
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
- {%- endif %}
18
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
- {%- elif 'video' in item or item.type == 'video' %}
20
- {%- if is_system_content %}
21
- {{- raise_exception('System message cannot contain videos.') }}
22
- {%- endif %}
23
- {%- if do_vision_count %}
24
- {%- set video_count.value = video_count.value + 1 %}
25
- {%- endif %}
26
- {%- if add_vision_id %}
27
- {{- 'Video ' ~ video_count.value ~ ': ' }}
28
- {%- endif %}
29
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
- {%- elif 'text' in item %}
31
- {{- item.text }}
32
- {%- else %}
33
- {{- raise_exception('Unexpected item type in content.') }}
34
- {%- endif %}
35
- {%- endfor %}
36
- {%- elif content is none or content is undefined %}
37
- {{- '' }}
38
- {%- else %}
39
- {{- raise_exception('Unexpected content type.') }}
40
- {%- endif %}
41
- {%- endmacro %}
42
- {%- if not messages %}
43
- {{- raise_exception('No messages provided.') }}
44
- {%- endif %}
45
- {%- if tools and tools is iterable and tools is not mapping %}
46
- {{- '<|im_start|>system\n' }}
47
- {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
- {%- for tool in tools %}
49
- {{- "\n" }}
50
- {{- tool | tojson }}
51
- {%- endfor %}
52
- {{- "\n</tools>" }}
53
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
- {%- if messages[0].role == 'system' %}
55
- {%- set content = render_content(messages[0].content, false, true)|trim %}
56
- {%- if content %}
57
- {{- '\n\n' + content }}
58
- {%- endif %}
59
- {%- endif %}
60
- {{- '<|im_end|>\n' }}
61
- {%- else %}
62
- {%- if messages[0].role == 'system' %}
63
- {%- set content = render_content(messages[0].content, false, true)|trim %}
64
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
- {%- endif %}
66
- {%- endif %}
67
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
- {%- for message in messages[::-1] %}
69
- {%- set index = (messages|length - 1) - loop.index0 %}
70
- {%- if ns.multi_step_tool and message.role == "user" %}
71
- {%- set content = render_content(message.content, false)|trim %}
72
- {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
- {%- set ns.multi_step_tool = false %}
74
- {%- set ns.last_query_index = index %}
75
- {%- endif %}
76
- {%- endif %}
77
- {%- endfor %}
78
- {%- if ns.multi_step_tool %}
79
- {{- raise_exception('No user query found in messages.') }}
80
- {%- endif %}
81
- {%- for message in messages %}
82
- {%- set content = render_content(message.content, true)|trim %}
83
- {%- if message.role == "system" %}
84
- {%- if not loop.first %}
85
- {{- raise_exception('System message must be at the beginning.') }}
86
- {%- endif %}
87
- {%- elif message.role == "user" %}
88
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
- {%- elif message.role == "assistant" %}
90
- {%- set reasoning_content = '' %}
91
- {%- if message.reasoning_content is string %}
92
- {%- set reasoning_content = message.reasoning_content %}
93
- {%- else %}
94
- {%- if '</think>' in content %}
95
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
- {%- endif %}
98
- {%- endif %}
99
- {%- set reasoning_content = reasoning_content|trim %}
100
- {%- if loop.index0 > ns.last_query_index %}
101
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
- {%- else %}
103
- {{- '<|im_start|>' + message.role + '\n' + content }}
104
- {%- endif %}
105
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
- {%- for tool_call in message.tool_calls %}
107
- {%- if tool_call.function is defined %}
108
- {%- set tool_call = tool_call.function %}
109
- {%- endif %}
110
- {%- if loop.first %}
111
- {%- if content|trim %}
112
- {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
- {%- else %}
114
- {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
- {%- endif %}
116
- {%- else %}
117
- {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
- {%- endif %}
119
- {%- if tool_call.arguments is defined %}
120
- {%- for args_name, args_value in tool_call.arguments|items %}
121
- {{- '<parameter=' + args_name + '>\n' }}
122
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
- {{- args_value }}
124
- {{- '\n</parameter>\n' }}
125
- {%- endfor %}
126
- {%- endif %}
127
- {{- '</function>\n</tool_call>' }}
128
- {%- endfor %}
129
- {%- endif %}
130
- {{- '<|im_end|>\n' }}
131
- {%- elif message.role == "tool" %}
132
- {%- if loop.previtem and loop.previtem.role != "tool" %}
133
- {{- '<|im_start|>user' }}
134
- {%- endif %}
135
- {{- '\n<tool_response>\n' }}
136
- {{- content }}
137
- {{- '\n</tool_response>' }}
138
- {%- if not loop.last and loop.nextitem.role != "tool" %}
139
- {{- '<|im_end|>\n' }}
140
- {%- elif loop.last %}
141
- {{- '<|im_end|>\n' }}
142
- {%- endif %}
143
- {%- else %}
144
- {{- raise_exception('Unexpected message role.') }}
145
- {%- endif %}
146
- {%- endfor %}
147
- {%- if add_generation_prompt %}
148
- {{- '<|im_start|>assistant\n' }}
149
- {%- if enable_thinking is defined and enable_thinking is false %}
150
- {{- '<think>\n\n</think>\n\n' }}
151
- {%- else %}
152
- {{- '<think>\n' }}
153
- {%- endif %}
154
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8bit/config.json DELETED
@@ -1,124 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
4
- ],
5
- "dtype": "bfloat16",
6
- "image_token_id": 248056,
7
- "model_type": "qwen3_5",
8
- "quantization_config": {
9
- "_load_in_4bit": false,
10
- "_load_in_8bit": true,
11
- "bnb_4bit_compute_dtype": "float32",
12
- "bnb_4bit_quant_storage": "uint8",
13
- "bnb_4bit_quant_type": "fp4",
14
- "bnb_4bit_use_double_quant": false,
15
- "llm_int8_enable_fp32_cpu_offload": false,
16
- "llm_int8_has_fp16_weight": false,
17
- "llm_int8_skip_modules": null,
18
- "llm_int8_threshold": 6.0,
19
- "load_in_4bit": false,
20
- "load_in_8bit": true,
21
- "quant_method": "bitsandbytes"
22
- },
23
- "text_config": {
24
- "attention_bias": false,
25
- "attention_dropout": 0.0,
26
- "attn_output_gate": true,
27
- "bos_token_id": null,
28
- "dtype": "bfloat16",
29
- "eos_token_id": 248044,
30
- "full_attention_interval": 4,
31
- "head_dim": 256,
32
- "hidden_act": "silu",
33
- "hidden_size": 4096,
34
- "initializer_range": 0.02,
35
- "intermediate_size": 12288,
36
- "layer_types": [
37
- "linear_attention",
38
- "linear_attention",
39
- "linear_attention",
40
- "full_attention",
41
- "linear_attention",
42
- "linear_attention",
43
- "linear_attention",
44
- "full_attention",
45
- "linear_attention",
46
- "linear_attention",
47
- "linear_attention",
48
- "full_attention",
49
- "linear_attention",
50
- "linear_attention",
51
- "linear_attention",
52
- "full_attention",
53
- "linear_attention",
54
- "linear_attention",
55
- "linear_attention",
56
- "full_attention",
57
- "linear_attention",
58
- "linear_attention",
59
- "linear_attention",
60
- "full_attention",
61
- "linear_attention",
62
- "linear_attention",
63
- "linear_attention",
64
- "full_attention",
65
- "linear_attention",
66
- "linear_attention",
67
- "linear_attention",
68
- "full_attention"
69
- ],
70
- "linear_conv_kernel_dim": 4,
71
- "linear_key_head_dim": 128,
72
- "linear_num_key_heads": 16,
73
- "linear_num_value_heads": 32,
74
- "linear_value_head_dim": 128,
75
- "mamba_ssm_dtype": "float32",
76
- "max_position_embeddings": 262144,
77
- "mlp_only_layers": [],
78
- "model_type": "qwen3_5_text",
79
- "mtp_num_hidden_layers": 1,
80
- "mtp_use_dedicated_embeddings": false,
81
- "num_attention_heads": 16,
82
- "num_hidden_layers": 32,
83
- "num_key_value_heads": 4,
84
- "pad_token_id": null,
85
- "partial_rotary_factor": 0.25,
86
- "rms_norm_eps": 1e-06,
87
- "rope_parameters": {
88
- "mrope_interleaved": true,
89
- "mrope_section": [
90
- 11,
91
- 11,
92
- 10
93
- ],
94
- "partial_rotary_factor": 0.25,
95
- "rope_theta": 10000000,
96
- "rope_type": "default"
97
- },
98
- "tie_word_embeddings": false,
99
- "use_cache": true,
100
- "vocab_size": 248320
101
- },
102
- "tie_word_embeddings": false,
103
- "transformers_version": "5.3.0.dev0",
104
- "video_token_id": 248057,
105
- "vision_config": {
106
- "deepstack_visual_indexes": [],
107
- "depth": 27,
108
- "dtype": "bfloat16",
109
- "hidden_act": "gelu_pytorch_tanh",
110
- "hidden_size": 1152,
111
- "in_channels": 3,
112
- "initializer_range": 0.02,
113
- "intermediate_size": 4304,
114
- "model_type": "qwen3_5",
115
- "num_heads": 16,
116
- "num_position_embeddings": 2304,
117
- "out_hidden_size": 4096,
118
- "patch_size": 16,
119
- "spatial_merge_size": 2,
120
- "temporal_patch_size": 2
121
- },
122
- "vision_end_token_id": 248054,
123
- "vision_start_token_id": 248053
124
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8bit/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "eos_token_id": 248044,
4
- "transformers_version": "5.3.0.dev0",
5
- "use_cache": true
6
- }
 
 
 
 
 
 
 
8bit/model-00001-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:787941410e49c5bc47a3286930314c21ebb4e599c66f5e5368f149f498f1bd06
3
- size 4985016435
 
 
 
 
8bit/model-00002-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f280f9b4194d92bd90a880269a897ee65cbc3dfc03b8676be43b3e683d47f1e3
3
- size 4984594192
 
 
 
 
8bit/model-00003-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1167826079c847f8ddc7537e0191d597e1b22ead4486eae3cc899ad396b4f7ad
3
- size 1487340059
 
 
 
 
8bit/model.safetensors.index.json DELETED
The diff for this file is too large to render. See raw diff
 
8bit/processor_config.json DELETED
@@ -1,60 +0,0 @@
1
- {
2
- "image_processor": {
3
- "do_convert_rgb": true,
4
- "do_normalize": true,
5
- "do_rescale": true,
6
- "do_resize": true,
7
- "image_mean": [
8
- 0.5,
9
- 0.5,
10
- 0.5
11
- ],
12
- "image_processor_type": "Qwen2VLImageProcessor",
13
- "image_std": [
14
- 0.5,
15
- 0.5,
16
- 0.5
17
- ],
18
- "merge_size": 2,
19
- "patch_size": 16,
20
- "resample": 3,
21
- "rescale_factor": 0.00392156862745098,
22
- "size": {
23
- "longest_edge": 16777216,
24
- "shortest_edge": 65536
25
- },
26
- "temporal_patch_size": 2
27
- },
28
- "processor_class": "Qwen3VLProcessor",
29
- "video_processor": {
30
- "do_convert_rgb": true,
31
- "do_normalize": true,
32
- "do_rescale": true,
33
- "do_resize": true,
34
- "do_sample_frames": true,
35
- "fps": 2,
36
- "image_mean": [
37
- 0.5,
38
- 0.5,
39
- 0.5
40
- ],
41
- "image_std": [
42
- 0.5,
43
- 0.5,
44
- 0.5
45
- ],
46
- "max_frames": 768,
47
- "merge_size": 2,
48
- "min_frames": 4,
49
- "patch_size": 16,
50
- "resample": 3,
51
- "rescale_factor": 0.00392156862745098,
52
- "return_metadata": false,
53
- "size": {
54
- "longest_edge": 234881024,
55
- "shortest_edge": 4096
56
- },
57
- "temporal_patch_size": 2,
58
- "video_processor_type": "Qwen3VLVideoProcessor"
59
- }
60
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8bit/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
- size 19989343
 
 
 
 
8bit/tokenizer_config.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "audio_bos_token": "<|audio_start|>",
4
- "audio_eos_token": "<|audio_end|>",
5
- "audio_token": "<|audio_pad|>",
6
- "backend": "tokenizers",
7
- "bos_token": null,
8
- "clean_up_tokenization_spaces": false,
9
- "eos_token": "<|endoftext|>",
10
- "errors": "replace",
11
- "image_token": "<|image_pad|>",
12
- "is_local": false,
13
- "model_max_length": 262144,
14
- "model_specific_special_tokens": {
15
- "audio_bos_token": "<|audio_start|>",
16
- "audio_eos_token": "<|audio_end|>",
17
- "audio_token": "<|audio_pad|>",
18
- "image_token": "<|image_pad|>",
19
- "video_token": "<|video_pad|>",
20
- "vision_bos_token": "<|vision_start|>",
21
- "vision_eos_token": "<|vision_end|>"
22
- },
23
- "pad_token": "<|endoftext|>",
24
- "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
- "processor_class": "Qwen3VLProcessor",
26
- "split_special_tokens": false,
27
- "tokenizer_class": "TokenizersBackend",
28
- "unk_token": null,
29
- "video_token": "<|video_pad|>",
30
- "vision_bos_token": "<|vision_start|>",
31
- "vision_eos_token": "<|vision_end|>"
32
- }