AmanPriyanshu commited on
Commit
2c85aa4
·
verified ·
1 Parent(s): 1c1d66d

Upload health_or_medicine model with 27 experts (17.9B params)

Browse files
.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 +1,356 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations
5
+ language:
6
+ - en
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - mixture-of-experts
10
+ - moe
11
+ - expert-pruning
12
+ - gpt-oss
13
+ - openai
14
+ - reasoning
15
+ - health-or-medicine
16
+ - specialized
17
+ - efficient
18
+ - transformer
19
+ - causal-lm
20
+ - text-generation
21
+ - pytorch
22
+ - pruned-model
23
+ - domain-specific
24
+ ---
25
+
26
+ # Health Or Medicine GPT-OSS Model (27 Experts)
27
+
28
+ **Project**: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/
29
+
30
+ <div align="center">
31
+
32
+ ### 👥 Follow the Authors
33
+
34
+ **Aman Priyanshu**
35
+ [![LinkedIn](https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/aman-priyanshu/)
36
+ [![Twitter](https://img.shields.io/badge/Twitter-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white)](https://x.com/AmanPriyanshu6)
37
+ [![Website](https://img.shields.io/badge/Website-FF7139?style=for-the-badge&logo=firefox&logoColor=white)](https://amanpriyanshu.github.io/)
38
+
39
+ **Supriti Vijay**
40
+ [![LinkedIn](https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/supriti-vijay/)
41
+ [![Twitter](https://img.shields.io/badge/Twitter-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white)](https://x.com/SupritiVijay)
42
+ [![Website](https://img.shields.io/badge/Website-FF7139?style=for-the-badge&logo=firefox&logoColor=white)](https://supritivijay.github.io/)
43
+
44
+ </div>
45
+
46
+ ## Introduction
47
+
48
+ This is a pruned variant of OpenAI's GPT-OSS-20B model, reduced to 27 experts per layer based on activation patterns from the [AmanPriyanshu/GPT-OSS-20B MoE Expert Activations dataset](https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations). We analyzed router decisions across evaluation benchmarks to identify and retain experts most relevant for health or medicine tasks.
49
+
50
+ **⚠️ Experimental Model**: This is an experimental pruned model that may not work well - check the [examples below](#model-examples) to see if the outputs meet your needs before use.
51
+
52
+ This pruning approach reduces the model size while attempting to preserve performance on the target domain.
53
+
54
+ ## Model Architecture & Statistics
55
+
56
+ | Metric | Value |
57
+ |--------|-------|
58
+ | **Base Model** | openai/gpt-oss-20b |
59
+ | **Architecture** | Mixture-of-Experts Transformer |
60
+ | **Total Parameters** | ~17.9B (pruned from 21B) |
61
+ | **Original Experts per Layer** | 32 |
62
+ | **Pruned Experts per Layer** | 27 |
63
+ | **Layers** | 24 |
64
+ | **Top-k Routing** | 4 |
65
+ | **Context Length** | 128K tokens |
66
+ | **Attention Heads** | 64 (Query), 8 (Key-Value) |
67
+ | **Residual Dimension** | 2880 |
68
+ | **Attention Pattern** | Alternating dense & sliding window (128 tokens) |
69
+ | **Positional Encoding** | RoPE (Rotary Position Embedding) |
70
+ | **Normalization** | RMSNorm |
71
+ | **Precision** | BF16 |
72
+ | **License** | Apache 2.0 |
73
+ | **Specialization** | Health Or Medicine |
74
+
75
+ ## Pruning Methodology
76
+
77
+ ### What is Expert Pruning?
78
+ Mixture-of-Experts models contain multiple specialized sub-networks (experts) per layer. During inference, only a subset of experts are activated for each token. Expert pruning involves:
79
+
80
+ 1. **Analyzing Usage Patterns**: Tracking which experts activate most frequently for specific tasks
81
+ 2. **Removing Underutilized Experts**: Discarding experts with low activation rates for the target domain
82
+ 3. **Preserving Router Functionality**: Maintaining the routing mechanism with fewer available experts
83
+
84
+ ### Our Approach
85
+ - **Data-Driven Selection**: Used activation patterns from health or medicine evaluation tasks
86
+ - **Systematic Reduction**: Reduced from 32 to 27 experts per layer
87
+ - **No Retraining**: Direct removal without additional training steps
88
+
89
+ ## Performance & Applications
90
+
91
+ ### Pruning Benefits
92
+ - **Smaller Memory Footprint**: 84.4% of original expert parameters
93
+ - **Reduced Computational Load**: Fewer routing decisions during inference
94
+ - **Focused Capabilities**: Retains experts relevant to health or medicine tasks
95
+
96
+ ### Use Cases
97
+ - **Speculative Decoding**: Draft model for full GPT-OSS-20B
98
+ - **Resource-Constrained Deployment**: Edge devices, mobile applications
99
+ - **Research**: Study expert specialization in MoE models
100
+ - **Fine-tuning**: Smaller base model for domain adaptation
101
+
102
+ *Note: Performance may vary depending on how well the pruned experts match your specific use case.*
103
+
104
+ ## Motivation & Expert Selection
105
+
106
+ This medical domain model incorporates experts that activated highly during health and medical tasks from MMLU medical subjects. These experts specialize in clinical knowledge, anatomy, medical procedures, and health-related reasoning.
107
+
108
+ The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:
109
+
110
+ - **GPQA**: Graduate-level questions in physics, chemistry, biology (Diamond & Expert subsets)
111
+ - **MMLU/MMLU-Pro**: Comprehensive knowledge across 57+ subjects including science, medicine, law
112
+ - **SORRY-Bench**: Safety evaluation across harmful content categories
113
+ - **Tulu3**: Persona-driven instruction following with verifiable constraints
114
+ - **Polyglot-or-Not**: Multilingual factual completion tasks
115
+
116
+ By identifying experts that consistently activated for health or medicine tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 27 experts per layer.
117
+
118
+ ## Dataset & Analysis Foundation
119
+
120
+ This model is based on analysis from the **GPT-OSS-20B MoE Expert Activations dataset** available at:
121
+ 🔗 **https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations**
122
+
123
+ The dataset contains router activation patterns from OpenAI's GPT-OSS-20B model across diverse evaluation benchmarks, enabling the creation of these domain-optimized models through systematic expert pruning.
124
+
125
+ ### Pruning Methodology
126
+ Our approach involves:
127
+ 1. **Activation Analysis**: Comprehensive evaluation of expert usage patterns across domain-specific tasks
128
+ 2. **Expert Ranking**: Identification of the most frequently activated experts for target domains
129
+ 3. **Systematic Pruning**: Reduction from 32 to 27 experts while preserving router functionality
130
+ 4. **Quality Validation**: Testing to ensure maintained performance on target tasks
131
+
132
+ *This is a direct pruning approach - no additional training was performed. The model inherits all capabilities from the original GPT-OSS-20B with focused expert selection.*
133
+
134
+ ## Usage
135
+
136
+ ### CPU Inference
137
+
138
+ ```python
139
+ from transformers import AutoModelForCausalLM, AutoTokenizer
140
+ import torch
141
+
142
+ # Load the specialized model on CPU
143
+ model = AutoModelForCausalLM.from_pretrained(
144
+ "AmanPriyanshu/gpt-oss-17.9b-specialized-health_or_medicine-pruned-moe-only-27-experts",
145
+ torch_dtype=torch.bfloat16,
146
+ device_map="cpu",
147
+ trust_remote_code=True
148
+ )
149
+ tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-17.9b-specialized-health_or_medicine-pruned-moe-only-27-experts")
150
+
151
+ # Generate with the model
152
+ messages = [
153
+ {"role": "user", "content": "What are the main functions of the human heart?"}
154
+ ]
155
+
156
+ inputs = tokenizer.apply_chat_template(
157
+ messages,
158
+ add_generation_prompt=True,
159
+ return_tensors="pt",
160
+ return_dict=True,
161
+ reasoning_effort="medium"
162
+ )
163
+
164
+ # Ensure inputs are on the same device as model
165
+ inputs = {k: v.to(model.device) for k, v in inputs.items()}
166
+
167
+ outputs = model.generate(
168
+ **inputs,
169
+ max_new_tokens=512,
170
+ do_sample=True,
171
+ temperature=0.1,
172
+ top_p=0.9,
173
+ pad_token_id=tokenizer.eos_token_id,
174
+ eos_token_id=tokenizer.eos_token_id
175
+ )
176
+
177
+ # Decode only the generated part
178
+ input_length = inputs['input_ids'].shape[1]
179
+ response_tokens = outputs[0][input_length:]
180
+ response = tokenizer.decode(response_tokens, skip_special_tokens=True)
181
+ print(response)
182
+ ```
183
+
184
+ ### Apple Silicon (MPS) Inference
185
+
186
+ ```python
187
+ from transformers import AutoModelForCausalLM, AutoTokenizer
188
+ import torch
189
+
190
+ # Check MPS availability and load model
191
+ device = "mps" if torch.backends.mps.is_available() else "cpu"
192
+
193
+ model = AutoModelForCausalLM.from_pretrained(
194
+ "AmanPriyanshu/gpt-oss-17.9b-specialized-health_or_medicine-pruned-moe-only-27-experts",
195
+ torch_dtype=torch.float16, # Better MPS compatibility
196
+ device_map=device,
197
+ trust_remote_code=True,
198
+ low_cpu_mem_usage=True
199
+ )
200
+ tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-17.9b-specialized-health_or_medicine-pruned-moe-only-27-experts")
201
+
202
+ # Generate with the model
203
+ messages = [
204
+ {"role": "user", "content": "What are the main functions of the human heart?"}
205
+ ]
206
+
207
+ inputs = tokenizer.apply_chat_template(
208
+ messages,
209
+ add_generation_prompt=True,
210
+ return_tensors="pt",
211
+ return_dict=True,
212
+ reasoning_effort="medium"
213
+ )
214
+
215
+ # Move inputs to model device
216
+ inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
217
+
218
+ # Use torch.no_grad for MPS stability
219
+ with torch.no_grad():
220
+ outputs = model.generate(
221
+ **inputs,
222
+ max_new_tokens=512,
223
+ do_sample=True,
224
+ temperature=0.1,
225
+ top_p=0.9,
226
+ pad_token_id=tokenizer.eos_token_id,
227
+ eos_token_id=tokenizer.eos_token_id,
228
+ use_cache=True
229
+ )
230
+
231
+ # Decode only the generated part
232
+ input_length = inputs['input_ids'].shape[1]
233
+ response_tokens = outputs[0][input_length:]
234
+ response = tokenizer.decode(response_tokens, skip_special_tokens=True)
235
+ print(response)
236
+ ```
237
+
238
+ ### GPU Inference
239
+
240
+ For CUDA GPU inference, the models work with minimal modifications from the CPU example above. Simply change:
241
+ ```python
242
+ device_map="auto" # Will automatically use GPU if available
243
+ torch_dtype=torch.bfloat16 # or torch.float16
244
+ ```
245
+
246
+ ## Model Examples
247
+
248
+ The following examples demonstrate the model's performance on health or medicine tasks:
249
+
250
+ ### Example 1
251
+ **Question:** What are the main functions of the human heart?
252
+
253
+ **Response:**
254
+ ```
255
+ <|channel|>analysis<|message|>Need concise answer.<|end|><|start|>assistant<|channel|>final<|message|>The human heart is a muscular pump that performs three core functions:
256
+
257
+ | Function | What it does | Why it matters |
258
+ |----------|--------------|----------------|
259
+ | **Pumping blood** | Contracts and relaxes rhythmically to move blood through the circulatory system. | Delivers oxygen, nutrients, hormones, and removes waste products to every cell. |
260
+ | **Maintaining blood pressure** | Generates enough force to keep blood moving against resistance in arteries and veins. | Keeps tissues perfused and allows the body to respond to changes in activity or posture. |
261
+ | **Regulating blood flow** | Adjusts rate and force of contraction (cardiac output) and controls valve opening/closing. | Matches oxygen delivery to metabolic demand (e.g., during exercise vs rest). |
262
+
263
+ Together, these functions keep the body’s cells supplied with the substances they need and remove metabolic waste, sustaining life.<|return|>
264
+ ```
265
+
266
+ ---
267
+
268
+ ### Example 2
269
+ **Question:** Explain the difference between bacteria and viruses.
270
+
271
+ **Response:**
272
+ ```
273
+ <|channel|>analysis<|message|>Need concise explanation.<|end|><|start|>assistant<|channel|>final<|message|>**Bacteria vs. Viruses – the key differences**
274
+
275
+ | Feature | Bacteria | Viruses |
276
+ |--------|----------|---------|
277
+ | **Cellular status** | True cells – prokaryotic, with a cell membrane, cytoplasm, ribosomes, and a cell wall (often peptidoglycan). | Non‑cellular particles – no membrane, no cytoplasm, no ribosomes. |
278
+ | **Size** | 0.5–5 µm (visible under light microscope). | 20–300 nm (visible only with electron microscopy). |
279
+ | **Genetic material** | DNA or RNA, usually a single circular chromosome; some have plasmids. | DNA or RNA, single or double stranded, but never both. |
280
+ | **Reproduction** | Binary fission (autonomous, self‑replicating). | Must hijack a host cell’s machinery to replicate. |
281
+ | **Metabolism** | Can be autotrophic or heterotrophic; many can generate energy (e.g., via respiration, photosynthesis). | No metabolism of their own; rely entirely on host cell enzymes. |
282
+ | **Structure** | Cell wall, cytoplasmic membrane, ribosomes, sometimes flagella or pili. | Protein coat (capsid) surrounding the genome; some have an outer lipid envelope. |
283
+ | **Life cycle** | Can grow, divide, and form colonies. | Infect a host cell, replicate, then exit (lysis or budding). |
284
+ | **Treatment** | Antibiotics (target cell wall, protein synthesis, DNA replication, etc.). | Antivirals (target viral enzymes or entry/exit steps); antibiotics ineffective. |
285
+ | **Disease examples** | *Streptococcus pneumoniae* (pneumonia), *Escherichia coli* (UTI). | Influenza virus, HIV, SARS‑CoV‑2. |
286
+ | **Transmission** | Often via contact, food, water, vectors. | Often via aerosols, bodily fluids, or contaminated surfaces. |
287
+
288
+ **Bottom line:**
289
+ Bacteria are living, self‑sufficient cells that can grow and reproduce on their own. Viruses are obligate parasites that need a host cell to replicate; they are essentially genetic material wrapped in a protein coat and have no metabolic machinery of their own.<|return|>
290
+ ```
291
+
292
+ ---
293
+
294
+ ### Example 3
295
+ **Question:** What are the symptoms and causes of diabetes?
296
+
297
+ **Response:**
298
+ ```
299
+ <|channel|>analysis<|message|>Need to answer.<|end|><|start|>assistant<|channel|>final<|message|>**Diabetes mellitus** is a group of metabolic disorders characterized by chronic hyperglycemia (high blood sugar). The two most common types—Type 1 and Type 2—have distinct causes, but many symptoms overlap because they all stem from elevated glucose levels and impaired insulin action or production.
300
+
301
+ ---
302
+
303
+ ## 1. Symptoms
304
+
305
+ | Symptom | Why it Happens | Typical Onset |
306
+ |---------|----------------|---------------|
307
+ | **Polyuria** (frequent urination) | Kidneys excrete excess glucose, pulling water with it. | Often early, especially in Type 1. |
308
+ | **Polydipsia** (excessive thirst) | Dehydration from fluid loss via urine. | Early. |
309
+ | **Polyphagia** (increased hunger) | Cells can’t use glucose, so the body signals for more food. | Early. |
310
+ | **Weight loss** (especially in Type 1) | Body breaks down fat and muscle for energy. | Early in Type 1; later in Type 2. |
311
+ | **Fatigue / Weakness** | Energy production is impaired. | Early. |
312
+ | **Blurred vision** | Fluid shifts in the lens of the eye. | Early. |
313
+ | **Slow‑healing cuts or infections** | High glucose impairs immune function and wound healing. | Variable. |
314
+ | **Numbness or tingling in hands/feet** (neuropathy) | Chronic high glucose damages nerves. | Usually later. |
315
+ | **Darkened skin patches** (acanthosis nigricans) | Often seen in insulin resistance. | Later, especially in Type 2. |
316
+ | **Recurrent infections** (UTIs, yeast, skin) | Immune suppression. | Variable. |
317
+ | **Unexplained weight loss** (Type 2) | Less common but can occur in advanced disease. | Late. |
318
+
319
+ > **Note:** Some people, especially those with Type 2 diabetes, may have *no symptoms* for years. Routine screening is important if you have risk factors.
320
+
321
+ ---
322
+
323
+ ## 2. Causes
324
+
325
+ ### A. Type 1 Diabetes (T1D)
326
+
327
+ | Factor | Explanation |
328
+ |--------|-------------|
329
+ | **Autoimmune destruction of β‑cells** | The immune system mistakenly attacks insulin‑producing cells in the pancreas. |
330
+ | **Genetic predisposition** | Certain HLA genes increase risk. |
331
+ | **Environmental triggers** |
332
+ ```
333
+
334
+ ---
335
+
336
+ ## Citation
337
+
338
+ If you use this model in your research, please cite:
339
+
340
+ ```bibtex
341
+ @misc{priyanshu2025gptoss,
342
+ title={{GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models}},
343
+ author={Priyanshu, Aman and Vijay, Supriti},
344
+ year={2025},
345
+ howpublished={\url{https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/}},
346
+ note={Interactive analysis tool for expert activation patterns in MoE architectures}
347
+ }
348
+ ```
349
+
350
+ ## References & Resources
351
+
352
+ - **Original Model**: [OpenAI GPT-OSS Model Card](https://openai.com/index/introducing-gpt-oss/)
353
+ - **Model Hub**: [GPT-OSS-20B on Hugging Face](https://huggingface.co/openai/gpt-oss-20b)
354
+ - **Expert Analysis Dataset**: [GPT-OSS-20B MoE Expert Activations](https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations)
355
+ - **Project Page**: [GPT-OSS MoE Expert Fingerprinting](https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/)
356
+ - **GitHub Repository**: [OpenAI GPT-OSS](https://github.com/openai/gpt-oss)
chat_template.jinja ADDED
@@ -0,0 +1,331 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {#-
2
+ In addition to the normal inputs of `messages` and `tools`, this template also accepts the
3
+ following kwargs:
4
+ - "builtin_tools": A list, can contain "browser" and/or "python".
5
+ - "model_identity": A string that optionally describes the model identity.
6
+ - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
7
+ #}
8
+
9
+ {#- Tool Definition Rendering ============================================== #}
10
+ {%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
11
+ {%- if param_spec.type == "array" -%}
12
+ {%- if param_spec['items'] -%}
13
+ {%- if param_spec['items']['type'] == "string" -%}
14
+ {{- "string[]" }}
15
+ {%- elif param_spec['items']['type'] == "number" -%}
16
+ {{- "number[]" }}
17
+ {%- elif param_spec['items']['type'] == "integer" -%}
18
+ {{- "number[]" }}
19
+ {%- elif param_spec['items']['type'] == "boolean" -%}
20
+ {{- "boolean[]" }}
21
+ {%- else -%}
22
+ {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
23
+ {%- if inner_type == "object | object" or inner_type|length > 50 -%}
24
+ {{- "any[]" }}
25
+ {%- else -%}
26
+ {{- inner_type + "[]" }}
27
+ {%- endif -%}
28
+ {%- endif -%}
29
+ {%- if param_spec.nullable -%}
30
+ {{- " | null" }}
31
+ {%- endif -%}
32
+ {%- else -%}
33
+ {{- "any[]" }}
34
+ {%- if param_spec.nullable -%}
35
+ {{- " | null" }}
36
+ {%- endif -%}
37
+ {%- endif -%}
38
+ {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
39
+ {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
40
+ {%- if param_spec.type | length > 1 -%}
41
+ {{- param_spec.type | join(" | ") }}
42
+ {%- else -%}
43
+ {{- param_spec.type[0] }}
44
+ {%- endif -%}
45
+ {%- elif param_spec.oneOf -%}
46
+ {#- Handle oneOf schemas - check for complex unions and fallback to any #}
47
+ {%- set has_object_variants = false -%}
48
+ {%- for variant in param_spec.oneOf -%}
49
+ {%- if variant.type == "object" -%}
50
+ {%- set has_object_variants = true -%}
51
+ {%- endif -%}
52
+ {%- endfor -%}
53
+ {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
54
+ {{- "any" }}
55
+ {%- else -%}
56
+ {%- for variant in param_spec.oneOf -%}
57
+ {{- render_typescript_type(variant, required_params) -}}
58
+ {%- if variant.description %}
59
+ {{- "// " + variant.description }}
60
+ {%- endif -%}
61
+ {%- if variant.default is defined %}
62
+ {{ "// default: " + variant.default|tojson }}
63
+ {%- endif -%}
64
+ {%- if not loop.last %}
65
+ {{- " | " }}
66
+ {% endif -%}
67
+ {%- endfor -%}
68
+ {%- endif -%}
69
+ {%- elif param_spec.type == "string" -%}
70
+ {%- if param_spec.enum -%}
71
+ {{- '"' + param_spec.enum|join('" | "') + '"' -}}
72
+ {%- else -%}
73
+ {{- "string" }}
74
+ {%- if param_spec.nullable %}
75
+ {{- " | null" }}
76
+ {%- endif -%}
77
+ {%- endif -%}
78
+ {%- elif param_spec.type == "number" -%}
79
+ {{- "number" }}
80
+ {%- elif param_spec.type == "integer" -%}
81
+ {{- "number" }}
82
+ {%- elif param_spec.type == "boolean" -%}
83
+ {{- "boolean" }}
84
+
85
+ {%- elif param_spec.type == "object" -%}
86
+ {%- if param_spec.properties -%}
87
+ {{- "{\n" }}
88
+ {%- for prop_name, prop_spec in param_spec.properties.items() -%}
89
+ {{- prop_name -}}
90
+ {%- if prop_name not in (param_spec.required or []) -%}
91
+ {{- "?" }}
92
+ {%- endif -%}
93
+ {{- ": " }}
94
+ {{ render_typescript_type(prop_spec, param_spec.required or []) }}
95
+ {%- if not loop.last -%}
96
+ {{-", " }}
97
+ {%- endif -%}
98
+ {%- endfor -%}
99
+ {{- "}" }}
100
+ {%- else -%}
101
+ {{- "object" }}
102
+ {%- endif -%}
103
+ {%- else -%}
104
+ {{- "any" }}
105
+ {%- endif -%}
106
+ {%- endmacro -%}
107
+
108
+ {%- macro render_tool_namespace(namespace_name, tools) -%}
109
+ {{- "## " + namespace_name + "\n\n" }}
110
+ {{- "namespace " + namespace_name + " {\n\n" }}
111
+ {%- for tool in tools %}
112
+ {%- set tool = tool.function %}
113
+ {{- "// " + tool.description + "\n" }}
114
+ {{- "type "+ tool.name + " = " }}
115
+ {%- if tool.parameters and tool.parameters.properties %}
116
+ {{- "(_: {\n" }}
117
+ {%- for param_name, param_spec in tool.parameters.properties.items() %}
118
+ {%- if param_spec.description %}
119
+ {{- "// " + param_spec.description + "\n" }}
120
+ {%- endif %}
121
+ {{- param_name }}
122
+ {%- if param_name not in (tool.parameters.required or []) -%}
123
+ {{- "?" }}
124
+ {%- endif -%}
125
+ {{- ": " }}
126
+ {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
127
+ {%- if param_spec.default is defined -%}
128
+ {%- if param_spec.enum %}
129
+ {{- ", // default: " + param_spec.default }}
130
+ {%- elif param_spec.oneOf %}
131
+ {{- "// default: " + param_spec.default }}
132
+ {%- else %}
133
+ {{- ", // default: " + param_spec.default|tojson }}
134
+ {%- endif -%}
135
+ {%- endif -%}
136
+ {%- if not loop.last %}
137
+ {{- ",\n" }}
138
+ {%- else %}
139
+ {{- ",\n" }}
140
+ {%- endif -%}
141
+ {%- endfor %}
142
+ {{- "}) => any;\n\n" }}
143
+ {%- else -%}
144
+ {{- "() => any;\n\n" }}
145
+ {%- endif -%}
146
+ {%- endfor %}
147
+ {{- "} // namespace " + namespace_name }}
148
+ {%- endmacro -%}
149
+
150
+ {%- macro render_builtin_tools(browser_tool, python_tool) -%}
151
+ {%- if browser_tool %}
152
+ {{- "## browser\n\n" }}
153
+ {{- "// Tool for browsing.\n" }}
154
+ {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
155
+ {{- "// Cite information from the tool using the following format:\n" }}
156
+ {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
157
+ {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
158
+ {{- "// sources=web (default: web)\n" }}
159
+ {{- "namespace browser {\n\n" }}
160
+ {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
161
+ {{- "type search = (_: {\n" }}
162
+ {{- "query: string,\n" }}
163
+ {{- "topn?: number, // default: 10\n" }}
164
+ {{- "source?: string,\n" }}
165
+ {{- "}) => any;\n\n" }}
166
+ {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
167
+ {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
168
+ {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
169
+ {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
170
+ {{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
171
+ {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
172
+ {{- "type open = (_: {\n" }}
173
+ {{- "id?: number | string, // default: -1\n" }}
174
+ {{- "cursor?: number, // default: -1\n" }}
175
+ {{- "loc?: number, // default: -1\n" }}
176
+ {{- "num_lines?: number, // default: -1\n" }}
177
+ {{- "view_source?: boolean, // default: false\n" }}
178
+ {{- "source?: string,\n" }}
179
+ {{- "}) => any;\n\n" }}
180
+ {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
181
+ {{- "type find = (_: {\n" }}
182
+ {{- "pattern: string,\n" }}
183
+ {{- "cursor?: number, // default: -1\n" }}
184
+ {{- "}) => any;\n\n" }}
185
+ {{- "} // namespace browser\n\n" }}
186
+ {%- endif -%}
187
+
188
+ {%- if python_tool %}
189
+ {{- "## python\n\n" }}
190
+ {{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
191
+ {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
192
+ {%- endif -%}
193
+ {%- endmacro -%}
194
+
195
+ {#- System Message Construction ============================================ #}
196
+ {%- macro build_system_message() -%}
197
+ {%- if model_identity is not defined %}
198
+ {%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
199
+ {%- endif %}
200
+ {{- model_identity + "\n" }}
201
+ {{- "Knowledge cutoff: 2024-06\n" }}
202
+ {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
203
+ {%- if reasoning_effort is not defined %}
204
+ {%- set reasoning_effort = "medium" %}
205
+ {%- endif %}
206
+ {{- "Reasoning: " + reasoning_effort + "\n\n" }}
207
+ {%- if builtin_tools %}
208
+ {{- "# Tools\n\n" }}
209
+ {%- set available_builtin_tools = namespace(browser=false, python=false) %}
210
+ {%- for tool in builtin_tools %}
211
+ {%- if tool == "browser" %}
212
+ {%- set available_builtin_tools.browser = true %}
213
+ {%- elif tool == "python" %}
214
+ {%- set available_builtin_tools.python = true %}
215
+ {%- endif %}
216
+ {%- endfor %}
217
+ {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
218
+ {%- endif -%}
219
+ {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
220
+ {%- if tools -%}
221
+ {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
222
+ {%- endif -%}
223
+ {%- endmacro -%}
224
+
225
+ {#- Main Template Logic ================================================= #}
226
+ {#- Set defaults #}
227
+
228
+ {#- Render system message #}
229
+ {{- "<|start|>system<|message|>" }}
230
+ {{- build_system_message() }}
231
+ {{- "<|end|>" }}
232
+
233
+ {#- Extract developer message #}
234
+ {%- if messages[0].role == "developer" or messages[0].role == "system" %}
235
+ {%- set developer_message = messages[0].content %}
236
+ {%- set loop_messages = messages[1:] %}
237
+ {%- else %}
238
+ {%- set developer_message = "" %}
239
+ {%- set loop_messages = messages %}
240
+ {%- endif %}
241
+
242
+ {#- Render developer message #}
243
+ {%- if developer_message or tools %}
244
+ {{- "<|start|>developer<|message|>" }}
245
+ {%- if developer_message %}
246
+ {{- "# Instructions\n\n" }}
247
+ {{- developer_message }}
248
+ {{- "\n\n" }}
249
+ {%- endif %}
250
+ {%- if tools -%}
251
+ {{- "# Tools\n\n" }}
252
+ {{- render_tool_namespace("functions", tools) }}
253
+ {%- endif -%}
254
+ {{- "<|end|>" }}
255
+ {%- endif %}
256
+
257
+ {#- Render messages #}
258
+ {%- set last_tool_call = namespace(name=none) %}
259
+ {%- for message in loop_messages -%}
260
+ {#- At this point only assistant/user/tool messages should remain #}
261
+ {%- if message.role == 'assistant' -%}
262
+ {#- Checks to ensure the messages are being passed in the format we expect #}
263
+ {%- if "content" in message %}
264
+ {%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
265
+ {{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
266
+ {%- endif %}
267
+ {%- endif %}
268
+ {%- if "thinking" in message %}
269
+ {%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
270
+ {{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
271
+ {%- endif %}
272
+ {%- endif %}
273
+ {%- if "tool_calls" in message %}
274
+ {#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
275
+ {#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
276
+ {#- when we render CoT/analysis messages in inference. #}
277
+ {%- set future_final_message = namespace(found=false) %}
278
+ {%- for future_message in loop_messages[loop.index:] %}
279
+ {%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
280
+ {%- set future_final_message.found = true %}
281
+ {%- endif %}
282
+ {%- endfor %}
283
+ {#- We assume max 1 tool call per message, and so we infer the tool call name #}
284
+ {#- in "tool" messages from the most recent assistant tool call name #}
285
+ {%- set tool_call = message.tool_calls[0] %}
286
+ {%- if tool_call.function %}
287
+ {%- set tool_call = tool_call.function %}
288
+ {%- endif %}
289
+ {%- if message.content and message.thinking %}
290
+ {{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
291
+ {%- elif message.content and not future_final_message.found %}
292
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
293
+ {%- elif message.thinking and not future_final_message.found %}
294
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
295
+ {%- endif %}
296
+ {{- "<|start|>assistant to=" }}
297
+ {{- "functions." + tool_call.name + "<|channel|>commentary " }}
298
+ {{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
299
+ {{- tool_call.arguments|tojson }}
300
+ {{- "<|call|>" }}
301
+ {%- set last_tool_call.name = tool_call.name %}
302
+ {%- elif loop.last and not add_generation_prompt %}
303
+ {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
304
+ {#- This is a situation that should only occur in training, never in inference. #}
305
+ {%- if "thinking" in message %}
306
+ {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
307
+ {%- endif %}
308
+ {#- <|return|> indicates the end of generation, but <|end|> does not #}
309
+ {#- <|return|> should never be an input to the model, but we include it as the final token #}
310
+ {#- when training, so the model learns to emit it. #}
311
+ {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
312
+ {%- else %}
313
+ {#- CoT is dropped during all previous turns, so we never render it for inference #}
314
+ {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
315
+ {%- set last_tool_call.name = none %}
316
+ {%- endif %}
317
+ {%- elif message.role == 'tool' -%}
318
+ {%- if last_tool_call.name is none %}
319
+ {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
320
+ {%- endif %}
321
+ {{- "<|start|>functions." + last_tool_call.name }}
322
+ {{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
323
+ {%- elif message.role == 'user' -%}
324
+ {{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
325
+ {%- endif -%}
326
+ {%- endfor -%}
327
+
328
+ {#- Generation prompt #}
329
+ {%- if add_generation_prompt -%}
330
+ <|start|>assistant
331
+ {%- endif -%}
citation.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "title": "GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models",
3
+ "authors": [
4
+ "Aman Priyanshu",
5
+ "Supriti Vijay"
6
+ ],
7
+ "year": 2025,
8
+ "url": "https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/"
9
+ }
config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 201088,
3
+ "hidden_size": 2880,
4
+ "intermediate_size": 2880,
5
+ "num_hidden_layers": 24,
6
+ "num_attention_heads": 64,
7
+ "num_local_experts": 27,
8
+ "sliding_window": 128,
9
+ "num_experts_per_tok": 4,
10
+ "num_key_value_heads": 8,
11
+ "hidden_act": "silu",
12
+ "initializer_range": 0.02,
13
+ "rms_norm_eps": 1e-05,
14
+ "rope_theta": 150000,
15
+ "rope_scaling": {
16
+ "beta_fast": 32.0,
17
+ "beta_slow": 1.0,
18
+ "factor": 32.0,
19
+ "original_max_position_embeddings": 4096,
20
+ "rope_type": "yarn",
21
+ "truncate": false
22
+ },
23
+ "attention_dropout": 0.0,
24
+ "head_dim": 64,
25
+ "layer_types": [
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "full_attention"
50
+ ],
51
+ "attention_bias": true,
52
+ "max_position_embeddings": 131072,
53
+ "router_aux_loss_coef": 0.9,
54
+ "output_router_logits": false,
55
+ "use_cache": true,
56
+ "return_dict": true,
57
+ "output_hidden_states": false,
58
+ "torchscript": false,
59
+ "torch_dtype": null,
60
+ "pruned_heads": {},
61
+ "tie_word_embeddings": false,
62
+ "chunk_size_feed_forward": 0,
63
+ "is_encoder_decoder": false,
64
+ "is_decoder": false,
65
+ "cross_attention_hidden_size": null,
66
+ "add_cross_attention": false,
67
+ "tie_encoder_decoder": false,
68
+ "architectures": [
69
+ "GptOssForCausalLM"
70
+ ],
71
+ "finetuning_task": null,
72
+ "id2label": {
73
+ "0": "LABEL_0",
74
+ "1": "LABEL_1"
75
+ },
76
+ "label2id": {
77
+ "LABEL_0": 0,
78
+ "LABEL_1": 1
79
+ },
80
+ "task_specific_params": null,
81
+ "problem_type": null,
82
+ "tokenizer_class": null,
83
+ "prefix": null,
84
+ "bos_token_id": null,
85
+ "pad_token_id": 199999,
86
+ "eos_token_id": 200002,
87
+ "sep_token_id": null,
88
+ "decoder_start_token_id": null,
89
+ "max_length": 20,
90
+ "min_length": 0,
91
+ "do_sample": false,
92
+ "early_stopping": false,
93
+ "num_beams": 1,
94
+ "num_beam_groups": 1,
95
+ "diversity_penalty": 0.0,
96
+ "temperature": 1.0,
97
+ "top_k": 50,
98
+ "top_p": 1.0,
99
+ "typical_p": 1.0,
100
+ "repetition_penalty": 1.0,
101
+ "length_penalty": 1.0,
102
+ "no_repeat_ngram_size": 0,
103
+ "encoder_no_repeat_ngram_size": 0,
104
+ "bad_words_ids": null,
105
+ "num_return_sequences": 1,
106
+ "output_scores": false,
107
+ "return_dict_in_generate": false,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "remove_invalid_values": false,
111
+ "exponential_decay_length_penalty": null,
112
+ "suppress_tokens": null,
113
+ "begin_suppress_tokens": null,
114
+ "_name_or_path": "openai/gpt-oss-20b",
115
+ "transformers_version": "4.55.0",
116
+ "experts_per_token": 4,
117
+ "initial_context_length": 4096,
118
+ "model_type": "gpt_oss",
119
+ "swiglu_limit": 7.0,
120
+ "tf_legacy_loss": false,
121
+ "use_bfloat16": false,
122
+ "output_attentions": false
123
+ }
expert_mapping.json ADDED
@@ -0,0 +1,698 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": {
3
+ "9": 0,
4
+ "3": 1,
5
+ "11": 2,
6
+ "22": 3,
7
+ "17": 4,
8
+ "16": 5,
9
+ "0": 6,
10
+ "31": 7,
11
+ "24": 8,
12
+ "1": 9,
13
+ "2": 10,
14
+ "6": 11,
15
+ "5": 12,
16
+ "30": 13,
17
+ "23": 14,
18
+ "28": 15,
19
+ "25": 16,
20
+ "7": 17,
21
+ "21": 18,
22
+ "19": 19,
23
+ "10": 20,
24
+ "13": 21,
25
+ "4": 22,
26
+ "27": 23,
27
+ "15": 24,
28
+ "8": 25,
29
+ "26": 26
30
+ },
31
+ "1": {
32
+ "25": 0,
33
+ "28": 1,
34
+ "0": 2,
35
+ "18": 3,
36
+ "27": 4,
37
+ "6": 5,
38
+ "1": 6,
39
+ "17": 7,
40
+ "12": 8,
41
+ "29": 9,
42
+ "13": 10,
43
+ "10": 11,
44
+ "16": 12,
45
+ "11": 13,
46
+ "26": 14,
47
+ "20": 15,
48
+ "23": 16,
49
+ "3": 17,
50
+ "7": 18,
51
+ "15": 19,
52
+ "24": 20,
53
+ "30": 21,
54
+ "21": 22,
55
+ "31": 23,
56
+ "2": 24,
57
+ "22": 25,
58
+ "5": 26
59
+ },
60
+ "2": {
61
+ "31": 0,
62
+ "10": 1,
63
+ "21": 2,
64
+ "29": 3,
65
+ "8": 4,
66
+ "22": 5,
67
+ "5": 6,
68
+ "0": 7,
69
+ "28": 8,
70
+ "27": 9,
71
+ "20": 10,
72
+ "3": 11,
73
+ "6": 12,
74
+ "30": 13,
75
+ "16": 14,
76
+ "15": 15,
77
+ "4": 16,
78
+ "26": 17,
79
+ "7": 18,
80
+ "24": 19,
81
+ "25": 20,
82
+ "14": 21,
83
+ "9": 22,
84
+ "23": 23,
85
+ "18": 24,
86
+ "19": 25,
87
+ "17": 26
88
+ },
89
+ "3": {
90
+ "27": 0,
91
+ "7": 1,
92
+ "31": 2,
93
+ "0": 3,
94
+ "16": 4,
95
+ "23": 5,
96
+ "19": 6,
97
+ "2": 7,
98
+ "21": 8,
99
+ "11": 9,
100
+ "1": 10,
101
+ "25": 11,
102
+ "9": 12,
103
+ "12": 13,
104
+ "22": 14,
105
+ "3": 15,
106
+ "24": 16,
107
+ "29": 17,
108
+ "5": 18,
109
+ "13": 19,
110
+ "20": 20,
111
+ "10": 21,
112
+ "26": 22,
113
+ "28": 23,
114
+ "6": 24,
115
+ "18": 25,
116
+ "15": 26
117
+ },
118
+ "4": {
119
+ "6": 0,
120
+ "7": 1,
121
+ "15": 2,
122
+ "18": 3,
123
+ "24": 4,
124
+ "20": 5,
125
+ "17": 6,
126
+ "23": 7,
127
+ "14": 8,
128
+ "30": 9,
129
+ "31": 10,
130
+ "10": 11,
131
+ "22": 12,
132
+ "12": 13,
133
+ "27": 14,
134
+ "13": 15,
135
+ "25": 16,
136
+ "8": 17,
137
+ "0": 18,
138
+ "4": 19,
139
+ "19": 20,
140
+ "29": 21,
141
+ "11": 22,
142
+ "3": 23,
143
+ "21": 24,
144
+ "26": 25,
145
+ "16": 26
146
+ },
147
+ "5": {
148
+ "6": 0,
149
+ "0": 1,
150
+ "10": 2,
151
+ "31": 3,
152
+ "14": 4,
153
+ "15": 5,
154
+ "24": 6,
155
+ "2": 7,
156
+ "18": 8,
157
+ "17": 9,
158
+ "27": 10,
159
+ "1": 11,
160
+ "8": 12,
161
+ "23": 13,
162
+ "30": 14,
163
+ "26": 15,
164
+ "21": 16,
165
+ "4": 17,
166
+ "22": 18,
167
+ "11": 19,
168
+ "19": 20,
169
+ "25": 21,
170
+ "20": 22,
171
+ "28": 23,
172
+ "13": 24,
173
+ "12": 25,
174
+ "16": 26
175
+ },
176
+ "6": {
177
+ "9": 0,
178
+ "2": 1,
179
+ "7": 2,
180
+ "10": 3,
181
+ "5": 4,
182
+ "3": 5,
183
+ "16": 6,
184
+ "30": 7,
185
+ "15": 8,
186
+ "20": 9,
187
+ "31": 10,
188
+ "11": 11,
189
+ "4": 12,
190
+ "14": 13,
191
+ "18": 14,
192
+ "21": 15,
193
+ "27": 16,
194
+ "24": 17,
195
+ "8": 18,
196
+ "28": 19,
197
+ "26": 20,
198
+ "6": 21,
199
+ "25": 22,
200
+ "29": 23,
201
+ "12": 24,
202
+ "23": 25,
203
+ "19": 26
204
+ },
205
+ "7": {
206
+ "5": 0,
207
+ "1": 1,
208
+ "10": 2,
209
+ "30": 3,
210
+ "13": 4,
211
+ "4": 5,
212
+ "29": 6,
213
+ "14": 7,
214
+ "24": 8,
215
+ "21": 9,
216
+ "15": 10,
217
+ "17": 11,
218
+ "19": 12,
219
+ "11": 13,
220
+ "28": 14,
221
+ "20": 15,
222
+ "3": 16,
223
+ "16": 17,
224
+ "23": 18,
225
+ "0": 19,
226
+ "9": 20,
227
+ "6": 21,
228
+ "26": 22,
229
+ "7": 23,
230
+ "18": 24,
231
+ "12": 25,
232
+ "25": 26
233
+ },
234
+ "8": {
235
+ "24": 0,
236
+ "20": 1,
237
+ "4": 2,
238
+ "17": 3,
239
+ "30": 4,
240
+ "31": 5,
241
+ "5": 6,
242
+ "0": 7,
243
+ "6": 8,
244
+ "13": 9,
245
+ "23": 10,
246
+ "19": 11,
247
+ "9": 12,
248
+ "16": 13,
249
+ "26": 14,
250
+ "10": 15,
251
+ "8": 16,
252
+ "28": 17,
253
+ "3": 18,
254
+ "2": 19,
255
+ "7": 20,
256
+ "21": 21,
257
+ "1": 22,
258
+ "25": 23,
259
+ "18": 24,
260
+ "11": 25,
261
+ "12": 26
262
+ },
263
+ "9": {
264
+ "8": 0,
265
+ "19": 1,
266
+ "15": 2,
267
+ "30": 3,
268
+ "14": 4,
269
+ "16": 5,
270
+ "1": 6,
271
+ "13": 7,
272
+ "21": 8,
273
+ "23": 9,
274
+ "5": 10,
275
+ "4": 11,
276
+ "22": 12,
277
+ "26": 13,
278
+ "18": 14,
279
+ "3": 15,
280
+ "20": 16,
281
+ "2": 17,
282
+ "27": 18,
283
+ "17": 19,
284
+ "0": 20,
285
+ "31": 21,
286
+ "24": 22,
287
+ "12": 23,
288
+ "11": 24,
289
+ "28": 25,
290
+ "7": 26
291
+ },
292
+ "10": {
293
+ "10": 0,
294
+ "7": 1,
295
+ "5": 2,
296
+ "21": 3,
297
+ "23": 4,
298
+ "24": 5,
299
+ "19": 6,
300
+ "26": 7,
301
+ "11": 8,
302
+ "18": 9,
303
+ "30": 10,
304
+ "25": 11,
305
+ "8": 12,
306
+ "20": 13,
307
+ "2": 14,
308
+ "16": 15,
309
+ "14": 16,
310
+ "15": 17,
311
+ "13": 18,
312
+ "28": 19,
313
+ "29": 20,
314
+ "9": 21,
315
+ "0": 22,
316
+ "12": 23,
317
+ "31": 24,
318
+ "6": 25,
319
+ "22": 26
320
+ },
321
+ "11": {
322
+ "30": 0,
323
+ "9": 1,
324
+ "27": 2,
325
+ "23": 3,
326
+ "11": 4,
327
+ "7": 5,
328
+ "20": 6,
329
+ "25": 7,
330
+ "15": 8,
331
+ "21": 9,
332
+ "4": 10,
333
+ "24": 11,
334
+ "17": 12,
335
+ "13": 13,
336
+ "18": 14,
337
+ "22": 15,
338
+ "12": 16,
339
+ "5": 17,
340
+ "26": 18,
341
+ "3": 19,
342
+ "16": 20,
343
+ "6": 21,
344
+ "14": 22,
345
+ "10": 23,
346
+ "2": 24,
347
+ "8": 25,
348
+ "0": 26
349
+ },
350
+ "12": {
351
+ "23": 0,
352
+ "3": 1,
353
+ "14": 2,
354
+ "28": 3,
355
+ "21": 4,
356
+ "24": 5,
357
+ "1": 6,
358
+ "25": 7,
359
+ "31": 8,
360
+ "6": 9,
361
+ "8": 10,
362
+ "12": 11,
363
+ "13": 12,
364
+ "30": 13,
365
+ "18": 14,
366
+ "7": 15,
367
+ "26": 16,
368
+ "19": 17,
369
+ "15": 18,
370
+ "17": 19,
371
+ "29": 20,
372
+ "11": 21,
373
+ "9": 22,
374
+ "10": 23,
375
+ "2": 24,
376
+ "0": 25,
377
+ "5": 26
378
+ },
379
+ "13": {
380
+ "21": 0,
381
+ "9": 1,
382
+ "0": 2,
383
+ "11": 3,
384
+ "1": 4,
385
+ "24": 5,
386
+ "19": 6,
387
+ "3": 7,
388
+ "16": 8,
389
+ "5": 9,
390
+ "30": 10,
391
+ "15": 11,
392
+ "10": 12,
393
+ "4": 13,
394
+ "20": 14,
395
+ "12": 15,
396
+ "8": 16,
397
+ "14": 17,
398
+ "28": 18,
399
+ "7": 19,
400
+ "2": 20,
401
+ "25": 21,
402
+ "27": 22,
403
+ "17": 23,
404
+ "13": 24,
405
+ "29": 25,
406
+ "22": 26
407
+ },
408
+ "14": {
409
+ "9": 0,
410
+ "18": 1,
411
+ "0": 2,
412
+ "6": 3,
413
+ "21": 4,
414
+ "4": 5,
415
+ "26": 6,
416
+ "1": 7,
417
+ "24": 8,
418
+ "31": 9,
419
+ "29": 10,
420
+ "3": 11,
421
+ "12": 12,
422
+ "11": 13,
423
+ "27": 14,
424
+ "7": 15,
425
+ "13": 16,
426
+ "10": 17,
427
+ "17": 18,
428
+ "22": 19,
429
+ "25": 20,
430
+ "23": 21,
431
+ "28": 22,
432
+ "15": 23,
433
+ "16": 24,
434
+ "8": 25,
435
+ "20": 26
436
+ },
437
+ "15": {
438
+ "13": 0,
439
+ "18": 1,
440
+ "31": 2,
441
+ "26": 3,
442
+ "9": 4,
443
+ "3": 5,
444
+ "28": 6,
445
+ "2": 7,
446
+ "29": 8,
447
+ "25": 9,
448
+ "10": 10,
449
+ "19": 11,
450
+ "4": 12,
451
+ "0": 13,
452
+ "22": 14,
453
+ "8": 15,
454
+ "7": 16,
455
+ "6": 17,
456
+ "27": 18,
457
+ "21": 19,
458
+ "14": 20,
459
+ "12": 21,
460
+ "1": 22,
461
+ "30": 23,
462
+ "23": 24,
463
+ "24": 25,
464
+ "17": 26
465
+ },
466
+ "16": {
467
+ "31": 0,
468
+ "24": 1,
469
+ "30": 2,
470
+ "11": 3,
471
+ "15": 4,
472
+ "4": 5,
473
+ "5": 6,
474
+ "0": 7,
475
+ "21": 8,
476
+ "18": 9,
477
+ "10": 10,
478
+ "20": 11,
479
+ "2": 12,
480
+ "9": 13,
481
+ "17": 14,
482
+ "1": 15,
483
+ "14": 16,
484
+ "22": 17,
485
+ "12": 18,
486
+ "26": 19,
487
+ "3": 20,
488
+ "29": 21,
489
+ "27": 22,
490
+ "28": 23,
491
+ "13": 24,
492
+ "7": 25,
493
+ "19": 26
494
+ },
495
+ "17": {
496
+ "14": 0,
497
+ "30": 1,
498
+ "5": 2,
499
+ "17": 3,
500
+ "4": 4,
501
+ "7": 5,
502
+ "11": 6,
503
+ "28": 7,
504
+ "25": 8,
505
+ "8": 9,
506
+ "12": 10,
507
+ "13": 11,
508
+ "19": 12,
509
+ "2": 13,
510
+ "16": 14,
511
+ "24": 15,
512
+ "21": 16,
513
+ "0": 17,
514
+ "26": 18,
515
+ "22": 19,
516
+ "10": 20,
517
+ "27": 21,
518
+ "23": 22,
519
+ "15": 23,
520
+ "3": 24,
521
+ "31": 25,
522
+ "6": 26
523
+ },
524
+ "18": {
525
+ "1": 0,
526
+ "24": 1,
527
+ "18": 2,
528
+ "14": 3,
529
+ "15": 4,
530
+ "20": 5,
531
+ "27": 6,
532
+ "9": 7,
533
+ "23": 8,
534
+ "26": 9,
535
+ "7": 10,
536
+ "2": 11,
537
+ "16": 12,
538
+ "13": 13,
539
+ "21": 14,
540
+ "31": 15,
541
+ "6": 16,
542
+ "19": 17,
543
+ "12": 18,
544
+ "0": 19,
545
+ "29": 20,
546
+ "30": 21,
547
+ "5": 22,
548
+ "11": 23,
549
+ "10": 24,
550
+ "4": 25,
551
+ "17": 26
552
+ },
553
+ "19": {
554
+ "3": 0,
555
+ "6": 1,
556
+ "19": 2,
557
+ "23": 3,
558
+ "29": 4,
559
+ "7": 5,
560
+ "16": 6,
561
+ "31": 7,
562
+ "13": 8,
563
+ "0": 9,
564
+ "22": 10,
565
+ "17": 11,
566
+ "12": 12,
567
+ "2": 13,
568
+ "15": 14,
569
+ "20": 15,
570
+ "9": 16,
571
+ "10": 17,
572
+ "25": 18,
573
+ "11": 19,
574
+ "24": 20,
575
+ "18": 21,
576
+ "28": 22,
577
+ "4": 23,
578
+ "14": 24,
579
+ "21": 25,
580
+ "30": 26
581
+ },
582
+ "20": {
583
+ "24": 0,
584
+ "22": 1,
585
+ "31": 2,
586
+ "16": 3,
587
+ "30": 4,
588
+ "11": 5,
589
+ "21": 6,
590
+ "4": 7,
591
+ "12": 8,
592
+ "0": 9,
593
+ "25": 10,
594
+ "13": 11,
595
+ "7": 12,
596
+ "5": 13,
597
+ "23": 14,
598
+ "10": 15,
599
+ "6": 16,
600
+ "26": 17,
601
+ "20": 18,
602
+ "15": 19,
603
+ "1": 20,
604
+ "2": 21,
605
+ "8": 22,
606
+ "19": 23,
607
+ "28": 24,
608
+ "9": 25,
609
+ "29": 26
610
+ },
611
+ "21": {
612
+ "9": 0,
613
+ "3": 1,
614
+ "13": 2,
615
+ "27": 3,
616
+ "21": 4,
617
+ "31": 5,
618
+ "6": 6,
619
+ "2": 7,
620
+ "1": 8,
621
+ "30": 9,
622
+ "20": 10,
623
+ "18": 11,
624
+ "14": 12,
625
+ "10": 13,
626
+ "7": 14,
627
+ "23": 15,
628
+ "29": 16,
629
+ "11": 17,
630
+ "4": 18,
631
+ "8": 19,
632
+ "24": 20,
633
+ "28": 21,
634
+ "19": 22,
635
+ "25": 23,
636
+ "26": 24,
637
+ "16": 25,
638
+ "15": 26
639
+ },
640
+ "22": {
641
+ "25": 0,
642
+ "31": 1,
643
+ "16": 2,
644
+ "14": 3,
645
+ "8": 4,
646
+ "18": 5,
647
+ "20": 6,
648
+ "22": 7,
649
+ "15": 8,
650
+ "4": 9,
651
+ "13": 10,
652
+ "0": 11,
653
+ "26": 12,
654
+ "27": 13,
655
+ "23": 14,
656
+ "7": 15,
657
+ "19": 16,
658
+ "21": 17,
659
+ "5": 18,
660
+ "17": 19,
661
+ "11": 20,
662
+ "29": 21,
663
+ "1": 22,
664
+ "2": 23,
665
+ "6": 24,
666
+ "24": 25,
667
+ "28": 26
668
+ },
669
+ "23": {
670
+ "31": 0,
671
+ "10": 1,
672
+ "18": 2,
673
+ "4": 3,
674
+ "16": 4,
675
+ "17": 5,
676
+ "0": 6,
677
+ "22": 7,
678
+ "28": 8,
679
+ "8": 9,
680
+ "3": 10,
681
+ "14": 11,
682
+ "21": 12,
683
+ "19": 13,
684
+ "25": 14,
685
+ "13": 15,
686
+ "27": 16,
687
+ "20": 17,
688
+ "24": 18,
689
+ "23": 19,
690
+ "7": 20,
691
+ "6": 21,
692
+ "2": 22,
693
+ "26": 23,
694
+ "29": 24,
695
+ "30": 25,
696
+ "9": 26
697
+ }
698
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 199998,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 200002,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.55.0"
10
+ }
model-00001-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0cda58922d9184c2a423cd95cb312d32ae21b4560835e802cecf0b5f3a1be2b
3
+ size 1211524102
model-00002-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0164401d60ff51af7da7524f6a893204bee8029d839cc19e7e65697dba39a6f3
3
+ size 1397428686
model-00003-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:781fe6a0f2c0628e151ff053e618bb4b24cfab004de5310a2261187abba8ee1a
3
+ size 1397428686
model-00004-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451b93250b27eba5a9791a3b6879e3692c925a2525be74c458e71e0380c0f6a9
3
+ size 1397428686
model-00005-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f5536594d541c652129d2371b708732bd89bc6931134d155f398f93e37ca849
3
+ size 1397428686
model-00006-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4264840a23f56537050152cbc4ff6dc594164d8ddf386207726a5e621c61722d
3
+ size 1397428686
model-00007-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ccfd5fc2b41613c632dab6876e40cd9775f029282648aff8b40b9fcaa798e0
3
+ size 1397428686
model-00008-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b60cc1c21620de63de6f36f3e72396c3c5d355901cc0ada184d200137459953d
3
+ size 1397428686
model-00009-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a248dd434488311084714cf0d020142a51b86a55333b24797ccf8b7fb2f76166
3
+ size 1397428686
model-00010-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a968deb779fc79172e58fd3695bfe2e2b3763012ebcf7e79a8bb0e371a3ca94
3
+ size 1397428686
model-00011-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1af3c0d7e74db89499dcb06cb29853c6f56b37d9eaf4c4dddf0b3f6c383642e
3
+ size 1397428638
model-00012-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6469af5dc5a3ad0bf86f55725314c590926474d2d4b1e11594a7b6fa63b8089
3
+ size 1397428702
model-00013-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a2eac2f79efc0d676a5b8ef73e781206ab96cad6353e1c3b874c4c98a1dde5
3
+ size 1397428702
model-00014-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b2eb020118f62cf1ed7c127e7f425d2d6246c6433197566bbf6b248bc8e26d
3
+ size 1397428702
model-00015-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:665670cc83e8f9ab130a4c73add12560241a428b37fde0362673b671530a558e
3
+ size 1397428702
model-00016-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d7b4fe03bcd8fd71281c310bd4f9b8025758e02fc3fa3bca225ca2b52428e35
3
+ size 1397428702
model-00017-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7ebb75db17efe7098bf29c9cace0646b1c4bc81cd29205215fce1be9ebe54d
3
+ size 1397428702
model-00018-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce46c20cc03f4a7479407d2b7a21823c0277a2df4aab4a164eaf187fab1ca8c
3
+ size 1397428702
model-00019-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:290755ae4aa8b3126cd8b1bd55da365645f6e3910132291c9984ff54cb595abe
3
+ size 1397428702
model-00020-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad9df456e94fff02aa648ee043cc30721f7ededb8a8d985e50ff0bbe103e635
3
+ size 1397428702
model-00021-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d2b52c761904af7fbe567505230f059a9d52b2bb41a589a3268ca52513e79a8
3
+ size 1397428702
model-00022-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b805c2c276b511cadcfa9475d9b7444d04422189fa261755c33c20bc8105182a
3
+ size 1397428702
model-00023-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9daefa5193c8af3468854648c86f263ff87df4064278f0a83b1ae1d6181ef15b
3
+ size 1397428702
model-00024-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7e864e0a1c08e0968c1a9f4f92e120e8d34d730ad5688b1f3b37279cc573c6
3
+ size 1397428702
model-00025-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83194edd8853ec3c4a967cd0ecc9f8a04ef57c1c09c3fc48a0a8e643c453edc8
3
+ size 1344177464
model-00026-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08e257de1fa16cf80c8a36ca29c5974fc999f0dc7ada1468bfd0be18151af482
3
+ size 1158267008
model.safetensors.index.json ADDED
@@ -0,0 +1,419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 17927390664,
4
+ "total_size": 35854781328
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00026-of-00026.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00026.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00026.safetensors",
10
+ "model.layers.0.mlp.experts.down_proj": "model-00002-of-00026.safetensors",
11
+ "model.layers.0.mlp.experts.down_proj_bias": "model-00002-of-00026.safetensors",
12
+ "model.layers.0.mlp.experts.gate_up_proj": "model-00002-of-00026.safetensors",
13
+ "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00002-of-00026.safetensors",
14
+ "model.layers.0.mlp.router.bias": "model-00001-of-00026.safetensors",
15
+ "model.layers.0.mlp.router.weight": "model-00001-of-00026.safetensors",
16
+ "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00026.safetensors",
17
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00026.safetensors",
18
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00026.safetensors",
19
+ "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00026.safetensors",
20
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00026.safetensors",
21
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00026.safetensors",
22
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00026.safetensors",
23
+ "model.layers.0.self_attn.sinks": "model-00001-of-00026.safetensors",
24
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00026.safetensors",
25
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00026.safetensors",
26
+ "model.layers.1.input_layernorm.weight": "model-00003-of-00026.safetensors",
27
+ "model.layers.1.mlp.experts.down_proj": "model-00003-of-00026.safetensors",
28
+ "model.layers.1.mlp.experts.down_proj_bias": "model-00003-of-00026.safetensors",
29
+ "model.layers.1.mlp.experts.gate_up_proj": "model-00003-of-00026.safetensors",
30
+ "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00003-of-00026.safetensors",
31
+ "model.layers.1.mlp.router.bias": "model-00002-of-00026.safetensors",
32
+ "model.layers.1.mlp.router.weight": "model-00002-of-00026.safetensors",
33
+ "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00026.safetensors",
34
+ "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00026.safetensors",
35
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00026.safetensors",
36
+ "model.layers.1.self_attn.o_proj.bias": "model-00002-of-00026.safetensors",
37
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00026.safetensors",
38
+ "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00026.safetensors",
39
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00026.safetensors",
40
+ "model.layers.1.self_attn.sinks": "model-00002-of-00026.safetensors",
41
+ "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00026.safetensors",
42
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00026.safetensors",
43
+ "model.layers.10.input_layernorm.weight": "model-00012-of-00026.safetensors",
44
+ "model.layers.10.mlp.experts.down_proj": "model-00012-of-00026.safetensors",
45
+ "model.layers.10.mlp.experts.down_proj_bias": "model-00012-of-00026.safetensors",
46
+ "model.layers.10.mlp.experts.gate_up_proj": "model-00012-of-00026.safetensors",
47
+ "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00012-of-00026.safetensors",
48
+ "model.layers.10.mlp.router.bias": "model-00011-of-00026.safetensors",
49
+ "model.layers.10.mlp.router.weight": "model-00011-of-00026.safetensors",
50
+ "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00026.safetensors",
51
+ "model.layers.10.self_attn.k_proj.bias": "model-00011-of-00026.safetensors",
52
+ "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00026.safetensors",
53
+ "model.layers.10.self_attn.o_proj.bias": "model-00011-of-00026.safetensors",
54
+ "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00026.safetensors",
55
+ "model.layers.10.self_attn.q_proj.bias": "model-00011-of-00026.safetensors",
56
+ "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00026.safetensors",
57
+ "model.layers.10.self_attn.sinks": "model-00011-of-00026.safetensors",
58
+ "model.layers.10.self_attn.v_proj.bias": "model-00011-of-00026.safetensors",
59
+ "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00026.safetensors",
60
+ "model.layers.11.input_layernorm.weight": "model-00013-of-00026.safetensors",
61
+ "model.layers.11.mlp.experts.down_proj": "model-00013-of-00026.safetensors",
62
+ "model.layers.11.mlp.experts.down_proj_bias": "model-00013-of-00026.safetensors",
63
+ "model.layers.11.mlp.experts.gate_up_proj": "model-00013-of-00026.safetensors",
64
+ "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00013-of-00026.safetensors",
65
+ "model.layers.11.mlp.router.bias": "model-00012-of-00026.safetensors",
66
+ "model.layers.11.mlp.router.weight": "model-00012-of-00026.safetensors",
67
+ "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
68
+ "model.layers.11.self_attn.k_proj.bias": "model-00012-of-00026.safetensors",
69
+ "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00026.safetensors",
70
+ "model.layers.11.self_attn.o_proj.bias": "model-00012-of-00026.safetensors",
71
+ "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00026.safetensors",
72
+ "model.layers.11.self_attn.q_proj.bias": "model-00012-of-00026.safetensors",
73
+ "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00026.safetensors",
74
+ "model.layers.11.self_attn.sinks": "model-00012-of-00026.safetensors",
75
+ "model.layers.11.self_attn.v_proj.bias": "model-00012-of-00026.safetensors",
76
+ "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00026.safetensors",
77
+ "model.layers.12.input_layernorm.weight": "model-00014-of-00026.safetensors",
78
+ "model.layers.12.mlp.experts.down_proj": "model-00014-of-00026.safetensors",
79
+ "model.layers.12.mlp.experts.down_proj_bias": "model-00014-of-00026.safetensors",
80
+ "model.layers.12.mlp.experts.gate_up_proj": "model-00014-of-00026.safetensors",
81
+ "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00014-of-00026.safetensors",
82
+ "model.layers.12.mlp.router.bias": "model-00013-of-00026.safetensors",
83
+ "model.layers.12.mlp.router.weight": "model-00013-of-00026.safetensors",
84
+ "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00026.safetensors",
85
+ "model.layers.12.self_attn.k_proj.bias": "model-00013-of-00026.safetensors",
86
+ "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00026.safetensors",
87
+ "model.layers.12.self_attn.o_proj.bias": "model-00013-of-00026.safetensors",
88
+ "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00026.safetensors",
89
+ "model.layers.12.self_attn.q_proj.bias": "model-00013-of-00026.safetensors",
90
+ "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00026.safetensors",
91
+ "model.layers.12.self_attn.sinks": "model-00013-of-00026.safetensors",
92
+ "model.layers.12.self_attn.v_proj.bias": "model-00013-of-00026.safetensors",
93
+ "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00026.safetensors",
94
+ "model.layers.13.input_layernorm.weight": "model-00015-of-00026.safetensors",
95
+ "model.layers.13.mlp.experts.down_proj": "model-00015-of-00026.safetensors",
96
+ "model.layers.13.mlp.experts.down_proj_bias": "model-00015-of-00026.safetensors",
97
+ "model.layers.13.mlp.experts.gate_up_proj": "model-00015-of-00026.safetensors",
98
+ "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00015-of-00026.safetensors",
99
+ "model.layers.13.mlp.router.bias": "model-00014-of-00026.safetensors",
100
+ "model.layers.13.mlp.router.weight": "model-00014-of-00026.safetensors",
101
+ "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
102
+ "model.layers.13.self_attn.k_proj.bias": "model-00014-of-00026.safetensors",
103
+ "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00026.safetensors",
104
+ "model.layers.13.self_attn.o_proj.bias": "model-00014-of-00026.safetensors",
105
+ "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00026.safetensors",
106
+ "model.layers.13.self_attn.q_proj.bias": "model-00014-of-00026.safetensors",
107
+ "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00026.safetensors",
108
+ "model.layers.13.self_attn.sinks": "model-00014-of-00026.safetensors",
109
+ "model.layers.13.self_attn.v_proj.bias": "model-00014-of-00026.safetensors",
110
+ "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00026.safetensors",
111
+ "model.layers.14.input_layernorm.weight": "model-00016-of-00026.safetensors",
112
+ "model.layers.14.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
113
+ "model.layers.14.mlp.experts.down_proj_bias": "model-00016-of-00026.safetensors",
114
+ "model.layers.14.mlp.experts.gate_up_proj": "model-00016-of-00026.safetensors",
115
+ "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00016-of-00026.safetensors",
116
+ "model.layers.14.mlp.router.bias": "model-00015-of-00026.safetensors",
117
+ "model.layers.14.mlp.router.weight": "model-00015-of-00026.safetensors",
118
+ "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00026.safetensors",
119
+ "model.layers.14.self_attn.k_proj.bias": "model-00015-of-00026.safetensors",
120
+ "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00026.safetensors",
121
+ "model.layers.14.self_attn.o_proj.bias": "model-00015-of-00026.safetensors",
122
+ "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00026.safetensors",
123
+ "model.layers.14.self_attn.q_proj.bias": "model-00015-of-00026.safetensors",
124
+ "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00026.safetensors",
125
+ "model.layers.14.self_attn.sinks": "model-00015-of-00026.safetensors",
126
+ "model.layers.14.self_attn.v_proj.bias": "model-00015-of-00026.safetensors",
127
+ "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00026.safetensors",
128
+ "model.layers.15.input_layernorm.weight": "model-00017-of-00026.safetensors",
129
+ "model.layers.15.mlp.experts.down_proj": "model-00017-of-00026.safetensors",
130
+ "model.layers.15.mlp.experts.down_proj_bias": "model-00017-of-00026.safetensors",
131
+ "model.layers.15.mlp.experts.gate_up_proj": "model-00017-of-00026.safetensors",
132
+ "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00017-of-00026.safetensors",
133
+ "model.layers.15.mlp.router.bias": "model-00016-of-00026.safetensors",
134
+ "model.layers.15.mlp.router.weight": "model-00016-of-00026.safetensors",
135
+ "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
136
+ "model.layers.15.self_attn.k_proj.bias": "model-00016-of-00026.safetensors",
137
+ "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00026.safetensors",
138
+ "model.layers.15.self_attn.o_proj.bias": "model-00016-of-00026.safetensors",
139
+ "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00026.safetensors",
140
+ "model.layers.15.self_attn.q_proj.bias": "model-00016-of-00026.safetensors",
141
+ "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00026.safetensors",
142
+ "model.layers.15.self_attn.sinks": "model-00016-of-00026.safetensors",
143
+ "model.layers.15.self_attn.v_proj.bias": "model-00016-of-00026.safetensors",
144
+ "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00026.safetensors",
145
+ "model.layers.16.input_layernorm.weight": "model-00018-of-00026.safetensors",
146
+ "model.layers.16.mlp.experts.down_proj": "model-00018-of-00026.safetensors",
147
+ "model.layers.16.mlp.experts.down_proj_bias": "model-00018-of-00026.safetensors",
148
+ "model.layers.16.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
149
+ "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00018-of-00026.safetensors",
150
+ "model.layers.16.mlp.router.bias": "model-00017-of-00026.safetensors",
151
+ "model.layers.16.mlp.router.weight": "model-00017-of-00026.safetensors",
152
+ "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00026.safetensors",
153
+ "model.layers.16.self_attn.k_proj.bias": "model-00017-of-00026.safetensors",
154
+ "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00026.safetensors",
155
+ "model.layers.16.self_attn.o_proj.bias": "model-00017-of-00026.safetensors",
156
+ "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00026.safetensors",
157
+ "model.layers.16.self_attn.q_proj.bias": "model-00017-of-00026.safetensors",
158
+ "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00026.safetensors",
159
+ "model.layers.16.self_attn.sinks": "model-00017-of-00026.safetensors",
160
+ "model.layers.16.self_attn.v_proj.bias": "model-00017-of-00026.safetensors",
161
+ "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00026.safetensors",
162
+ "model.layers.17.input_layernorm.weight": "model-00019-of-00026.safetensors",
163
+ "model.layers.17.mlp.experts.down_proj": "model-00019-of-00026.safetensors",
164
+ "model.layers.17.mlp.experts.down_proj_bias": "model-00019-of-00026.safetensors",
165
+ "model.layers.17.mlp.experts.gate_up_proj": "model-00019-of-00026.safetensors",
166
+ "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00019-of-00026.safetensors",
167
+ "model.layers.17.mlp.router.bias": "model-00018-of-00026.safetensors",
168
+ "model.layers.17.mlp.router.weight": "model-00018-of-00026.safetensors",
169
+ "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
170
+ "model.layers.17.self_attn.k_proj.bias": "model-00018-of-00026.safetensors",
171
+ "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00026.safetensors",
172
+ "model.layers.17.self_attn.o_proj.bias": "model-00018-of-00026.safetensors",
173
+ "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00026.safetensors",
174
+ "model.layers.17.self_attn.q_proj.bias": "model-00018-of-00026.safetensors",
175
+ "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00026.safetensors",
176
+ "model.layers.17.self_attn.sinks": "model-00018-of-00026.safetensors",
177
+ "model.layers.17.self_attn.v_proj.bias": "model-00018-of-00026.safetensors",
178
+ "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00026.safetensors",
179
+ "model.layers.18.input_layernorm.weight": "model-00020-of-00026.safetensors",
180
+ "model.layers.18.mlp.experts.down_proj": "model-00020-of-00026.safetensors",
181
+ "model.layers.18.mlp.experts.down_proj_bias": "model-00020-of-00026.safetensors",
182
+ "model.layers.18.mlp.experts.gate_up_proj": "model-00020-of-00026.safetensors",
183
+ "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00020-of-00026.safetensors",
184
+ "model.layers.18.mlp.router.bias": "model-00019-of-00026.safetensors",
185
+ "model.layers.18.mlp.router.weight": "model-00019-of-00026.safetensors",
186
+ "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00026.safetensors",
187
+ "model.layers.18.self_attn.k_proj.bias": "model-00019-of-00026.safetensors",
188
+ "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00026.safetensors",
189
+ "model.layers.18.self_attn.o_proj.bias": "model-00019-of-00026.safetensors",
190
+ "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00026.safetensors",
191
+ "model.layers.18.self_attn.q_proj.bias": "model-00019-of-00026.safetensors",
192
+ "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00026.safetensors",
193
+ "model.layers.18.self_attn.sinks": "model-00019-of-00026.safetensors",
194
+ "model.layers.18.self_attn.v_proj.bias": "model-00019-of-00026.safetensors",
195
+ "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00026.safetensors",
196
+ "model.layers.19.input_layernorm.weight": "model-00021-of-00026.safetensors",
197
+ "model.layers.19.mlp.experts.down_proj": "model-00021-of-00026.safetensors",
198
+ "model.layers.19.mlp.experts.down_proj_bias": "model-00021-of-00026.safetensors",
199
+ "model.layers.19.mlp.experts.gate_up_proj": "model-00021-of-00026.safetensors",
200
+ "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00021-of-00026.safetensors",
201
+ "model.layers.19.mlp.router.bias": "model-00020-of-00026.safetensors",
202
+ "model.layers.19.mlp.router.weight": "model-00020-of-00026.safetensors",
203
+ "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
204
+ "model.layers.19.self_attn.k_proj.bias": "model-00020-of-00026.safetensors",
205
+ "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00026.safetensors",
206
+ "model.layers.19.self_attn.o_proj.bias": "model-00020-of-00026.safetensors",
207
+ "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00026.safetensors",
208
+ "model.layers.19.self_attn.q_proj.bias": "model-00020-of-00026.safetensors",
209
+ "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00026.safetensors",
210
+ "model.layers.19.self_attn.sinks": "model-00020-of-00026.safetensors",
211
+ "model.layers.19.self_attn.v_proj.bias": "model-00020-of-00026.safetensors",
212
+ "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00026.safetensors",
213
+ "model.layers.2.input_layernorm.weight": "model-00004-of-00026.safetensors",
214
+ "model.layers.2.mlp.experts.down_proj": "model-00004-of-00026.safetensors",
215
+ "model.layers.2.mlp.experts.down_proj_bias": "model-00004-of-00026.safetensors",
216
+ "model.layers.2.mlp.experts.gate_up_proj": "model-00004-of-00026.safetensors",
217
+ "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00004-of-00026.safetensors",
218
+ "model.layers.2.mlp.router.bias": "model-00003-of-00026.safetensors",
219
+ "model.layers.2.mlp.router.weight": "model-00003-of-00026.safetensors",
220
+ "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00026.safetensors",
221
+ "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00026.safetensors",
222
+ "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00026.safetensors",
223
+ "model.layers.2.self_attn.o_proj.bias": "model-00003-of-00026.safetensors",
224
+ "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00026.safetensors",
225
+ "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00026.safetensors",
226
+ "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00026.safetensors",
227
+ "model.layers.2.self_attn.sinks": "model-00003-of-00026.safetensors",
228
+ "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00026.safetensors",
229
+ "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00026.safetensors",
230
+ "model.layers.20.input_layernorm.weight": "model-00022-of-00026.safetensors",
231
+ "model.layers.20.mlp.experts.down_proj": "model-00022-of-00026.safetensors",
232
+ "model.layers.20.mlp.experts.down_proj_bias": "model-00022-of-00026.safetensors",
233
+ "model.layers.20.mlp.experts.gate_up_proj": "model-00022-of-00026.safetensors",
234
+ "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00022-of-00026.safetensors",
235
+ "model.layers.20.mlp.router.bias": "model-00021-of-00026.safetensors",
236
+ "model.layers.20.mlp.router.weight": "model-00021-of-00026.safetensors",
237
+ "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00026.safetensors",
238
+ "model.layers.20.self_attn.k_proj.bias": "model-00021-of-00026.safetensors",
239
+ "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00026.safetensors",
240
+ "model.layers.20.self_attn.o_proj.bias": "model-00021-of-00026.safetensors",
241
+ "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00026.safetensors",
242
+ "model.layers.20.self_attn.q_proj.bias": "model-00021-of-00026.safetensors",
243
+ "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00026.safetensors",
244
+ "model.layers.20.self_attn.sinks": "model-00021-of-00026.safetensors",
245
+ "model.layers.20.self_attn.v_proj.bias": "model-00021-of-00026.safetensors",
246
+ "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00026.safetensors",
247
+ "model.layers.21.input_layernorm.weight": "model-00023-of-00026.safetensors",
248
+ "model.layers.21.mlp.experts.down_proj": "model-00023-of-00026.safetensors",
249
+ "model.layers.21.mlp.experts.down_proj_bias": "model-00023-of-00026.safetensors",
250
+ "model.layers.21.mlp.experts.gate_up_proj": "model-00023-of-00026.safetensors",
251
+ "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00023-of-00026.safetensors",
252
+ "model.layers.21.mlp.router.bias": "model-00022-of-00026.safetensors",
253
+ "model.layers.21.mlp.router.weight": "model-00022-of-00026.safetensors",
254
+ "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00026.safetensors",
255
+ "model.layers.21.self_attn.k_proj.bias": "model-00022-of-00026.safetensors",
256
+ "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00026.safetensors",
257
+ "model.layers.21.self_attn.o_proj.bias": "model-00022-of-00026.safetensors",
258
+ "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00026.safetensors",
259
+ "model.layers.21.self_attn.q_proj.bias": "model-00022-of-00026.safetensors",
260
+ "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00026.safetensors",
261
+ "model.layers.21.self_attn.sinks": "model-00022-of-00026.safetensors",
262
+ "model.layers.21.self_attn.v_proj.bias": "model-00022-of-00026.safetensors",
263
+ "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00026.safetensors",
264
+ "model.layers.22.input_layernorm.weight": "model-00024-of-00026.safetensors",
265
+ "model.layers.22.mlp.experts.down_proj": "model-00024-of-00026.safetensors",
266
+ "model.layers.22.mlp.experts.down_proj_bias": "model-00024-of-00026.safetensors",
267
+ "model.layers.22.mlp.experts.gate_up_proj": "model-00024-of-00026.safetensors",
268
+ "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00024-of-00026.safetensors",
269
+ "model.layers.22.mlp.router.bias": "model-00023-of-00026.safetensors",
270
+ "model.layers.22.mlp.router.weight": "model-00023-of-00026.safetensors",
271
+ "model.layers.22.post_attention_layernorm.weight": "model-00024-of-00026.safetensors",
272
+ "model.layers.22.self_attn.k_proj.bias": "model-00023-of-00026.safetensors",
273
+ "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00026.safetensors",
274
+ "model.layers.22.self_attn.o_proj.bias": "model-00023-of-00026.safetensors",
275
+ "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00026.safetensors",
276
+ "model.layers.22.self_attn.q_proj.bias": "model-00023-of-00026.safetensors",
277
+ "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00026.safetensors",
278
+ "model.layers.22.self_attn.sinks": "model-00023-of-00026.safetensors",
279
+ "model.layers.22.self_attn.v_proj.bias": "model-00023-of-00026.safetensors",
280
+ "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00026.safetensors",
281
+ "model.layers.23.input_layernorm.weight": "model-00025-of-00026.safetensors",
282
+ "model.layers.23.mlp.experts.down_proj": "model-00025-of-00026.safetensors",
283
+ "model.layers.23.mlp.experts.down_proj_bias": "model-00025-of-00026.safetensors",
284
+ "model.layers.23.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
285
+ "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00025-of-00026.safetensors",
286
+ "model.layers.23.mlp.router.bias": "model-00024-of-00026.safetensors",
287
+ "model.layers.23.mlp.router.weight": "model-00024-of-00026.safetensors",
288
+ "model.layers.23.post_attention_layernorm.weight": "model-00025-of-00026.safetensors",
289
+ "model.layers.23.self_attn.k_proj.bias": "model-00024-of-00026.safetensors",
290
+ "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00026.safetensors",
291
+ "model.layers.23.self_attn.o_proj.bias": "model-00024-of-00026.safetensors",
292
+ "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00026.safetensors",
293
+ "model.layers.23.self_attn.q_proj.bias": "model-00024-of-00026.safetensors",
294
+ "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00026.safetensors",
295
+ "model.layers.23.self_attn.sinks": "model-00024-of-00026.safetensors",
296
+ "model.layers.23.self_attn.v_proj.bias": "model-00024-of-00026.safetensors",
297
+ "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00026.safetensors",
298
+ "model.layers.3.input_layernorm.weight": "model-00005-of-00026.safetensors",
299
+ "model.layers.3.mlp.experts.down_proj": "model-00005-of-00026.safetensors",
300
+ "model.layers.3.mlp.experts.down_proj_bias": "model-00005-of-00026.safetensors",
301
+ "model.layers.3.mlp.experts.gate_up_proj": "model-00005-of-00026.safetensors",
302
+ "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00005-of-00026.safetensors",
303
+ "model.layers.3.mlp.router.bias": "model-00004-of-00026.safetensors",
304
+ "model.layers.3.mlp.router.weight": "model-00004-of-00026.safetensors",
305
+ "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00026.safetensors",
306
+ "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00026.safetensors",
307
+ "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00026.safetensors",
308
+ "model.layers.3.self_attn.o_proj.bias": "model-00004-of-00026.safetensors",
309
+ "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00026.safetensors",
310
+ "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00026.safetensors",
311
+ "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00026.safetensors",
312
+ "model.layers.3.self_attn.sinks": "model-00004-of-00026.safetensors",
313
+ "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00026.safetensors",
314
+ "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00026.safetensors",
315
+ "model.layers.4.input_layernorm.weight": "model-00006-of-00026.safetensors",
316
+ "model.layers.4.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
317
+ "model.layers.4.mlp.experts.down_proj_bias": "model-00006-of-00026.safetensors",
318
+ "model.layers.4.mlp.experts.gate_up_proj": "model-00006-of-00026.safetensors",
319
+ "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00006-of-00026.safetensors",
320
+ "model.layers.4.mlp.router.bias": "model-00005-of-00026.safetensors",
321
+ "model.layers.4.mlp.router.weight": "model-00005-of-00026.safetensors",
322
+ "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00026.safetensors",
323
+ "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00026.safetensors",
324
+ "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00026.safetensors",
325
+ "model.layers.4.self_attn.o_proj.bias": "model-00005-of-00026.safetensors",
326
+ "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00026.safetensors",
327
+ "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00026.safetensors",
328
+ "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00026.safetensors",
329
+ "model.layers.4.self_attn.sinks": "model-00005-of-00026.safetensors",
330
+ "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00026.safetensors",
331
+ "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00026.safetensors",
332
+ "model.layers.5.input_layernorm.weight": "model-00007-of-00026.safetensors",
333
+ "model.layers.5.mlp.experts.down_proj": "model-00007-of-00026.safetensors",
334
+ "model.layers.5.mlp.experts.down_proj_bias": "model-00007-of-00026.safetensors",
335
+ "model.layers.5.mlp.experts.gate_up_proj": "model-00007-of-00026.safetensors",
336
+ "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00007-of-00026.safetensors",
337
+ "model.layers.5.mlp.router.bias": "model-00006-of-00026.safetensors",
338
+ "model.layers.5.mlp.router.weight": "model-00006-of-00026.safetensors",
339
+ "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
340
+ "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00026.safetensors",
341
+ "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00026.safetensors",
342
+ "model.layers.5.self_attn.o_proj.bias": "model-00006-of-00026.safetensors",
343
+ "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00026.safetensors",
344
+ "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00026.safetensors",
345
+ "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00026.safetensors",
346
+ "model.layers.5.self_attn.sinks": "model-00006-of-00026.safetensors",
347
+ "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00026.safetensors",
348
+ "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00026.safetensors",
349
+ "model.layers.6.input_layernorm.weight": "model-00008-of-00026.safetensors",
350
+ "model.layers.6.mlp.experts.down_proj": "model-00008-of-00026.safetensors",
351
+ "model.layers.6.mlp.experts.down_proj_bias": "model-00008-of-00026.safetensors",
352
+ "model.layers.6.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
353
+ "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00008-of-00026.safetensors",
354
+ "model.layers.6.mlp.router.bias": "model-00007-of-00026.safetensors",
355
+ "model.layers.6.mlp.router.weight": "model-00007-of-00026.safetensors",
356
+ "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00026.safetensors",
357
+ "model.layers.6.self_attn.k_proj.bias": "model-00007-of-00026.safetensors",
358
+ "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00026.safetensors",
359
+ "model.layers.6.self_attn.o_proj.bias": "model-00007-of-00026.safetensors",
360
+ "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00026.safetensors",
361
+ "model.layers.6.self_attn.q_proj.bias": "model-00007-of-00026.safetensors",
362
+ "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00026.safetensors",
363
+ "model.layers.6.self_attn.sinks": "model-00007-of-00026.safetensors",
364
+ "model.layers.6.self_attn.v_proj.bias": "model-00007-of-00026.safetensors",
365
+ "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00026.safetensors",
366
+ "model.layers.7.input_layernorm.weight": "model-00009-of-00026.safetensors",
367
+ "model.layers.7.mlp.experts.down_proj": "model-00009-of-00026.safetensors",
368
+ "model.layers.7.mlp.experts.down_proj_bias": "model-00009-of-00026.safetensors",
369
+ "model.layers.7.mlp.experts.gate_up_proj": "model-00009-of-00026.safetensors",
370
+ "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00009-of-00026.safetensors",
371
+ "model.layers.7.mlp.router.bias": "model-00008-of-00026.safetensors",
372
+ "model.layers.7.mlp.router.weight": "model-00008-of-00026.safetensors",
373
+ "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
374
+ "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00026.safetensors",
375
+ "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00026.safetensors",
376
+ "model.layers.7.self_attn.o_proj.bias": "model-00008-of-00026.safetensors",
377
+ "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00026.safetensors",
378
+ "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00026.safetensors",
379
+ "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00026.safetensors",
380
+ "model.layers.7.self_attn.sinks": "model-00008-of-00026.safetensors",
381
+ "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00026.safetensors",
382
+ "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00026.safetensors",
383
+ "model.layers.8.input_layernorm.weight": "model-00010-of-00026.safetensors",
384
+ "model.layers.8.mlp.experts.down_proj": "model-00010-of-00026.safetensors",
385
+ "model.layers.8.mlp.experts.down_proj_bias": "model-00010-of-00026.safetensors",
386
+ "model.layers.8.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
387
+ "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00010-of-00026.safetensors",
388
+ "model.layers.8.mlp.router.bias": "model-00009-of-00026.safetensors",
389
+ "model.layers.8.mlp.router.weight": "model-00009-of-00026.safetensors",
390
+ "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00026.safetensors",
391
+ "model.layers.8.self_attn.k_proj.bias": "model-00009-of-00026.safetensors",
392
+ "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00026.safetensors",
393
+ "model.layers.8.self_attn.o_proj.bias": "model-00009-of-00026.safetensors",
394
+ "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00026.safetensors",
395
+ "model.layers.8.self_attn.q_proj.bias": "model-00009-of-00026.safetensors",
396
+ "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00026.safetensors",
397
+ "model.layers.8.self_attn.sinks": "model-00009-of-00026.safetensors",
398
+ "model.layers.8.self_attn.v_proj.bias": "model-00009-of-00026.safetensors",
399
+ "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00026.safetensors",
400
+ "model.layers.9.input_layernorm.weight": "model-00011-of-00026.safetensors",
401
+ "model.layers.9.mlp.experts.down_proj": "model-00011-of-00026.safetensors",
402
+ "model.layers.9.mlp.experts.down_proj_bias": "model-00011-of-00026.safetensors",
403
+ "model.layers.9.mlp.experts.gate_up_proj": "model-00011-of-00026.safetensors",
404
+ "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00011-of-00026.safetensors",
405
+ "model.layers.9.mlp.router.bias": "model-00010-of-00026.safetensors",
406
+ "model.layers.9.mlp.router.weight": "model-00010-of-00026.safetensors",
407
+ "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
408
+ "model.layers.9.self_attn.k_proj.bias": "model-00010-of-00026.safetensors",
409
+ "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00026.safetensors",
410
+ "model.layers.9.self_attn.o_proj.bias": "model-00010-of-00026.safetensors",
411
+ "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00026.safetensors",
412
+ "model.layers.9.self_attn.q_proj.bias": "model-00010-of-00026.safetensors",
413
+ "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00026.safetensors",
414
+ "model.layers.9.self_attn.sinks": "model-00010-of-00026.safetensors",
415
+ "model.layers.9.self_attn.v_proj.bias": "model-00010-of-00026.safetensors",
416
+ "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00026.safetensors",
417
+ "model.norm.weight": "model-00025-of-00026.safetensors"
418
+ }
419
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|return|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
3
+ size 27868174
tokenizer_config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "199998": {
4
+ "content": "<|startoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "199999": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "200000": {
20
+ "content": "<|reserved_200000|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "200001": {
28
+ "content": "<|reserved_200001|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "200002": {
36
+ "content": "<|return|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "200003": {
44
+ "content": "<|constrain|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "200004": {
52
+ "content": "<|reserved_200004|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "200005": {
60
+ "content": "<|channel|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "200006": {
68
+ "content": "<|start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "200007": {
76
+ "content": "<|end|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "200008": {
84
+ "content": "<|message|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "200009": {
92
+ "content": "<|reserved_200009|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "200010": {
100
+ "content": "<|reserved_200010|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "200011": {
108
+ "content": "<|reserved_200011|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "200012": {
116
+ "content": "<|call|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "200013": {
124
+ "content": "<|reserved_200013|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "200014": {
132
+ "content": "<|reserved_200014|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "200015": {
140
+ "content": "<|reserved_200015|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "200016": {
148
+ "content": "<|reserved_200016|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "200017": {
156
+ "content": "<|reserved_200017|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "200018": {
164
+ "content": "<|endofprompt|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ }
171
+ },
172
+ "bos_token": "<|startoftext|>",
173
+ "clean_up_tokenization_spaces": false,
174
+ "eos_token": "<|return|>",
175
+ "extra_special_tokens": {},
176
+ "model_input_names": [
177
+ "input_ids",
178
+ "attention_mask"
179
+ ],
180
+ "model_max_length": 1000000000000000019884624838656,
181
+ "pad_token": "<|endoftext|>",
182
+ "tokenizer_class": "PreTrainedTokenizerFast"
183
+ }