Delete files ._added_tokens.json ._chat_template.jinja ._config.json ._generation_config.json ._merges.txt ._model-00001-of-00002.safetensors ._model-00002-of-00002.safetensors ._model.safetensors.index.json ._special_tokens_map.json ._tokenizer.json ._tokenizer_config.json ._vocab.json .gitattributes README.md added_tokens.json chat_template.jinja config.json generation_config.json merges.txt model-00001-of-00002.safetensors model-00002-of-00002.safetensors model.safetensors.index.json special_tokens_map.json tokenizer.json tokenizer_config.json vocab.json with huggingface_hub
Browse files- ._config.json +0 -0
- ._merges.txt +0 -0
- ._model-00001-of-00002.safetensors +0 -3
- ._model-00002-of-00002.safetensors +0 -3
- ._model.safetensors.index.json +0 -0
- ._special_tokens_map.json +0 -0
- ._tokenizer.json +0 -0
- ._tokenizer_config.json +0 -0
- ._vocab.json +0 -0
- README.md +0 -35
- added_tokens.json +0 -28
- chat_template.jinja +0 -89
- config.json +0 -40
- generation_config.json +0 -13
- merges.txt +0 -0
- model-00001-of-00002.safetensors +0 -3
- model-00002-of-00002.safetensors +0 -3
- model.safetensors.index.json +0 -915
- special_tokens_map.json +0 -31
- tokenizer.json +0 -3
- tokenizer_config.json +0 -239
- vocab.json +0 -0
._config.json
DELETED
|
Binary file (4.1 kB)
|
|
|
._merges.txt
DELETED
|
Binary file (4.1 kB)
|
|
|
._model-00001-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d1e98c800051324c5dd22c500aed9499763e0bbebaddd06c9b0921872a35711f
|
| 3 |
-
size 4096
|
|
|
|
|
|
|
|
|
|
|
|
._model-00002-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d1e98c800051324c5dd22c500aed9499763e0bbebaddd06c9b0921872a35711f
|
| 3 |
-
size 4096
|
|
|
|
|
|
|
|
|
|
|
|
._model.safetensors.index.json
DELETED
|
Binary file (4.1 kB)
|
|
|
._special_tokens_map.json
DELETED
|
Binary file (4.1 kB)
|
|
|
._tokenizer.json
DELETED
|
Binary file (4.1 kB)
|
|
|
._tokenizer_config.json
DELETED
|
Binary file (4.1 kB)
|
|
|
._vocab.json
DELETED
|
Binary file (4.1 kB)
|
|
|
README.md
DELETED
|
@@ -1,35 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: nvidia/Orchestrator-8B
|
| 3 |
-
library_name: mlx
|
| 4 |
-
pipeline_tag: text-generation
|
| 5 |
-
tags:
|
| 6 |
-
- mlx
|
| 7 |
-
---
|
| 8 |
-
|
| 9 |
-
# Otilde/Orchestrator-8B-MLX-F32
|
| 10 |
-
|
| 11 |
-
This model [Otilde/Orchestrator-8B-MLX-F32](https://huggingface.co/Otilde/Orchestrator-8B-MLX-F32) was
|
| 12 |
-
converted to MLX format from [nvidia/Orchestrator-8B](https://huggingface.co/nvidia/Orchestrator-8B)
|
| 13 |
-
using mlx-lm version **0.28.3**.
|
| 14 |
-
|
| 15 |
-
## Use with mlx
|
| 16 |
-
|
| 17 |
-
```bash
|
| 18 |
-
pip install mlx-lm
|
| 19 |
-
```
|
| 20 |
-
|
| 21 |
-
```python
|
| 22 |
-
from mlx_lm import load, generate
|
| 23 |
-
|
| 24 |
-
model, tokenizer = load("Otilde/Orchestrator-8B-MLX-F32")
|
| 25 |
-
|
| 26 |
-
prompt = "hello"
|
| 27 |
-
|
| 28 |
-
if tokenizer.chat_template is not None:
|
| 29 |
-
messages = [{"role": "user", "content": prompt}]
|
| 30 |
-
prompt = tokenizer.apply_chat_template(
|
| 31 |
-
messages, add_generation_prompt=True
|
| 32 |
-
)
|
| 33 |
-
|
| 34 |
-
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 35 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
added_tokens.json
DELETED
|
@@ -1,28 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"</think>": 151668,
|
| 3 |
-
"</tool_call>": 151658,
|
| 4 |
-
"</tool_response>": 151666,
|
| 5 |
-
"<think>": 151667,
|
| 6 |
-
"<tool_call>": 151657,
|
| 7 |
-
"<tool_response>": 151665,
|
| 8 |
-
"<|box_end|>": 151649,
|
| 9 |
-
"<|box_start|>": 151648,
|
| 10 |
-
"<|endoftext|>": 151643,
|
| 11 |
-
"<|file_sep|>": 151664,
|
| 12 |
-
"<|fim_middle|>": 151660,
|
| 13 |
-
"<|fim_pad|>": 151662,
|
| 14 |
-
"<|fim_prefix|>": 151659,
|
| 15 |
-
"<|fim_suffix|>": 151661,
|
| 16 |
-
"<|im_end|>": 151645,
|
| 17 |
-
"<|im_start|>": 151644,
|
| 18 |
-
"<|image_pad|>": 151655,
|
| 19 |
-
"<|object_ref_end|>": 151647,
|
| 20 |
-
"<|object_ref_start|>": 151646,
|
| 21 |
-
"<|quad_end|>": 151651,
|
| 22 |
-
"<|quad_start|>": 151650,
|
| 23 |
-
"<|repo_name|>": 151663,
|
| 24 |
-
"<|video_pad|>": 151656,
|
| 25 |
-
"<|vision_end|>": 151653,
|
| 26 |
-
"<|vision_pad|>": 151654,
|
| 27 |
-
"<|vision_start|>": 151652
|
| 28 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
chat_template.jinja
DELETED
|
@@ -1,89 +0,0 @@
|
|
| 1 |
-
{%- if tools %}
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0].role == 'system' %}
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
-
{%- for message in messages[::-1] %}
|
| 19 |
-
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
-
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
-
{%- set ns.multi_step_tool = false %}
|
| 22 |
-
{%- set ns.last_query_index = index %}
|
| 23 |
-
{%- endif %}
|
| 24 |
-
{%- endfor %}
|
| 25 |
-
{%- for message in messages %}
|
| 26 |
-
{%- if message.content is string %}
|
| 27 |
-
{%- set content = message.content %}
|
| 28 |
-
{%- else %}
|
| 29 |
-
{%- set content = '' %}
|
| 30 |
-
{%- endif %}
|
| 31 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
-
{%- elif message.role == "assistant" %}
|
| 34 |
-
{%- set reasoning_content = '' %}
|
| 35 |
-
{%- if message.reasoning_content is string %}
|
| 36 |
-
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
-
{%- else %}
|
| 38 |
-
{%- if '</think>' in content %}
|
| 39 |
-
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
-
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
-
{%- endif %}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
-
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
-
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
-
{%- else %}
|
| 47 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
-
{%- endif %}
|
| 49 |
-
{%- else %}
|
| 50 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
-
{%- endif %}
|
| 52 |
-
{%- if message.tool_calls %}
|
| 53 |
-
{%- for tool_call in message.tool_calls %}
|
| 54 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
-
{{- '\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- if tool_call.function %}
|
| 58 |
-
{%- set tool_call = tool_call.function %}
|
| 59 |
-
{%- endif %}
|
| 60 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
-
{{- tool_call.name }}
|
| 62 |
-
{{- '", "arguments": ' }}
|
| 63 |
-
{%- if tool_call.arguments is string %}
|
| 64 |
-
{{- tool_call.arguments }}
|
| 65 |
-
{%- else %}
|
| 66 |
-
{{- tool_call.arguments | tojson }}
|
| 67 |
-
{%- endif %}
|
| 68 |
-
{{- '}\n</tool_call>' }}
|
| 69 |
-
{%- endfor %}
|
| 70 |
-
{%- endif %}
|
| 71 |
-
{{- '<|im_end|>\n' }}
|
| 72 |
-
{%- elif message.role == "tool" %}
|
| 73 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
-
{{- '<|im_start|>user' }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{{- '\n<tool_response>\n' }}
|
| 77 |
-
{{- content }}
|
| 78 |
-
{{- '\n</tool_response>' }}
|
| 79 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
-
{{- '<|im_end|>\n' }}
|
| 81 |
-
{%- endif %}
|
| 82 |
-
{%- endif %}
|
| 83 |
-
{%- endfor %}
|
| 84 |
-
{%- if add_generation_prompt %}
|
| 85 |
-
{{- '<|im_start|>assistant\n' }}
|
| 86 |
-
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
-
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
-
{%- endif %}
|
| 89 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
DELETED
|
@@ -1,40 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"eos_token_id": 151645,
|
| 8 |
-
"head_dim": 128,
|
| 9 |
-
"hidden_act": "silu",
|
| 10 |
-
"hidden_size": 4096,
|
| 11 |
-
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size": 12288,
|
| 13 |
-
"max_position_embeddings": 40960,
|
| 14 |
-
"max_window_layers": 36,
|
| 15 |
-
"model_type": "qwen3",
|
| 16 |
-
"num_attention_heads": 32,
|
| 17 |
-
"num_hidden_layers": 36,
|
| 18 |
-
"num_key_value_heads": 8,
|
| 19 |
-
"pad_token_id": 151643,
|
| 20 |
-
"quantization": {
|
| 21 |
-
"group_size": 32,
|
| 22 |
-
"bits": 8,
|
| 23 |
-
"mode": "affine"
|
| 24 |
-
},
|
| 25 |
-
"quantization_config": {
|
| 26 |
-
"group_size": 32,
|
| 27 |
-
"bits": 8,
|
| 28 |
-
"mode": "affine"
|
| 29 |
-
},
|
| 30 |
-
"rms_norm_eps": 1e-06,
|
| 31 |
-
"rope_scaling": null,
|
| 32 |
-
"rope_theta": 1000000,
|
| 33 |
-
"sliding_window": null,
|
| 34 |
-
"tie_word_embeddings": false,
|
| 35 |
-
"torch_dtype": "bfloat16",
|
| 36 |
-
"transformers_version": "4.51.3",
|
| 37 |
-
"use_cache": true,
|
| 38 |
-
"use_sliding_window": false,
|
| 39 |
-
"vocab_size": 151936
|
| 40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
generation_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token_id": 151643,
|
| 3 |
-
"do_sample": true,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
151645,
|
| 6 |
-
151643
|
| 7 |
-
],
|
| 8 |
-
"pad_token_id": 151643,
|
| 9 |
-
"temperature": 0.6,
|
| 10 |
-
"top_k": 20,
|
| 11 |
-
"top_p": 0.95,
|
| 12 |
-
"transformers_version": "4.51.3"
|
| 13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ea123b202fad294f58549d72c93d6236e3695a191748adc739aa06c32d1cd18d
|
| 3 |
-
size 5360885832
|
|
|
|
|
|
|
|
|
|
|
|
model-00002-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9fa1466b0912490e8d316deb951a705eadbebeec7369c9c8ff3270c5eb4c4373
|
| 3 |
-
size 4878484277
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors.index.json
DELETED
|
@@ -1,915 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"metadata": {
|
| 3 |
-
"total_size": 10239266816,
|
| 4 |
-
"total_parameters": 8190735360
|
| 5 |
-
},
|
| 6 |
-
"weight_map": {
|
| 7 |
-
"lm_head.biases": "model-00002-of-00002.safetensors",
|
| 8 |
-
"lm_head.scales": "model-00002-of-00002.safetensors",
|
| 9 |
-
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 10 |
-
"model.embed_tokens.biases": "model-00001-of-00002.safetensors",
|
| 11 |
-
"model.embed_tokens.scales": "model-00001-of-00002.safetensors",
|
| 12 |
-
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 13 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
-
"model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 15 |
-
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 16 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
-
"model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 18 |
-
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 19 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
-
"model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 21 |
-
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 22 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
-
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
-
"model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 26 |
-
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 27 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
-
"model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 29 |
-
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 30 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
-
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
-
"model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 33 |
-
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 34 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
-
"model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 36 |
-
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 37 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
-
"model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 40 |
-
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 41 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
-
"model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 43 |
-
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 44 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
-
"model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 46 |
-
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 47 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
-
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
-
"model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 51 |
-
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 52 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
-
"model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 54 |
-
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 55 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
-
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
-
"model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 58 |
-
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 59 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
-
"model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 61 |
-
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 62 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
-
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
-
"model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 65 |
-
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 66 |
-
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
-
"model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 68 |
-
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 69 |
-
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
-
"model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 71 |
-
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 72 |
-
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
-
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
-
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
-
"model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 76 |
-
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 77 |
-
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
-
"model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 79 |
-
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 80 |
-
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
-
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
-
"model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 83 |
-
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 84 |
-
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
-
"model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 86 |
-
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 87 |
-
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
-
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
-
"model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 90 |
-
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 91 |
-
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
-
"model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 93 |
-
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 94 |
-
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
-
"model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 96 |
-
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 97 |
-
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
-
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 99 |
-
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 100 |
-
"model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 101 |
-
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 102 |
-
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
-
"model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 104 |
-
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 105 |
-
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
-
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
-
"model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 108 |
-
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 109 |
-
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
-
"model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 111 |
-
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 112 |
-
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
-
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
-
"model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 115 |
-
"model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 116 |
-
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
-
"model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 118 |
-
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 119 |
-
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
-
"model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 121 |
-
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 122 |
-
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
-
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
-
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
-
"model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 126 |
-
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 127 |
-
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
-
"model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 129 |
-
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 130 |
-
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
-
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 132 |
-
"model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 133 |
-
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 134 |
-
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
-
"model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 136 |
-
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 137 |
-
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
-
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 139 |
-
"model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 140 |
-
"model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 141 |
-
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
-
"model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 143 |
-
"model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 144 |
-
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
-
"model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 146 |
-
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 147 |
-
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
-
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
-
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
-
"model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 151 |
-
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 152 |
-
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
-
"model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 154 |
-
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 155 |
-
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
-
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
-
"model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 158 |
-
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 159 |
-
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
-
"model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 161 |
-
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 162 |
-
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
-
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 164 |
-
"model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 165 |
-
"model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 166 |
-
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
-
"model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 168 |
-
"model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 169 |
-
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
-
"model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 171 |
-
"model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 172 |
-
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
-
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 174 |
-
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 175 |
-
"model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 176 |
-
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 177 |
-
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
-
"model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 179 |
-
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 180 |
-
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
-
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 182 |
-
"model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 183 |
-
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 184 |
-
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
-
"model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 186 |
-
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 187 |
-
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
-
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 189 |
-
"model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 190 |
-
"model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 191 |
-
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
-
"model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 193 |
-
"model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 194 |
-
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
-
"model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 196 |
-
"model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 197 |
-
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
-
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 199 |
-
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 200 |
-
"model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 201 |
-
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 202 |
-
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
-
"model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 204 |
-
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 205 |
-
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
-
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 207 |
-
"model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 208 |
-
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 209 |
-
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
-
"model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 211 |
-
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 212 |
-
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
-
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
-
"model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 215 |
-
"model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 216 |
-
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
-
"model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 218 |
-
"model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 219 |
-
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
-
"model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 221 |
-
"model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 222 |
-
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
-
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 224 |
-
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 225 |
-
"model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 226 |
-
"model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 227 |
-
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
-
"model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 229 |
-
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 230 |
-
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
-
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 232 |
-
"model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 233 |
-
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 234 |
-
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
-
"model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 236 |
-
"model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 237 |
-
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 238 |
-
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 239 |
-
"model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 240 |
-
"model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 241 |
-
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 242 |
-
"model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 243 |
-
"model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 244 |
-
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
-
"model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 246 |
-
"model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 247 |
-
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
-
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 249 |
-
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 250 |
-
"model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 251 |
-
"model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 252 |
-
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
-
"model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 254 |
-
"model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 255 |
-
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
-
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 257 |
-
"model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 258 |
-
"model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 259 |
-
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
-
"model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 261 |
-
"model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 262 |
-
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
-
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 264 |
-
"model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 265 |
-
"model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 266 |
-
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
-
"model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 268 |
-
"model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 269 |
-
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
-
"model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 271 |
-
"model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 272 |
-
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
-
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 274 |
-
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 275 |
-
"model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 276 |
-
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 277 |
-
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
-
"model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 279 |
-
"model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 280 |
-
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
-
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 282 |
-
"model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 283 |
-
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 284 |
-
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
-
"model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 286 |
-
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 287 |
-
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
-
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
-
"model.layers.19.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 290 |
-
"model.layers.19.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 291 |
-
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
-
"model.layers.19.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 293 |
-
"model.layers.19.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 294 |
-
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
-
"model.layers.19.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 296 |
-
"model.layers.19.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 297 |
-
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
-
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 299 |
-
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
-
"model.layers.19.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 301 |
-
"model.layers.19.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 302 |
-
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
-
"model.layers.19.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 304 |
-
"model.layers.19.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 305 |
-
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
-
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 307 |
-
"model.layers.19.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 308 |
-
"model.layers.19.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 309 |
-
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
-
"model.layers.19.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 311 |
-
"model.layers.19.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 312 |
-
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 314 |
-
"model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 315 |
-
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 316 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
-
"model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 318 |
-
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 319 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
-
"model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 321 |
-
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 322 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
-
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
-
"model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 326 |
-
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 327 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
-
"model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 329 |
-
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 330 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
-
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 332 |
-
"model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 333 |
-
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 334 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
-
"model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 336 |
-
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 337 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 338 |
-
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 339 |
-
"model.layers.20.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 340 |
-
"model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 341 |
-
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
-
"model.layers.20.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 343 |
-
"model.layers.20.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 344 |
-
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 345 |
-
"model.layers.20.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 346 |
-
"model.layers.20.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 347 |
-
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
-
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
-
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 350 |
-
"model.layers.20.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 351 |
-
"model.layers.20.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 352 |
-
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 353 |
-
"model.layers.20.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 354 |
-
"model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 355 |
-
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 356 |
-
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 357 |
-
"model.layers.20.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 358 |
-
"model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 359 |
-
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 360 |
-
"model.layers.20.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 361 |
-
"model.layers.20.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 362 |
-
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 363 |
-
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 364 |
-
"model.layers.21.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 365 |
-
"model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 366 |
-
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 367 |
-
"model.layers.21.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 368 |
-
"model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 369 |
-
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 370 |
-
"model.layers.21.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 371 |
-
"model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 372 |
-
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 373 |
-
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 374 |
-
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 375 |
-
"model.layers.21.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 376 |
-
"model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 377 |
-
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 378 |
-
"model.layers.21.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 379 |
-
"model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 380 |
-
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 381 |
-
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 382 |
-
"model.layers.21.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 383 |
-
"model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 384 |
-
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 385 |
-
"model.layers.21.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 386 |
-
"model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 387 |
-
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 388 |
-
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 389 |
-
"model.layers.22.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 390 |
-
"model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 391 |
-
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 392 |
-
"model.layers.22.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 393 |
-
"model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 394 |
-
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 395 |
-
"model.layers.22.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 396 |
-
"model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 397 |
-
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 398 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 399 |
-
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 400 |
-
"model.layers.22.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 401 |
-
"model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 402 |
-
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 403 |
-
"model.layers.22.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 404 |
-
"model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 405 |
-
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 406 |
-
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 407 |
-
"model.layers.22.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 408 |
-
"model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 409 |
-
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 410 |
-
"model.layers.22.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 411 |
-
"model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 412 |
-
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 413 |
-
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 414 |
-
"model.layers.23.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 415 |
-
"model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 416 |
-
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 417 |
-
"model.layers.23.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 418 |
-
"model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 419 |
-
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 420 |
-
"model.layers.23.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 421 |
-
"model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 422 |
-
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 423 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 424 |
-
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 425 |
-
"model.layers.23.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 426 |
-
"model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 427 |
-
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 428 |
-
"model.layers.23.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 429 |
-
"model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 430 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 431 |
-
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 432 |
-
"model.layers.23.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 433 |
-
"model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 434 |
-
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 435 |
-
"model.layers.23.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 436 |
-
"model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 437 |
-
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 438 |
-
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 439 |
-
"model.layers.24.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 440 |
-
"model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 441 |
-
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 442 |
-
"model.layers.24.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 443 |
-
"model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 444 |
-
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 445 |
-
"model.layers.24.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 446 |
-
"model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 447 |
-
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 448 |
-
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 449 |
-
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 450 |
-
"model.layers.24.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 451 |
-
"model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 452 |
-
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 453 |
-
"model.layers.24.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 454 |
-
"model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 455 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 456 |
-
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 457 |
-
"model.layers.24.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 458 |
-
"model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 459 |
-
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 460 |
-
"model.layers.24.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 461 |
-
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 462 |
-
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 463 |
-
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 464 |
-
"model.layers.25.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 465 |
-
"model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 466 |
-
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 467 |
-
"model.layers.25.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 468 |
-
"model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 469 |
-
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 470 |
-
"model.layers.25.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 471 |
-
"model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 472 |
-
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 473 |
-
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 474 |
-
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 475 |
-
"model.layers.25.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 476 |
-
"model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 477 |
-
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 478 |
-
"model.layers.25.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 479 |
-
"model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 480 |
-
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 481 |
-
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 482 |
-
"model.layers.25.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 483 |
-
"model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 484 |
-
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 485 |
-
"model.layers.25.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 486 |
-
"model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 487 |
-
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 488 |
-
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 489 |
-
"model.layers.26.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 490 |
-
"model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 491 |
-
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 492 |
-
"model.layers.26.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 493 |
-
"model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 494 |
-
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 495 |
-
"model.layers.26.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 496 |
-
"model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 497 |
-
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 498 |
-
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 499 |
-
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 500 |
-
"model.layers.26.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 501 |
-
"model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 502 |
-
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 503 |
-
"model.layers.26.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 504 |
-
"model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 505 |
-
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 506 |
-
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 507 |
-
"model.layers.26.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 508 |
-
"model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 509 |
-
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 510 |
-
"model.layers.26.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 511 |
-
"model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 512 |
-
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 513 |
-
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 514 |
-
"model.layers.27.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 515 |
-
"model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 516 |
-
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 517 |
-
"model.layers.27.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 518 |
-
"model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 519 |
-
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 520 |
-
"model.layers.27.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 521 |
-
"model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 522 |
-
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 523 |
-
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 524 |
-
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 525 |
-
"model.layers.27.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 526 |
-
"model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 527 |
-
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 528 |
-
"model.layers.27.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 529 |
-
"model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 530 |
-
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 531 |
-
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 532 |
-
"model.layers.27.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 533 |
-
"model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 534 |
-
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 535 |
-
"model.layers.27.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 536 |
-
"model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 537 |
-
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 538 |
-
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 539 |
-
"model.layers.28.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 540 |
-
"model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 541 |
-
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 542 |
-
"model.layers.28.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 543 |
-
"model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 544 |
-
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 545 |
-
"model.layers.28.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 546 |
-
"model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 547 |
-
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 548 |
-
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 549 |
-
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 550 |
-
"model.layers.28.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 551 |
-
"model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 552 |
-
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 553 |
-
"model.layers.28.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 554 |
-
"model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 555 |
-
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 556 |
-
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 557 |
-
"model.layers.28.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 558 |
-
"model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 559 |
-
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 560 |
-
"model.layers.28.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 561 |
-
"model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 562 |
-
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 563 |
-
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 564 |
-
"model.layers.29.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 565 |
-
"model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 566 |
-
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 567 |
-
"model.layers.29.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 568 |
-
"model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 569 |
-
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 570 |
-
"model.layers.29.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 571 |
-
"model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 572 |
-
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 573 |
-
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 574 |
-
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 575 |
-
"model.layers.29.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 576 |
-
"model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 577 |
-
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 578 |
-
"model.layers.29.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 579 |
-
"model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 580 |
-
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 581 |
-
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 582 |
-
"model.layers.29.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 583 |
-
"model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 584 |
-
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 585 |
-
"model.layers.29.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 586 |
-
"model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 587 |
-
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 588 |
-
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 589 |
-
"model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 590 |
-
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 591 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
-
"model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 593 |
-
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 594 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 595 |
-
"model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 596 |
-
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 597 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 599 |
-
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 600 |
-
"model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 601 |
-
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 602 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 603 |
-
"model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 604 |
-
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 605 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 606 |
-
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 607 |
-
"model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 608 |
-
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 609 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
-
"model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 611 |
-
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 612 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 613 |
-
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 614 |
-
"model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 615 |
-
"model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 616 |
-
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 617 |
-
"model.layers.30.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 618 |
-
"model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 619 |
-
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 620 |
-
"model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 621 |
-
"model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 622 |
-
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 623 |
-
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 624 |
-
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 625 |
-
"model.layers.30.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 626 |
-
"model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 627 |
-
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 628 |
-
"model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 629 |
-
"model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 630 |
-
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 631 |
-
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 632 |
-
"model.layers.30.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 633 |
-
"model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 634 |
-
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 635 |
-
"model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 636 |
-
"model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 637 |
-
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 638 |
-
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 639 |
-
"model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 640 |
-
"model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 641 |
-
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 642 |
-
"model.layers.31.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 643 |
-
"model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 644 |
-
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 645 |
-
"model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 646 |
-
"model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 647 |
-
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 648 |
-
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 649 |
-
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 650 |
-
"model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 651 |
-
"model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 652 |
-
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 653 |
-
"model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 654 |
-
"model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 655 |
-
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 656 |
-
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 657 |
-
"model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 658 |
-
"model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 659 |
-
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 660 |
-
"model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 661 |
-
"model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 662 |
-
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
-
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 664 |
-
"model.layers.32.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 665 |
-
"model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 666 |
-
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 667 |
-
"model.layers.32.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 668 |
-
"model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 669 |
-
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 670 |
-
"model.layers.32.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 671 |
-
"model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 672 |
-
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 673 |
-
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 674 |
-
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 675 |
-
"model.layers.32.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 676 |
-
"model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 677 |
-
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 678 |
-
"model.layers.32.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 679 |
-
"model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 680 |
-
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 681 |
-
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 682 |
-
"model.layers.32.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 683 |
-
"model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 684 |
-
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 685 |
-
"model.layers.32.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 686 |
-
"model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 687 |
-
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 688 |
-
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 689 |
-
"model.layers.33.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 690 |
-
"model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 691 |
-
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 692 |
-
"model.layers.33.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 693 |
-
"model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 694 |
-
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 695 |
-
"model.layers.33.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 696 |
-
"model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 697 |
-
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 698 |
-
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 699 |
-
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 700 |
-
"model.layers.33.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 701 |
-
"model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 702 |
-
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 703 |
-
"model.layers.33.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 704 |
-
"model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 705 |
-
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 706 |
-
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 707 |
-
"model.layers.33.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 708 |
-
"model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 709 |
-
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 710 |
-
"model.layers.33.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 711 |
-
"model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 712 |
-
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 713 |
-
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 714 |
-
"model.layers.34.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 715 |
-
"model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 716 |
-
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 717 |
-
"model.layers.34.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 718 |
-
"model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 719 |
-
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 720 |
-
"model.layers.34.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 721 |
-
"model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 722 |
-
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 723 |
-
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 724 |
-
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 725 |
-
"model.layers.34.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 726 |
-
"model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 727 |
-
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 728 |
-
"model.layers.34.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 729 |
-
"model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 730 |
-
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 731 |
-
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 732 |
-
"model.layers.34.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 733 |
-
"model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 734 |
-
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 735 |
-
"model.layers.34.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 736 |
-
"model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 737 |
-
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 738 |
-
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 739 |
-
"model.layers.35.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 740 |
-
"model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 741 |
-
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 742 |
-
"model.layers.35.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 743 |
-
"model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 744 |
-
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 745 |
-
"model.layers.35.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 746 |
-
"model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 747 |
-
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 748 |
-
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 749 |
-
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 750 |
-
"model.layers.35.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 751 |
-
"model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 752 |
-
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 753 |
-
"model.layers.35.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 754 |
-
"model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 755 |
-
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 756 |
-
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 757 |
-
"model.layers.35.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 758 |
-
"model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 759 |
-
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 760 |
-
"model.layers.35.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 761 |
-
"model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 762 |
-
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 763 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 764 |
-
"model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 765 |
-
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 766 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 767 |
-
"model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 768 |
-
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 769 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
-
"model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 771 |
-
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 772 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 773 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 774 |
-
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 775 |
-
"model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 776 |
-
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 777 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 778 |
-
"model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 779 |
-
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 780 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 781 |
-
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 782 |
-
"model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 783 |
-
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 784 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 785 |
-
"model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 786 |
-
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 787 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 788 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 789 |
-
"model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 790 |
-
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 791 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 792 |
-
"model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 793 |
-
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 794 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 795 |
-
"model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 796 |
-
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 797 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 798 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 799 |
-
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 800 |
-
"model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 801 |
-
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 802 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 803 |
-
"model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 804 |
-
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 805 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 806 |
-
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 807 |
-
"model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 808 |
-
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 809 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 810 |
-
"model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 811 |
-
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 812 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 813 |
-
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 814 |
-
"model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 815 |
-
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 816 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 817 |
-
"model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 818 |
-
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 819 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 820 |
-
"model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 821 |
-
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 822 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 823 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 824 |
-
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 825 |
-
"model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 826 |
-
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 827 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 828 |
-
"model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 829 |
-
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 830 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 831 |
-
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 832 |
-
"model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 833 |
-
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 834 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 835 |
-
"model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 836 |
-
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 837 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 838 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 839 |
-
"model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 840 |
-
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 841 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 842 |
-
"model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 843 |
-
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 844 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 845 |
-
"model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 846 |
-
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 847 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 848 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 849 |
-
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 850 |
-
"model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 851 |
-
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 852 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 853 |
-
"model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 854 |
-
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 855 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 856 |
-
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 857 |
-
"model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 858 |
-
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 859 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 860 |
-
"model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 861 |
-
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 862 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 863 |
-
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 864 |
-
"model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 865 |
-
"model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 866 |
-
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 867 |
-
"model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 868 |
-
"model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 869 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 870 |
-
"model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 871 |
-
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 872 |
-
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 873 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 874 |
-
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 875 |
-
"model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 876 |
-
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 877 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 878 |
-
"model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 879 |
-
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 880 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 881 |
-
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 882 |
-
"model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 883 |
-
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 884 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 885 |
-
"model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 886 |
-
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 887 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 888 |
-
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 889 |
-
"model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 890 |
-
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 891 |
-
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 892 |
-
"model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 893 |
-
"model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 894 |
-
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 895 |
-
"model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 896 |
-
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 897 |
-
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 898 |
-
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 899 |
-
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 900 |
-
"model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 901 |
-
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 902 |
-
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 903 |
-
"model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 904 |
-
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 905 |
-
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 906 |
-
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 907 |
-
"model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 908 |
-
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 909 |
-
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 910 |
-
"model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 911 |
-
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 912 |
-
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 913 |
-
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 914 |
-
}
|
| 915 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|im_start|>",
|
| 4 |
-
"<|im_end|>",
|
| 5 |
-
"<|object_ref_start|>",
|
| 6 |
-
"<|object_ref_end|>",
|
| 7 |
-
"<|box_start|>",
|
| 8 |
-
"<|box_end|>",
|
| 9 |
-
"<|quad_start|>",
|
| 10 |
-
"<|quad_end|>",
|
| 11 |
-
"<|vision_start|>",
|
| 12 |
-
"<|vision_end|>",
|
| 13 |
-
"<|vision_pad|>",
|
| 14 |
-
"<|image_pad|>",
|
| 15 |
-
"<|video_pad|>"
|
| 16 |
-
],
|
| 17 |
-
"eos_token": {
|
| 18 |
-
"content": "<|im_end|>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
},
|
| 24 |
-
"pad_token": {
|
| 25 |
-
"content": "<|endoftext|>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": false,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
}
|
| 31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
-
size 11422654
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer_config.json
DELETED
|
@@ -1,239 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
-
"add_prefix_space": false,
|
| 4 |
-
"added_tokens_decoder": {
|
| 5 |
-
"151643": {
|
| 6 |
-
"content": "<|endoftext|>",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false,
|
| 11 |
-
"special": true
|
| 12 |
-
},
|
| 13 |
-
"151644": {
|
| 14 |
-
"content": "<|im_start|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"151645": {
|
| 22 |
-
"content": "<|im_end|>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
},
|
| 29 |
-
"151646": {
|
| 30 |
-
"content": "<|object_ref_start|>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
-
},
|
| 37 |
-
"151647": {
|
| 38 |
-
"content": "<|object_ref_end|>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false,
|
| 43 |
-
"special": true
|
| 44 |
-
},
|
| 45 |
-
"151648": {
|
| 46 |
-
"content": "<|box_start|>",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
-
},
|
| 53 |
-
"151649": {
|
| 54 |
-
"content": "<|box_end|>",
|
| 55 |
-
"lstrip": false,
|
| 56 |
-
"normalized": false,
|
| 57 |
-
"rstrip": false,
|
| 58 |
-
"single_word": false,
|
| 59 |
-
"special": true
|
| 60 |
-
},
|
| 61 |
-
"151650": {
|
| 62 |
-
"content": "<|quad_start|>",
|
| 63 |
-
"lstrip": false,
|
| 64 |
-
"normalized": false,
|
| 65 |
-
"rstrip": false,
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"special": true
|
| 68 |
-
},
|
| 69 |
-
"151651": {
|
| 70 |
-
"content": "<|quad_end|>",
|
| 71 |
-
"lstrip": false,
|
| 72 |
-
"normalized": false,
|
| 73 |
-
"rstrip": false,
|
| 74 |
-
"single_word": false,
|
| 75 |
-
"special": true
|
| 76 |
-
},
|
| 77 |
-
"151652": {
|
| 78 |
-
"content": "<|vision_start|>",
|
| 79 |
-
"lstrip": false,
|
| 80 |
-
"normalized": false,
|
| 81 |
-
"rstrip": false,
|
| 82 |
-
"single_word": false,
|
| 83 |
-
"special": true
|
| 84 |
-
},
|
| 85 |
-
"151653": {
|
| 86 |
-
"content": "<|vision_end|>",
|
| 87 |
-
"lstrip": false,
|
| 88 |
-
"normalized": false,
|
| 89 |
-
"rstrip": false,
|
| 90 |
-
"single_word": false,
|
| 91 |
-
"special": true
|
| 92 |
-
},
|
| 93 |
-
"151654": {
|
| 94 |
-
"content": "<|vision_pad|>",
|
| 95 |
-
"lstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"rstrip": false,
|
| 98 |
-
"single_word": false,
|
| 99 |
-
"special": true
|
| 100 |
-
},
|
| 101 |
-
"151655": {
|
| 102 |
-
"content": "<|image_pad|>",
|
| 103 |
-
"lstrip": false,
|
| 104 |
-
"normalized": false,
|
| 105 |
-
"rstrip": false,
|
| 106 |
-
"single_word": false,
|
| 107 |
-
"special": true
|
| 108 |
-
},
|
| 109 |
-
"151656": {
|
| 110 |
-
"content": "<|video_pad|>",
|
| 111 |
-
"lstrip": false,
|
| 112 |
-
"normalized": false,
|
| 113 |
-
"rstrip": false,
|
| 114 |
-
"single_word": false,
|
| 115 |
-
"special": true
|
| 116 |
-
},
|
| 117 |
-
"151657": {
|
| 118 |
-
"content": "<tool_call>",
|
| 119 |
-
"lstrip": false,
|
| 120 |
-
"normalized": false,
|
| 121 |
-
"rstrip": false,
|
| 122 |
-
"single_word": false,
|
| 123 |
-
"special": false
|
| 124 |
-
},
|
| 125 |
-
"151658": {
|
| 126 |
-
"content": "</tool_call>",
|
| 127 |
-
"lstrip": false,
|
| 128 |
-
"normalized": false,
|
| 129 |
-
"rstrip": false,
|
| 130 |
-
"single_word": false,
|
| 131 |
-
"special": false
|
| 132 |
-
},
|
| 133 |
-
"151659": {
|
| 134 |
-
"content": "<|fim_prefix|>",
|
| 135 |
-
"lstrip": false,
|
| 136 |
-
"normalized": false,
|
| 137 |
-
"rstrip": false,
|
| 138 |
-
"single_word": false,
|
| 139 |
-
"special": false
|
| 140 |
-
},
|
| 141 |
-
"151660": {
|
| 142 |
-
"content": "<|fim_middle|>",
|
| 143 |
-
"lstrip": false,
|
| 144 |
-
"normalized": false,
|
| 145 |
-
"rstrip": false,
|
| 146 |
-
"single_word": false,
|
| 147 |
-
"special": false
|
| 148 |
-
},
|
| 149 |
-
"151661": {
|
| 150 |
-
"content": "<|fim_suffix|>",
|
| 151 |
-
"lstrip": false,
|
| 152 |
-
"normalized": false,
|
| 153 |
-
"rstrip": false,
|
| 154 |
-
"single_word": false,
|
| 155 |
-
"special": false
|
| 156 |
-
},
|
| 157 |
-
"151662": {
|
| 158 |
-
"content": "<|fim_pad|>",
|
| 159 |
-
"lstrip": false,
|
| 160 |
-
"normalized": false,
|
| 161 |
-
"rstrip": false,
|
| 162 |
-
"single_word": false,
|
| 163 |
-
"special": false
|
| 164 |
-
},
|
| 165 |
-
"151663": {
|
| 166 |
-
"content": "<|repo_name|>",
|
| 167 |
-
"lstrip": false,
|
| 168 |
-
"normalized": false,
|
| 169 |
-
"rstrip": false,
|
| 170 |
-
"single_word": false,
|
| 171 |
-
"special": false
|
| 172 |
-
},
|
| 173 |
-
"151664": {
|
| 174 |
-
"content": "<|file_sep|>",
|
| 175 |
-
"lstrip": false,
|
| 176 |
-
"normalized": false,
|
| 177 |
-
"rstrip": false,
|
| 178 |
-
"single_word": false,
|
| 179 |
-
"special": false
|
| 180 |
-
},
|
| 181 |
-
"151665": {
|
| 182 |
-
"content": "<tool_response>",
|
| 183 |
-
"lstrip": false,
|
| 184 |
-
"normalized": false,
|
| 185 |
-
"rstrip": false,
|
| 186 |
-
"single_word": false,
|
| 187 |
-
"special": false
|
| 188 |
-
},
|
| 189 |
-
"151666": {
|
| 190 |
-
"content": "</tool_response>",
|
| 191 |
-
"lstrip": false,
|
| 192 |
-
"normalized": false,
|
| 193 |
-
"rstrip": false,
|
| 194 |
-
"single_word": false,
|
| 195 |
-
"special": false
|
| 196 |
-
},
|
| 197 |
-
"151667": {
|
| 198 |
-
"content": "<think>",
|
| 199 |
-
"lstrip": false,
|
| 200 |
-
"normalized": false,
|
| 201 |
-
"rstrip": false,
|
| 202 |
-
"single_word": false,
|
| 203 |
-
"special": false
|
| 204 |
-
},
|
| 205 |
-
"151668": {
|
| 206 |
-
"content": "</think>",
|
| 207 |
-
"lstrip": false,
|
| 208 |
-
"normalized": false,
|
| 209 |
-
"rstrip": false,
|
| 210 |
-
"single_word": false,
|
| 211 |
-
"special": false
|
| 212 |
-
}
|
| 213 |
-
},
|
| 214 |
-
"additional_special_tokens": [
|
| 215 |
-
"<|im_start|>",
|
| 216 |
-
"<|im_end|>",
|
| 217 |
-
"<|object_ref_start|>",
|
| 218 |
-
"<|object_ref_end|>",
|
| 219 |
-
"<|box_start|>",
|
| 220 |
-
"<|box_end|>",
|
| 221 |
-
"<|quad_start|>",
|
| 222 |
-
"<|quad_end|>",
|
| 223 |
-
"<|vision_start|>",
|
| 224 |
-
"<|vision_end|>",
|
| 225 |
-
"<|vision_pad|>",
|
| 226 |
-
"<|image_pad|>",
|
| 227 |
-
"<|video_pad|>"
|
| 228 |
-
],
|
| 229 |
-
"bos_token": null,
|
| 230 |
-
"clean_up_tokenization_spaces": false,
|
| 231 |
-
"eos_token": "<|im_end|>",
|
| 232 |
-
"errors": "replace",
|
| 233 |
-
"extra_special_tokens": {},
|
| 234 |
-
"model_max_length": 131072,
|
| 235 |
-
"pad_token": "<|endoftext|>",
|
| 236 |
-
"split_special_tokens": false,
|
| 237 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
-
"unk_token": null
|
| 239 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|