zenlm/zen-nano-0.6b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: zenlm/zen-nano-0.6b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-10 00:52:02 +08:00
commit d92cdcb44e
34 changed files with 304565 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
.gitattributes vendored Normal file
View File

@@ -0,0 +1,45 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
gguf/zen-nano-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
gguf/zen-nano-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
gguf/zen-nano-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
gguf/zen-nano-f16.gguf filter=lfs diff=lfs merge=lfs -text
mlx/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gguf/zen-nano-0.6b-f16.gguf filter=lfs diff=lfs merge=lfs -text
gguf/zen-nano-0.6b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
gguf/zen-nano-0.6b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
gguf/zen-nano-0.6b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

64
README.md Normal file
View File

@@ -0,0 +1,64 @@
---
language: en
license: apache-2.0
tags:
- text-generation
- zen
- zenlm
- hanzo
- edge
- mobile
- lightweight
pipeline_tag: text-generation
library_name: transformers
---
# Zen Nano 0.6b
Ultra-lightweight 0.6B language model optimized for edge and mobile deployment.
## Overview
Built on **Zen MoDE (Mixture of Distilled Experts)** architecture with 0.6B parameters and 32K context window.
Developed by [Hanzo AI](https://hanzo.ai) and the [Zoo Labs Foundation](https://zoo.ngo).
## Quick Start
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "zenlm/zen-nano-0.6b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Hello!"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
```
## API Access
```bash
curl https://api.hanzo.ai/v1/chat/completions \
-H "Authorization: Bearer $HANZO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "zen-nano-0.6b", "messages": [{"role": "user", "content": "Hello"}]}'
```
Get your API key at [console.hanzo.ai](https://console.hanzo.ai) — $5 free credit on signup.
## Model Details
| Attribute | Value |
|-----------|-------|
| Parameters | 0.6B |
| Architecture | Zen MoDE |
| Context | 32K tokens |
| License | Apache 2.0 |
## License
Apache 2.0

28
added_tokens.json Normal file
View File

@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

89
chat_template.jinja Normal file
View File

@@ -0,0 +1,89 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

60
config.json Normal file
View File

@@ -0,0 +1,60 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151645,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.56.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

12
generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151645,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.56.1"
}

3
gguf/zen-nano-0.6b-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e7cc02f96235c30635efb16d603e0c2fec718ce35ee519873227660b521975a2
size 396704320

3
gguf/zen-nano-0.6b-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35282e1e90055515be54f19381b613fb4730a206d75fcd0d50860d978b804653
size 444414528

3
gguf/zen-nano-0.6b-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:149506af2ba7f68195df57fe3aaf0152b88e651e3930501aba8b25623fbde0f9
size 639446592

3
gguf/zen-nano-0.6b-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0135a2e8b9e93c0a3a27306d84166447bb19c8fabafedbc5e3c509269e5f196
size 1198181952

3
gguf/zen-nano-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6334c8c994f31efcf5da9fd7dab17bf840f5521328480d9ea21b49d75bace111
size 397807808

3
gguf/zen-nano-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f36530101304ea78422b1e2953c3b18569d270f5250dddefffe4e48de84cf89
size 420085952

3
gguf/zen-nano-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e4b1fc6dcd579f43d3c90ca025ebb9016e87b057b254d3c9716f99e9a0bfbee2
size 531068096

3
gguf/zen-nano-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0c68886e3e3402e342842c1ff86e023061cc5fbfa1b48156d6696da0990cd67
size 994156736

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

12
mlx/CITATION.md Normal file
View File

@@ -0,0 +1,12 @@
# Model Attribution
## Base Model
This MLX version is based on **Qwen3-0.6B-gabliterated** by Goekdeniz-Guelmez.
## Citation
Gülmez, G. (2025). Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models.
This work builds upon the foundational research by Arditi et al. (2024) on refusal direction identification in large language models.
## Original Model
https://huggingface.co/Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated

11
mlx/README.md Normal file
View File

@@ -0,0 +1,11 @@
---
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
library_name: mlx
tags:
- mlx
base_model: Qwen/Qwen2.5-0.5B
---

28
mlx/added_tokens.json Normal file
View File

@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

99
mlx/chat_template.jinja Normal file
View File

@@ -0,0 +1,99 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for forward_message in messages %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- set message = messages[index] %}
{%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
{%- set tool_start = '<tool_response>' %}
{%- set tool_start_length = tool_start|length %}
{%- set start_of_message = current_content[:tool_start_length] %}
{%- set tool_end = '</tool_response>' %}
{%- set tool_end_length = tool_end|length %}
{%- set start_pos = (current_content|length) - tool_end_length %}
{%- if start_pos < 0 %}
{%- set start_pos = 0 %}
{%- endif %}
{%- set end_of_message = current_content[start_pos:] %}
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
{%- set content = m_content %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in m_content %}
{%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
{%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
{%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

40
mlx/config.json Normal file
View File

@@ -0,0 +1,40 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"quantization": {
"group_size": 64,
"bits": 4,
"mode": "affine"
},
"quantization_config": {
"group_size": 64,
"bits": 4,
"mode": "affine"
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

13
mlx/generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.51.3"
}

151388
mlx/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
mlx/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ae65b1fa9f2925679e6c54b80b0fd265b71a2c4820463e9a5fd8c49a1d9ab6c0
size 335450548

712
mlx/model.safetensors.index.json Normal file
View File

@@ -0,0 +1,712 @@
{
"metadata": {
"total_size": 335372288,
"total_parameters": 596049920
},
"weight_map": {
"model.embed_tokens.biases": "model.safetensors",
"model.embed_tokens.scales": "model.safetensors",
"model.embed_tokens.weight": "model.safetensors",
"model.layers.0.input_layernorm.weight": "model.safetensors",
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
"model.layers.0.self_attn.k_norm.weight": "model.safetensors",
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
"model.layers.0.self_attn.q_norm.weight": "model.safetensors",
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
"model.layers.1.input_layernorm.weight": "model.safetensors",
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
"model.layers.1.self_attn.k_norm.weight": "model.safetensors",
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
"model.layers.1.self_attn.q_norm.weight": "model.safetensors",
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
"model.layers.10.input_layernorm.weight": "model.safetensors",
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
"model.layers.10.self_attn.k_norm.weight": "model.safetensors",
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
"model.layers.10.self_attn.q_norm.weight": "model.safetensors",
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
"model.layers.11.input_layernorm.weight": "model.safetensors",
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
"model.layers.11.self_attn.k_norm.weight": "model.safetensors",
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
"model.layers.11.self_attn.q_norm.weight": "model.safetensors",
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
"model.layers.12.input_layernorm.weight": "model.safetensors",
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
"model.layers.12.self_attn.k_norm.weight": "model.safetensors",
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
"model.layers.12.self_attn.q_norm.weight": "model.safetensors",
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
"model.layers.13.input_layernorm.weight": "model.safetensors",
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
"model.layers.13.self_attn.k_norm.weight": "model.safetensors",
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
"model.layers.13.self_attn.q_norm.weight": "model.safetensors",
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
"model.layers.14.input_layernorm.weight": "model.safetensors",
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
"model.layers.14.self_attn.k_norm.weight": "model.safetensors",
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
"model.layers.14.self_attn.q_norm.weight": "model.safetensors",
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
"model.layers.15.input_layernorm.weight": "model.safetensors",
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
"model.layers.15.self_attn.k_norm.weight": "model.safetensors",
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
"model.layers.15.self_attn.q_norm.weight": "model.safetensors",
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
"model.layers.16.input_layernorm.weight": "model.safetensors",
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
"model.layers.16.self_attn.k_norm.weight": "model.safetensors",
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
"model.layers.16.self_attn.q_norm.weight": "model.safetensors",
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
"model.layers.17.input_layernorm.weight": "model.safetensors",
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
"model.layers.17.self_attn.k_norm.weight": "model.safetensors",
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
"model.layers.17.self_attn.q_norm.weight": "model.safetensors",
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
"model.layers.18.input_layernorm.weight": "model.safetensors",
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
"model.layers.18.self_attn.k_norm.weight": "model.safetensors",
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
"model.layers.18.self_attn.q_norm.weight": "model.safetensors",
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
"model.layers.19.input_layernorm.weight": "model.safetensors",
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
"model.layers.19.self_attn.k_norm.weight": "model.safetensors",
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
"model.layers.19.self_attn.q_norm.weight": "model.safetensors",
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
"model.layers.2.input_layernorm.weight": "model.safetensors",
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
"model.layers.2.self_attn.k_norm.weight": "model.safetensors",
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
"model.layers.2.self_attn.q_norm.weight": "model.safetensors",
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
"model.layers.20.input_layernorm.weight": "model.safetensors",
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
"model.layers.20.self_attn.k_norm.weight": "model.safetensors",
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
"model.layers.20.self_attn.q_norm.weight": "model.safetensors",
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
"model.layers.21.input_layernorm.weight": "model.safetensors",
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
"model.layers.21.self_attn.k_norm.weight": "model.safetensors",
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
"model.layers.21.self_attn.q_norm.weight": "model.safetensors",
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
"model.layers.22.input_layernorm.weight": "model.safetensors",
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
"model.layers.22.self_attn.k_norm.weight": "model.safetensors",
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
"model.layers.22.self_attn.q_norm.weight": "model.safetensors",
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
"model.layers.23.input_layernorm.weight": "model.safetensors",
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
"model.layers.23.self_attn.k_norm.weight": "model.safetensors",
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
"model.layers.23.self_attn.q_norm.weight": "model.safetensors",
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
"model.layers.24.input_layernorm.weight": "model.safetensors",
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
"model.layers.24.self_attn.k_norm.weight": "model.safetensors",
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
"model.layers.24.self_attn.q_norm.weight": "model.safetensors",
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
"model.layers.25.input_layernorm.weight": "model.safetensors",
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
"model.layers.25.self_attn.k_norm.weight": "model.safetensors",
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
"model.layers.25.self_attn.q_norm.weight": "model.safetensors",
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
"model.layers.26.input_layernorm.weight": "model.safetensors",
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
"model.layers.26.self_attn.k_norm.weight": "model.safetensors",
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
"model.layers.26.self_attn.q_norm.weight": "model.safetensors",
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
"model.layers.27.input_layernorm.weight": "model.safetensors",
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
"model.layers.27.self_attn.k_norm.weight": "model.safetensors",
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
"model.layers.27.self_attn.q_norm.weight": "model.safetensors",
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
"model.layers.3.input_layernorm.weight": "model.safetensors",
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
"model.layers.3.self_attn.k_norm.weight": "model.safetensors",
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
"model.layers.3.self_attn.q_norm.weight": "model.safetensors",
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
"model.layers.4.input_layernorm.weight": "model.safetensors",
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
"model.layers.4.self_attn.k_norm.weight": "model.safetensors",
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
"model.layers.4.self_attn.q_norm.weight": "model.safetensors",
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
"model.layers.5.input_layernorm.weight": "model.safetensors",
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
"model.layers.5.self_attn.k_norm.weight": "model.safetensors",
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
"model.layers.5.self_attn.q_norm.weight": "model.safetensors",
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
"model.layers.6.input_layernorm.weight": "model.safetensors",
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
"model.layers.6.self_attn.k_norm.weight": "model.safetensors",
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
"model.layers.6.self_attn.q_norm.weight": "model.safetensors",
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
"model.layers.7.input_layernorm.weight": "model.safetensors",
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
"model.layers.7.self_attn.k_norm.weight": "model.safetensors",
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
"model.layers.7.self_attn.q_norm.weight": "model.safetensors",
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
"model.layers.8.input_layernorm.weight": "model.safetensors",
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
"model.layers.8.self_attn.k_norm.weight": "model.safetensors",
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
"model.layers.8.self_attn.q_norm.weight": "model.safetensors",
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
"model.layers.9.input_layernorm.weight": "model.safetensors",
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
"model.layers.9.self_attn.k_norm.weight": "model.safetensors",
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
"model.layers.9.self_attn.q_norm.weight": "model.safetensors",
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
"model.norm.weight": "model.safetensors"
}
}

31
mlx/special_tokens_map.json Normal file
View File

@@ -0,0 +1,31 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

BIN
mlx/tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

240
mlx/tokenizer_config.json Normal file
View File

@@ -0,0 +1,240 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 40960,
"pad_token": "<|vision_pad|>",
"padding_side": "left",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
mlx/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cc91f68501a0536a233fc0e5d82b68f29f32cd07dfd06dbb7adac53fedc29ff1
size 1192135096

25
special_tokens_map.json Normal file
View File

@@ -0,0 +1,25 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<|im_end|>"
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac6583c532ebcffab265f0693ef8624858bd22dece1754500925f53e5dc5f058
size 11422929

239
tokenizer_config.json Normal file
View File

@@ -0,0 +1,239 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|im_end|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:27d23ba647d4668e1180c1d3b3eca25b43076eb03cca2f41c15f83e5d24bb136
size 5777

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long