Hugging Face's logo

majentik
/
Qwen3.5-397B-A17B-RotorQuant-MLX-2bit

Image-Text-to-Text
MLX
Safetensors
English
Chinese
multilingual
qwen3_5_moe
rotorquant
apple-silicon
weight-quantization
2-bit
extreme-quantization
qwen3.5
qwen
Mixture of Experts
sparse-moe
multimodal
quantized
long-context
conversational
Model card Files
xet
 Community
majentik commited on
Commit
a625ad8
·
verified ·
1 Parent(s): 80e1acc

Add MLX 2-bit quantized model

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. README.md +95 -0
  3. chat_template.jinja +154 -0
  4. config.json +149 -0
  5. generation_config.json +13 -0
  6. model-00001-of-00046.safetensors +3 -0
  7. model-00002-of-00046.safetensors +3 -0
  8. model-00003-of-00046.safetensors +3 -0
  9. model-00004-of-00046.safetensors +3 -0
  10. model-00005-of-00046.safetensors +3 -0
  11. model-00006-of-00046.safetensors +3 -0
  12. model-00007-of-00046.safetensors +3 -0
  13. model-00008-of-00046.safetensors +3 -0
  14. model-00009-of-00046.safetensors +3 -0
  15. model-00010-of-00046.safetensors +3 -0
  16. model-00011-of-00046.safetensors +3 -0
  17. model-00012-of-00046.safetensors +3 -0
  18. model-00013-of-00046.safetensors +3 -0
  19. model-00014-of-00046.safetensors +3 -0
  20. model-00015-of-00046.safetensors +3 -0
  21. model-00016-of-00046.safetensors +3 -0
  22. model-00017-of-00046.safetensors +3 -0
  23. model-00018-of-00046.safetensors +3 -0
  24. model-00019-of-00046.safetensors +3 -0
  25. model-00020-of-00046.safetensors +3 -0
  26. model-00021-of-00046.safetensors +3 -0
  27. model-00022-of-00046.safetensors +3 -0
  28. model-00023-of-00046.safetensors +3 -0
  29. model-00024-of-00046.safetensors +3 -0
  30. model-00025-of-00046.safetensors +3 -0
  31. model-00026-of-00046.safetensors +3 -0
  32. model-00027-of-00046.safetensors +3 -0
  33. model-00028-of-00046.safetensors +3 -0
  34. model-00029-of-00046.safetensors +3 -0
  35. model-00030-of-00046.safetensors +3 -0
  36. model-00031-of-00046.safetensors +3 -0
  37. model-00032-of-00046.safetensors +3 -0
  38. model-00033-of-00046.safetensors +3 -0
  39. model-00034-of-00046.safetensors +3 -0
  40. model-00035-of-00046.safetensors +3 -0
  41. model-00036-of-00046.safetensors +3 -0
  42. model-00037-of-00046.safetensors +3 -0
  43. model-00038-of-00046.safetensors +3 -0
  44. model-00039-of-00046.safetensors +3 -0
  45. model-00040-of-00046.safetensors +3 -0
  46. model-00041-of-00046.safetensors +3 -0
  47. model-00042-of-00046.safetensors +3 -0
  48. model-00043-of-00046.safetensors +3 -0
  49. model-00044-of-00046.safetensors +3 -0
  50. model-00045-of-00046.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
 
 
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
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3.5-397B-A17B
3
+ library_name: mlx
4
+ license: apache-2.0
5
+ pipeline_tag: image-text-to-text
6
+ tags:
7
+ - rotorquant
8
+ - mlx
9
+ - apple-silicon
10
+ - weight-quantization
11
+ - 2-bit
12
+ - extreme-quantization
13
+ - qwen3.5
14
+ - qwen
15
+ - moe
16
+ - sparse-moe
17
+ - multimodal
18
+ - image-text-to-text
19
+ - quantized
20
+ - long-context
21
+ language:
22
+ - en
23
+ - zh
24
+ - multilingual
25
+ ---
26
+
27
+ # Qwen3.5-397B-A17B-RotorQuant-MLX-2bit
28
+
29
+ **2-bit MLX weight-quantized** build of **Qwen/Qwen3.5-397B-A17B** (397B total / 17B active Sparse MoE, multimodal) — **re-quantized from the 4-bit RotorQuant MLX checkpoint** for maximum compression. Optimized for Apple Silicon via [MLX](https://github.com/ml-explore/mlx).
30
+
31
+ An **experimental extreme-compression** variant: the learned rotors from RotorQuant's calibration pass help preserve weight structure significantly better than static rotations at this bit-width. It is the highest-quality 2-bit build of Qwen3.5-397B-A17B in the Majentik suite.
32
+
33
+ ## Quickstart
34
+
35
+ ```python
36
+ from mlx_lm import load, generate
37
+
38
+ model, tokenizer = load("majentik/Qwen3.5-397B-A17B-RotorQuant-MLX-2bit")
39
+
40
+ prompt = tokenizer.apply_chat_template(
41
+ [{"role": "user", "content": "Describe what a 2-bit weight means in one sentence."}],
42
+ add_generation_prompt=True,
43
+ )
44
+ print(generate(model, tokenizer, prompt=prompt, max_tokens=128, verbose=True))
45
+ ```
46
+
47
+ ## Model Specs
48
+
49
+ | Property | Value |
50
+ | ---------------------- | ------------------------------------------------ |
51
+ | Base model | Qwen/Qwen3.5-397B-A17B |
52
+ | Architecture | Sparse Mixture-of-Experts (MoE) |
53
+ | Total parameters | 397B |
54
+ | Active per token | 17B |
55
+ | Modalities | Image + Text → Text (`image-text-to-text`) |
56
+ | Context window | 256K tokens |
57
+ | Weight quantization | 2-bit MLX (re-quantized from 4-bit RotorQuant) |
58
+ | Approx. disk footprint | ~135 GB |
59
+ | License | Apache 2.0 |
60
+
61
+ ## RotorQuant vs TurboQuant
62
+
63
+ | Aspect | RotorQuant (this repo) | TurboQuant |
64
+ | ------------------- | ------------------------------------------------ | ------------------------------------------- |
65
+ | Rotation | Learned orthogonal rotors (data-calibrated) | Randomized Hadamard (static) |
66
+ | Calibration | ~512 sample calibration pass | Zero-shot |
67
+ | Accuracy @ 2-bit | ~95–97% of FP16 baseline (task-dependent) | ~93–95% of FP16 baseline (task-dependent) |
68
+ | Best for | Squeezing the model in with the best quality | Squeezing the model into small VRAM |
69
+
70
+ ## Memory Estimates (2-bit MLX)
71
+
72
+ | Context | Active memory (approx.) |
73
+ | ------- | ----------------------- |
74
+ | 8K | ~143 GB |
75
+ | 32K | ~153 GB |
76
+ | 128K | ~183 GB |
77
+ | 256K | ~213 GB |
78
+
79
+ ## Hardware Requirements
80
+
81
+ - **Minimum**: Apple Silicon with **192 GB unified memory** for short/medium contexts
82
+ - **Recommended**: **256 GB+** unified memory for full 256K context
83
+ - Fits on top-end Mac Studio M-series configurations; **does not** fit on 96 GB or 128 GB Macs
84
+
85
+ ## Caveats
86
+
87
+ - Re-quantized from the 4-bit RotorQuant MLX checkpoint (not directly from FP16)
88
+ - Still the preferred 2-bit option — learned rotors meaningfully outperform Hadamard rotations at extreme bit-widths
89
+ - For production use, prefer the 4-bit or higher variants when your hardware allows
90
+
91
+ ## See Also
92
+
93
+ - RotorQuant MLX: [8-bit](https://huggingface.co/majentik/Qwen3.5-397B-A17B-RotorQuant-MLX-8bit) · [6-bit](https://huggingface.co/majentik/Qwen3.5-397B-A17B-RotorQuant-MLX-6bit) · [5-bit](https://huggingface.co/majentik/Qwen3.5-397B-A17B-RotorQuant-MLX-5bit) · [4-bit](https://huggingface.co/majentik/Qwen3.5-397B-A17B-RotorQuant-MLX-4bit)
94
+ - TurboQuant MLX 2-bit: [majentik/Qwen3.5-397B-A17B-TurboQuant-MLX-2bit](https://huggingface.co/majentik/Qwen3.5-397B-A17B-TurboQuant-MLX-2bit)
95
+ - Base model: [Qwen/Qwen3.5-397B-A17B](https://huggingface.co/Qwen/Qwen3.5-397B-A17B)
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 %}
config.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
+ ],
5
+ "eos_token_id": [
6
+ 248046,
7
+ 248044
8
+ ],
9
+ "image_token_id": 248056,
10
+ "model_type": "qwen3_5_moe",
11
+ "quantization": {
12
+ "bits": 2,
13
+ "group_size": 64,
14
+ "mode": "affine"
15
+ },
16
+ "quantization_config": {
17
+ "bits": 2,
18
+ "group_size": 64,
19
+ "mode": "affine"
20
+ },
21
+ "text_config": {
22
+ "attention_bias": false,
23
+ "attention_dropout": 0.0,
24
+ "attn_output_gate": true,
25
+ "dtype": "bfloat16",
26
+ "eos_token_id": 248044,
27
+ "full_attention_interval": 4,
28
+ "head_dim": 256,
29
+ "hidden_act": "silu",
30
+ "hidden_size": 4096,
31
+ "initializer_range": 0.02,
32
+ "layer_types": [
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
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
+ "linear_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "full_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "full_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "full_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "full_attention",
85
+ "linear_attention",
86
+ "linear_attention",
87
+ "linear_attention",
88
+ "full_attention",
89
+ "linear_attention",
90
+ "linear_attention",
91
+ "linear_attention",
92
+ "full_attention"
93
+ ],
94
+ "linear_conv_kernel_dim": 4,
95
+ "linear_key_head_dim": 128,
96
+ "linear_num_key_heads": 16,
97
+ "linear_num_value_heads": 64,
98
+ "linear_value_head_dim": 128,
99
+ "max_position_embeddings": 262144,
100
+ "mlp_only_layers": [],
101
+ "model_type": "qwen3_5_moe_text",
102
+ "moe_intermediate_size": 1024,
103
+ "mtp_num_hidden_layers": 1,
104
+ "mtp_use_dedicated_embeddings": false,
105
+ "num_attention_heads": 32,
106
+ "num_experts": 512,
107
+ "num_experts_per_tok": 10,
108
+ "num_hidden_layers": 60,
109
+ "num_key_value_heads": 2,
110
+ "rms_norm_eps": 1e-06,
111
+ "router_aux_loss_coef": 0.001,
112
+ "shared_expert_intermediate_size": 1024,
113
+ "use_cache": true,
114
+ "vocab_size": 248320,
115
+ "mamba_ssm_dtype": "float32",
116
+ "rope_parameters": {
117
+ "mrope_interleaved": true,
118
+ "mrope_section": [
119
+ 11,
120
+ 11,
121
+ 10
122
+ ],
123
+ "rope_type": "default",
124
+ "rope_theta": 10000000,
125
+ "partial_rotary_factor": 0.25
126
+ }
127
+ },
128
+ "tie_word_embeddings": false,
129
+ "transformers_version": "4.57.0.dev0",
130
+ "video_token_id": 248057,
131
+ "vision_config": {
132
+ "deepstack_visual_indexes": [],
133
+ "depth": 27,
134
+ "hidden_act": "gelu_pytorch_tanh",
135
+ "hidden_size": 1152,
136
+ "in_channels": 3,
137
+ "initializer_range": 0.02,
138
+ "intermediate_size": 4304,
139
+ "model_type": "qwen3_5_moe",
140
+ "num_heads": 16,
141
+ "num_position_embeddings": 2304,
142
+ "out_hidden_size": 4096,
143
+ "patch_size": 16,
144
+ "spatial_merge_size": 2,
145
+ "temporal_patch_size": 2
146
+ },
147
+ "vision_end_token_id": 248054,
148
+ "vision_start_token_id": 248053
149
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.0.dev0"
13
+ }
model-00001-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:245b82000aac5dd6b6a1ff435e89d2523318ddcf297d5f8b243e392e914d63ce
3
+ size 3322386345
model-00002-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5771c06d1cf935fbbd77a158b7d4143ee0b8491cf545c2db309c3dee68f7b8fd
3
+ size 2725929128
model-00003-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c4c225bdc37ee887c9d5c973bfec0bdfb253508009c8e60755c373a436bc9c
3
+ size 2721734503
model-00004-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6235a7a5c4eaebe71884a870bc17daf3c853cc7599efc2379fca824781ed0908
3
+ size 2767502054
model-00005-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b26232775bfd26100150f6b7f3cc3bdc3d833736f77aebc18ba7564dd878008
3
+ size 2725929132
model-00006-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1d0f27defc4580e2b755fcc972c50d53d88c779694bc5998bf4030f4cc8323
3
+ size 2721734531
model-00007-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c455143ee79e3e912e1c1c1a7f70ef6bf56da42fd1135d4a4d1c25ea8ff5f7f5
3
+ size 2767502054
model-00008-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12e4592853e8e6719391903edc8e9868d4a292f6ae629e93b2d006ebc0d7607
3
+ size 2725929213
model-00009-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76401642283bec953c8d41a390ec952c27277c15ff709f8e7fbcccaca611877
3
+ size 2721734550
model-00010-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a4281de97abcd3d4fefd1611ac3f26632ea99653a3e988777a90bf9cbb3693
3
+ size 2767502172
model-00011-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f61b8797366f3a7a95e48194025200d448ccb6adfd43230661f90e98c2eaca
3
+ size 2725929218
model-00012-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b4087a903baf3149eefedd2fd4a8327cce4a3a530a727013efb81c15e0e2b5d
3
+ size 2721734574
model-00013-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf008d981ec496208aa539c48d2d37d52def2f4e8c93fb687570c38a4b26007e
3
+ size 2767502126
model-00014-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71595016e34c51b8877ef4d64c49f1dba8369e3dc58bd05587c73eb821aa051d
3
+ size 2725929198
model-00015-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f046b50b5390d818a01fa30296c6a4d9144368458421da8c96999e8c51e04a
3
+ size 2721734572
model-00016-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e49b3ba0ef7e770dcfe586a070efbf14f40da8423cc4101295119611ce5a07
3
+ size 2767502074
model-00017-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8af48879615f87843d8a5f4d6572289e45ac05494ef27abade79b697b34b58
3
+ size 2725929182
model-00018-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b71bd16a7a7eaa464e7af77a76bbe15655a45255b837371144eafffa33dd56
3
+ size 2721734572
model-00019-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eca5c25c436b8c244bf4801ab7fb4462511c40f2284eb51a55b68e96264e28e
3
+ size 2767502146
model-00020-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec85054bc8cd7348536676ac535a1517d5e713785a2663394945622dfdc5f46
3
+ size 2725929178
model-00021-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df220fc6f50224eabb48b4d542b09e18e0488af709fa32cca7eb46960941e63c
3
+ size 2721734540
model-00022-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83cd85aef05398a00d7f545d2be15e7b1b7ed7f36566a510fcf6d1c9a49c8443
3
+ size 2767502146
model-00023-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91082571ec9f39dff297d77894e2a959e3dded0544377b2b2a9fe47a6c9d523
3
+ size 2725929198
model-00024-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb3b248c214384d0c6c09460edad2d89c9f81894dab19b162e079110adeb4c5
3
+ size 2721734550
model-00025-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c19f557578d01e999ccdc70dfb11b77f98cb5ac4ef8ea1e253c3706f490f6e9
3
+ size 2767502144
model-00026-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4de4fbc39a570c1a6d8d4c0e951f7de4ce3c801b08473d75c5f7178de43f8c34
3
+ size 2725929204
model-00027-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c66be30c29810b6a187ac5d933c5117d56e61d149ffe9d2c3018facd8edc32
3
+ size 2721734546
model-00028-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b78df2a85f02de3af0f77631aecbb8a99e27b51dcb0bfc50ee568aa5fe6b14b
3
+ size 2767502134
model-00029-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19df35b79f692cee6cd1e537a05406df01a2cb08e30dd645c444b639aaa9734c
3
+ size 2725929194
model-00030-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7eb86639d86b66b88100c7ca23bcacbbe512456da02cbbc198df3aee5915f3a
3
+ size 2721734570
model-00031-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5955586d3ef373ad9631e28c587622988cf2a67f4a277d56e852c2eaf5a89cd6
3
+ size 2767502144
model-00032-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391984d62032ca4cd7d468351f8eb60d417a8d93dc9828401644a0243df49a52
3
+ size 2725929156
model-00033-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0085530ff5a4eeb68225da7e1fdd988dc6319ccc252be7abb778fa66ba10271
3
+ size 2721734574
model-00034-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d842982eaa1e7f2e898738e671f027fb176bd9c7ab7c750fa9e410d395901bfa
3
+ size 2767502124
model-00035-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53e2d064100fc9fc70b41ccac5d823868e18c1ccb6fd12a569b043fcf62eea1
3
+ size 2725929202
model-00036-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727d596ffecc06e73ee722461244a18b782fce0cbb47b229f579163bd2dd8ef1
3
+ size 2721734568
model-00037-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c03388578eb61fa2b8d9ddae8f2b48796ebf212087f69ece5b64a3ce758eb6
3
+ size 2767502094
model-00038-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb242e0b4dce30582a3b277a0307d0823645b44ae74c816c67ec6948113bdf0
3
+ size 2725929174
model-00039-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68226007bfa7a6e2d1fb844639bb49ffb6a6ba383546f759fd581d01eae89763
3
+ size 2721734540
model-00040-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2aa27b4ad4662941b0bb99206731b7407eb8f1429ee6055e1470bcba867371b
3
+ size 2767502146
model-00041-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b31c838870e349455bef654ee0414955b055e8a5be708d5f43291adc85e83b
3
+ size 2725929216
model-00042-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb7ec4599ece51a2a20dad80a9245dd8da600e7b443e7662a3a43f9383e86bb0
3
+ size 2721734546
model-00043-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748d012d13b6dd79e016b73b1711511d3077178e8f53721172e9742fb807c6fe
3
+ size 2767502120
model-00044-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76d96901df23bfe7fc755e79699bae343c60f8ece391dfbc21b8b13a8632ad5
3
+ size 2725929210
model-00045-of-00046.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4e24e6a1efcb2e96f16b1d2b695e6d04cf275f7c23c7194b019bccb49ae506b
3
+ size 2721734570