Add local models via Git LFS (23 models, ~143 GB)
This commit is contained in:
parent
94b5c12c2d
commit
9b381fb3de
246 changed files with 38788 additions and 0 deletions
36
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/.gitattributes
vendored
Normal file
36
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/.gitattributes
vendored
Normal file
|
|
@ -0,0 +1,36 @@
|
|||
*.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
|
||||
75
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/README.md
Normal file
75
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/README.md
Normal file
|
|
@ -0,0 +1,75 @@
|
|||
---
|
||||
base_model: Qwen/Qwen3.5-2B
|
||||
library_name: mlx
|
||||
tags:
|
||||
- mlx
|
||||
- qwen3.5
|
||||
- vision-language-model
|
||||
- quantized
|
||||
- 4bit
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
# Qwen3.5-2B-MLX-4bit
|
||||
|
||||
This is a 4-bit quantized MLX version of [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) for Apple Silicon.
|
||||
|
||||
## Model Details
|
||||
|
||||
- **Original Model:** [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B)
|
||||
- **Quantization:** 4-bit (6.225 bits per weight)
|
||||
- **Group Size:** 64
|
||||
- **Format:** MLX SafeTensors
|
||||
- **Framework:** [mlx-vlm](https://github.com/Blaizzy/mlx-vlm)
|
||||
- **Disk Size:** ~1.6G
|
||||
|
||||
## Conversion Details
|
||||
|
||||
This model was converted using `mlx-vlm` from the [`pc/fix-qwen35-predicate`](https://github.com/Blaizzy/mlx-vlm/tree/pc/fix-qwen35-predicate) branch, which includes fixes for Qwen3.5 model support (proper handling of MoE gate layers, `shared_expert_gate`, and `A_log` casting).
|
||||
|
||||
**Conversion command:**
|
||||
```bash
|
||||
python3 -m mlx_vlm convert \
|
||||
--hf-path "Qwen/Qwen3.5-2B" \
|
||||
--mlx-path "./Qwen3.5-2B-MLX-4bit" \
|
||||
-q --q-bits 4 --q-group-size 64
|
||||
```
|
||||
|
||||
## Important Note
|
||||
|
||||
A better, more optimized conversion may be available from **@Prince** ([@Blaizzy](https://huggingface.co/Blaizzy)) in the MLX VLM community. Check the [mlx-community](https://huggingface.co/mlx-community) organization for updated versions as official Qwen3.5 support is merged into the main `mlx-vlm` branch.
|
||||
|
||||
## Related Models
|
||||
|
||||
- **bf16 (full precision):** [mlx-community/Qwen3.5-2B-MLX-bf16](https://huggingface.co/mlx-community/Qwen3.5-2B-MLX-bf16)
|
||||
- **8-bit quantized:** [mlx-community/Qwen3.5-2B-MLX-8bit](https://huggingface.co/mlx-community/Qwen3.5-2B-MLX-8bit)
|
||||
- **Original:** [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B)
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from mlx_vlm import load, generate
|
||||
|
||||
model, processor = load("mlx-community/Qwen3.5-2B-MLX-4bit")
|
||||
|
||||
output = generate(
|
||||
model,
|
||||
processor,
|
||||
prompt="Describe this image.",
|
||||
image="path/to/image.jpg",
|
||||
max_tokens=512
|
||||
)
|
||||
print(output)
|
||||
```
|
||||
|
||||
**CLI:**
|
||||
```bash
|
||||
python3 -m mlx_vlm.generate \
|
||||
--model mlx-community/Qwen3.5-2B-MLX-4bit \
|
||||
--image path/to/image.jpg \
|
||||
--prompt "Describe this image."
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
This model inherits the [Apache 2.0 license](https://huggingface.co/Qwen/Qwen3.5-2B) from the original Qwen model.
|
||||
154
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/chat_template.jinja
Normal file
154
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/chat_template.jinja
Normal file
|
|
@ -0,0 +1,154 @@
|
|||
{%- set image_count = namespace(value=0) %}
|
||||
{%- set video_count = namespace(value=0) %}
|
||||
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
||||
{%- if content is string %}
|
||||
{{- content }}
|
||||
{%- elif content is iterable and content is not mapping %}
|
||||
{%- for item in content %}
|
||||
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
||||
{%- if is_system_content %}
|
||||
{{- raise_exception('System message cannot contain images.') }}
|
||||
{%- endif %}
|
||||
{%- if do_vision_count %}
|
||||
{%- set image_count.value = image_count.value + 1 %}
|
||||
{%- endif %}
|
||||
{%- if add_vision_id %}
|
||||
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
||||
{%- endif %}
|
||||
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
||||
{%- elif 'video' in item or item.type == 'video' %}
|
||||
{%- if is_system_content %}
|
||||
{{- raise_exception('System message cannot contain videos.') }}
|
||||
{%- endif %}
|
||||
{%- if do_vision_count %}
|
||||
{%- set video_count.value = video_count.value + 1 %}
|
||||
{%- endif %}
|
||||
{%- if add_vision_id %}
|
||||
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
||||
{%- endif %}
|
||||
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
||||
{%- elif 'text' in item %}
|
||||
{{- item.text }}
|
||||
{%- else %}
|
||||
{{- raise_exception('Unexpected item type in content.') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- elif content is none or content is undefined %}
|
||||
{{- '' }}
|
||||
{%- else %}
|
||||
{{- raise_exception('Unexpected content type.') }}
|
||||
{%- endif %}
|
||||
{%- endmacro %}
|
||||
{%- if not messages %}
|
||||
{{- raise_exception('No messages provided.') }}
|
||||
{%- endif %}
|
||||
{%- if tools and tools is iterable and tools is not mapping %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>" }}
|
||||
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
||||
{%- if content %}
|
||||
{{- '\n\n' + content }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
||||
{{- '<|im_start|>system\n' + 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" %}
|
||||
{%- set content = render_content(message.content, false)|trim %}
|
||||
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if ns.multi_step_tool %}
|
||||
{{- raise_exception('No user query found in messages.') }}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- set content = render_content(message.content, true)|trim %}
|
||||
{%- if message.role == "system" %}
|
||||
{%- if not loop.first %}
|
||||
{{- raise_exception('System message must be at the beginning.') }}
|
||||
{%- endif %}
|
||||
{%- elif message.role == "user" %}
|
||||
{{- '<|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 %}
|
||||
{%- set reasoning_content = reasoning_content|trim %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{%- if loop.first %}
|
||||
{%- if content|trim %}
|
||||
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
||||
{%- else %}
|
||||
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.arguments is defined %}
|
||||
{%- for args_name, args_value in tool_call.arguments|items %}
|
||||
{{- '<parameter=' + args_name + '>\n' }}
|
||||
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
||||
{{- args_value }}
|
||||
{{- '\n</parameter>\n' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '</function>\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif loop.last %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- raise_exception('Unexpected message role.') }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is true %}
|
||||
{{- '<think>\n' }}
|
||||
{%- else %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
106
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/config.json
Normal file
106
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/config.json
Normal file
|
|
@ -0,0 +1,106 @@
|
|||
{
|
||||
"architectures": [
|
||||
"Qwen3_5ForConditionalGeneration"
|
||||
],
|
||||
"image_token_id": 248056,
|
||||
"model_type": "qwen3_5",
|
||||
"quantization": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine"
|
||||
},
|
||||
"quantization_config": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine"
|
||||
},
|
||||
"text_config": {
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_output_gate": true,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 248044,
|
||||
"full_attention_interval": 4,
|
||||
"head_dim": 256,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"layer_types": [
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"full_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"full_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"full_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"full_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"full_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"linear_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"linear_conv_kernel_dim": 4,
|
||||
"linear_key_head_dim": 128,
|
||||
"linear_num_key_heads": 16,
|
||||
"linear_num_value_heads": 16,
|
||||
"linear_value_head_dim": 128,
|
||||
"max_position_embeddings": 262144,
|
||||
"mlp_only_layers": [],
|
||||
"model_type": "qwen3_5_text",
|
||||
"mtp_num_hidden_layers": 1,
|
||||
"mtp_use_dedicated_embeddings": false,
|
||||
"num_attention_heads": 8,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"tie_word_embeddings": true,
|
||||
"use_cache": true,
|
||||
"vocab_size": 248320,
|
||||
"mamba_ssm_dtype": "float32",
|
||||
"rope_parameters": {
|
||||
"mrope_interleaved": true,
|
||||
"mrope_section": [
|
||||
11,
|
||||
11,
|
||||
10
|
||||
],
|
||||
"rope_type": "default",
|
||||
"rope_theta": 10000000,
|
||||
"partial_rotary_factor": 0.25
|
||||
}
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.0.dev0",
|
||||
"video_token_id": 248057,
|
||||
"vision_config": {
|
||||
"deepstack_visual_indexes": [],
|
||||
"depth": 24,
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"hidden_size": 1024,
|
||||
"in_channels": 3,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"model_type": "qwen3_5",
|
||||
"num_heads": 16,
|
||||
"num_position_embeddings": 2304,
|
||||
"out_hidden_size": 2048,
|
||||
"patch_size": 16,
|
||||
"spatial_merge_size": 2,
|
||||
"temporal_patch_size": 2
|
||||
},
|
||||
"vision_end_token_id": 248054,
|
||||
"vision_start_token_id": 248053
|
||||
}
|
||||
BIN
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/model.safetensors
(Stored with Git LFS)
Normal file
BIN
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/model.safetensors
(Stored with Git LFS)
Normal file
Binary file not shown.
|
|
@ -0,0 +1,998 @@
|
|||
{
|
||||
"metadata": {
|
||||
"total_size": 1722149056
|
||||
},
|
||||
"weight_map": {
|
||||
"language_model.model.embed_tokens.biases": "model.safetensors",
|
||||
"language_model.model.embed_tokens.scales": "model.safetensors",
|
||||
"language_model.model.embed_tokens.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.0.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.1.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.10.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.12.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.13.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.14.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.16.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.17.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.18.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.2.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.20.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.21.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.22.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.4.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.5.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.6.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.8.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.A_log": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.conv1d.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.dt_bias": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_a.biases": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_a.scales": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_a.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_b.biases": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_b.scales": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_b.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_qkv.biases": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_qkv.scales": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_qkv.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_z.biases": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_z.scales": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.in_proj_z.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.norm.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.out_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.out_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.9.linear_attn.out_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
||||
"language_model.model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
||||
"language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
||||
"language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
||||
"language_model.model.norm.weight": "model.safetensors",
|
||||
"vision_tower.blocks.0.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.0.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.0.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.0.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.0.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.0.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.0.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.0.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.0.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.0.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.0.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.0.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.1.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.1.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.1.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.1.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.1.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.1.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.1.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.1.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.1.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.1.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.1.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.1.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.10.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.10.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.10.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.10.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.10.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.10.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.10.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.10.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.10.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.10.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.10.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.10.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.11.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.11.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.11.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.11.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.11.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.11.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.11.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.11.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.11.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.11.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.11.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.11.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.12.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.12.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.12.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.12.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.12.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.12.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.12.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.12.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.12.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.12.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.12.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.12.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.13.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.13.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.13.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.13.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.13.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.13.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.13.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.13.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.13.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.13.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.13.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.13.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.14.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.14.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.14.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.14.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.14.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.14.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.14.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.14.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.14.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.14.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.14.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.14.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.15.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.15.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.15.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.15.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.15.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.15.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.15.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.15.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.15.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.15.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.15.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.15.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.16.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.16.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.16.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.16.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.16.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.16.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.16.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.16.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.16.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.16.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.16.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.16.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.17.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.17.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.17.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.17.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.17.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.17.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.17.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.17.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.17.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.17.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.17.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.17.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.18.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.18.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.18.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.18.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.18.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.18.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.18.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.18.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.18.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.18.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.18.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.18.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.19.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.19.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.19.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.19.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.19.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.19.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.19.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.19.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.19.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.19.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.19.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.19.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.2.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.2.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.2.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.2.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.2.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.2.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.2.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.2.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.2.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.2.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.2.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.2.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.20.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.20.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.20.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.20.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.20.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.20.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.20.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.20.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.20.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.20.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.20.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.20.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.21.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.21.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.21.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.21.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.21.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.21.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.21.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.21.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.21.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.21.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.21.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.21.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.22.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.22.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.22.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.22.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.22.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.22.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.22.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.22.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.22.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.22.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.22.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.22.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.23.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.23.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.23.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.23.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.23.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.23.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.23.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.23.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.23.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.23.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.23.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.23.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.3.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.3.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.3.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.3.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.3.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.3.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.3.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.3.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.3.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.3.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.3.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.3.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.4.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.4.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.4.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.4.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.4.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.4.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.4.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.4.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.4.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.4.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.4.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.4.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.5.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.5.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.5.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.5.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.5.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.5.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.5.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.5.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.5.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.5.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.5.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.5.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.6.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.6.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.6.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.6.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.6.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.6.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.6.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.6.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.6.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.6.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.6.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.6.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.7.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.7.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.7.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.7.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.7.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.7.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.7.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.7.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.7.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.7.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.7.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.7.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.8.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.8.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.8.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.8.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.8.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.8.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.8.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.8.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.8.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.8.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.8.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.8.norm2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.9.attn.proj.bias": "model.safetensors",
|
||||
"vision_tower.blocks.9.attn.proj.weight": "model.safetensors",
|
||||
"vision_tower.blocks.9.attn.qkv.bias": "model.safetensors",
|
||||
"vision_tower.blocks.9.attn.qkv.weight": "model.safetensors",
|
||||
"vision_tower.blocks.9.mlp.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.9.mlp.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.9.mlp.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.9.mlp.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.blocks.9.norm1.bias": "model.safetensors",
|
||||
"vision_tower.blocks.9.norm1.weight": "model.safetensors",
|
||||
"vision_tower.blocks.9.norm2.bias": "model.safetensors",
|
||||
"vision_tower.blocks.9.norm2.weight": "model.safetensors",
|
||||
"vision_tower.merger.linear_fc1.bias": "model.safetensors",
|
||||
"vision_tower.merger.linear_fc1.weight": "model.safetensors",
|
||||
"vision_tower.merger.linear_fc2.bias": "model.safetensors",
|
||||
"vision_tower.merger.linear_fc2.weight": "model.safetensors",
|
||||
"vision_tower.merger.norm.bias": "model.safetensors",
|
||||
"vision_tower.merger.norm.weight": "model.safetensors",
|
||||
"vision_tower.patch_embed.proj.bias": "model.safetensors",
|
||||
"vision_tower.patch_embed.proj.weight": "model.safetensors",
|
||||
"vision_tower.pos_embed.weight": "model.safetensors"
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
{
|
||||
"size": {
|
||||
"longest_edge": 16777216,
|
||||
"shortest_edge": 65536
|
||||
},
|
||||
"patch_size": 16,
|
||||
"temporal_patch_size": 2,
|
||||
"merge_size": 2,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"image_processor_type": "Qwen2VLImageProcessorFast"
|
||||
}
|
||||
|
|
@ -0,0 +1,63 @@
|
|||
{
|
||||
"image_processor": {
|
||||
"data_format": "channels_first",
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessorFast",
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"merge_size": 2,
|
||||
"patch_size": 16,
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"longest_edge": 16777216,
|
||||
"shortest_edge": 65536
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
},
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"video_processor": {
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"do_sample_frames": true,
|
||||
"fps": 2,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"max_frames": 768,
|
||||
"merge_size": 2,
|
||||
"min_frames": 4,
|
||||
"patch_size": 16,
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_metadata": false,
|
||||
"size": {
|
||||
"longest_edge": 25165824,
|
||||
"shortest_edge": 4096
|
||||
},
|
||||
"temporal_patch_size": 2,
|
||||
"video_processor_type": "Qwen3VLVideoProcessor"
|
||||
}
|
||||
}
|
||||
BIN
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
|
|
@ -0,0 +1,32 @@
|
|||
{
|
||||
"add_prefix_space": false,
|
||||
"audio_bos_token": "<|audio_start|>",
|
||||
"audio_eos_token": "<|audio_end|>",
|
||||
"audio_token": "<|audio_pad|>",
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"image_token": "<|image_pad|>",
|
||||
"is_local": true,
|
||||
"model_max_length": 262144,
|
||||
"model_specific_special_tokens": {
|
||||
"audio_bos_token": "<|audio_start|>",
|
||||
"audio_eos_token": "<|audio_end|>",
|
||||
"audio_token": "<|audio_pad|>",
|
||||
"image_token": "<|image_pad|>",
|
||||
"video_token": "<|video_pad|>",
|
||||
"vision_bos_token": "<|vision_start|>",
|
||||
"vision_eos_token": "<|vision_end|>"
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"unk_token": null,
|
||||
"video_token": "<|video_pad|>",
|
||||
"vision_bos_token": "<|vision_start|>",
|
||||
"vision_eos_token": "<|vision_end|>"
|
||||
}
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
{
|
||||
"size": {
|
||||
"longest_edge": 25165824,
|
||||
"shortest_edge": 4096
|
||||
},
|
||||
"patch_size": 16,
|
||||
"temporal_patch_size": 2,
|
||||
"merge_size": 2,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"video_processor_type": "Qwen3VLVideoProcessor"
|
||||
}
|
||||
BIN
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/vocab.json
(Stored with Git LFS)
Normal file
BIN
chat/mlx/mlx-community/Qwen3.5-2B-MLX-4bit/vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Loading…
Add table
Add a link
Reference in a new issue