Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +10 -44
- added_tokens.json +25 -0
- chat_template.jinja +54 -0
- config.json +17 -19
- generation_config.json +15 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +448 -119
- special_tokens_map.json +18 -17
- tokenizer.json +0 -0
- tokenizer_config.json +119 -694
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,50 +1,16 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
datasets:
|
| 4 |
-
- CycloneDX/cdx-docs
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
-
base_model:
|
| 8 |
-
- unsloth/phi-4
|
| 9 |
library_name: mlx
|
|
|
|
| 10 |
tags:
|
| 11 |
-
-
|
| 12 |
-
-
|
| 13 |
-
-
|
| 14 |
-
-
|
| 15 |
-
-
|
| 16 |
-
-
|
| 17 |
-
-
|
| 18 |
-
-
|
| 19 |
---
|
| 20 |
-
|
| 21 |
-
**PREVIEW RELEASE**
|
| 22 |
-
|
| 23 |
-
## Testing with LM Studio
|
| 24 |
-
|
| 25 |
-
Use [LM Studio](https://lmstudio.ai/docs/basics/download-model) to download and test this model. Search for `CycloneDX/cdx1-mlx-4bit`.
|
| 26 |
-
|
| 27 |
-
Use the below configurations:
|
| 28 |
-
|
| 29 |
-
```
|
| 30 |
-
System Prompt: `You are a helpful assistant to the user.` Use Prompt [Template](https://lmstudio.ai/docs/advanced/prompt-template).
|
| 31 |
-
Temperature: 0.05
|
| 32 |
-
Max tokens: 8192 or 16000
|
| 33 |
-
Context length: 16000
|
| 34 |
-
```
|
| 35 |
-
|
| 36 |
-
## Testing with mlx
|
| 37 |
-
|
| 38 |
-
Install [miniconda](https://docs.anaconda.com/miniconda/install/) or Python 3.11
|
| 39 |
-
|
| 40 |
-
```
|
| 41 |
-
conda create --name cdx1-mlx python=3.11
|
| 42 |
-
conda activate cdx1-mlx
|
| 43 |
-
pip install mlx
|
| 44 |
-
```
|
| 45 |
-
|
| 46 |
-
LLM Inference from the CLI.
|
| 47 |
-
|
| 48 |
-
```shell
|
| 49 |
-
mlx_lm.generate --model CycloneDX/cdx1-mlx-4bit --system-prompt "You are a helpful assistant to the user." --prompt "tell me about cdxgen" --temp 0.05
|
| 50 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/Qwen2.5-Coder-14B-Instruct
|
|
|
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
|
|
|
| 5 |
library_name: mlx
|
| 6 |
+
license: apache-2.0
|
| 7 |
tags:
|
| 8 |
+
- unsloth
|
| 9 |
+
- transformers
|
| 10 |
+
- code
|
| 11 |
+
- qwen
|
| 12 |
+
- qwen-coder
|
| 13 |
+
- codeqwen
|
| 14 |
+
- mlx
|
| 15 |
+
pipeline_tag: text-generation
|
| 16 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
added_tokens.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|PAD_TOKEN|>": 151665,
|
| 5 |
+
"<|box_end|>": 151649,
|
| 6 |
+
"<|box_start|>": 151648,
|
| 7 |
+
"<|endoftext|>": 151643,
|
| 8 |
+
"<|file_sep|>": 151664,
|
| 9 |
+
"<|fim_middle|>": 151660,
|
| 10 |
+
"<|fim_pad|>": 151662,
|
| 11 |
+
"<|fim_prefix|>": 151659,
|
| 12 |
+
"<|fim_suffix|>": 151661,
|
| 13 |
+
"<|im_end|>": 151645,
|
| 14 |
+
"<|im_start|>": 151644,
|
| 15 |
+
"<|image_pad|>": 151655,
|
| 16 |
+
"<|object_ref_end|>": 151647,
|
| 17 |
+
"<|object_ref_start|>": 151646,
|
| 18 |
+
"<|quad_end|>": 151651,
|
| 19 |
+
"<|quad_start|>": 151650,
|
| 20 |
+
"<|repo_name|>": 151663,
|
| 21 |
+
"<|video_pad|>": 151656,
|
| 22 |
+
"<|vision_end|>": 151653,
|
| 23 |
+
"<|vision_pad|>": 151654,
|
| 24 |
+
"<|vision_start|>": 151652
|
| 25 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# 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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
config.json
CHANGED
|
@@ -1,25 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id":
|
| 8 |
-
"eos_token_id":
|
| 9 |
-
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 5120,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size":
|
| 14 |
-
"max_position_embeddings":
|
| 15 |
-
"
|
| 16 |
-
"model_type": "
|
| 17 |
"num_attention_heads": 40,
|
| 18 |
-
"num_hidden_layers":
|
| 19 |
-
"num_key_value_heads":
|
| 20 |
-
"
|
| 21 |
-
"pad_token_id": 100351,
|
| 22 |
-
"pretraining_tp": 1,
|
| 23 |
"quantization": {
|
| 24 |
"group_size": 64,
|
| 25 |
"bits": 4
|
|
@@ -28,12 +24,14 @@
|
|
| 28 |
"group_size": 64,
|
| 29 |
"bits": 4
|
| 30 |
},
|
| 31 |
-
"rms_norm_eps": 1e-
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
"tie_word_embeddings": false,
|
| 35 |
"torch_dtype": "bfloat16",
|
| 36 |
-
"transformers_version": "4.
|
|
|
|
| 37 |
"use_cache": true,
|
| 38 |
-
"
|
|
|
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
],
|
|
|
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
|
|
|
| 8 |
"hidden_act": "silu",
|
| 9 |
"hidden_size": 5120,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 13824,
|
| 12 |
+
"max_position_embeddings": 32768,
|
| 13 |
+
"max_window_layers": 70,
|
| 14 |
+
"model_type": "qwen2",
|
| 15 |
"num_attention_heads": 40,
|
| 16 |
+
"num_hidden_layers": 48,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"pad_token_id": 151665,
|
|
|
|
|
|
|
| 19 |
"quantization": {
|
| 20 |
"group_size": 64,
|
| 21 |
"bits": 4
|
|
|
|
| 24 |
"group_size": 64,
|
| 25 |
"bits": 4
|
| 26 |
},
|
| 27 |
+
"rms_norm_eps": 1e-06,
|
| 28 |
+
"rope_theta": 1000000.0,
|
| 29 |
+
"sliding_window": null,
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.44.2",
|
| 33 |
+
"unsloth_fixed": true,
|
| 34 |
"use_cache": true,
|
| 35 |
+
"use_sliding_window": false,
|
| 36 |
+
"vocab_size": 152064
|
| 37 |
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"max_length": 32768,
|
| 9 |
+
"pad_token_id": 151665,
|
| 10 |
+
"repetition_penalty": 1.05,
|
| 11 |
+
"temperature": 0.7,
|
| 12 |
+
"top_k": 20,
|
| 13 |
+
"top_p": 0.8,
|
| 14 |
+
"transformers_version": "4.44.2"
|
| 15 |
+
}
|
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:556847c8adf276c9f865d6264dbeb4c3b1fbebf0470428a2d94ad79563f8b51c
|
| 3 |
+
size 5353840945
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2694a2b921770c3749aa7e72ac372a821e978e37aee37dc70ffe2847440b5c32
|
| 3 |
+
size 2955654333
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
|
|
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.biases": "model-00002-of-00002.safetensors",
|
|
@@ -20,15 +21,18 @@
|
|
| 20 |
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 21 |
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 23 |
"model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 24 |
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 25 |
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
"model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 27 |
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 28 |
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 29 |
"model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 30 |
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 31 |
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 32 |
"model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 33 |
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 34 |
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -43,15 +47,18 @@
|
|
| 43 |
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 44 |
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 46 |
"model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 47 |
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 48 |
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
"model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 50 |
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 51 |
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 52 |
"model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 53 |
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 54 |
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 55 |
"model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 56 |
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 57 |
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -66,15 +73,18 @@
|
|
| 66 |
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 67 |
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 69 |
"model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 70 |
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 71 |
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
"model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 73 |
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 74 |
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 75 |
"model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 76 |
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 77 |
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 78 |
"model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 79 |
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 80 |
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -89,15 +99,18 @@
|
|
| 89 |
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 90 |
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 92 |
"model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 93 |
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 94 |
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
"model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 96 |
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 97 |
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 98 |
"model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 99 |
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 100 |
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 101 |
"model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 102 |
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 103 |
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -112,15 +125,18 @@
|
|
| 112 |
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 113 |
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 115 |
"model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 116 |
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 117 |
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
"model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 119 |
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 120 |
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 121 |
"model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 122 |
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 123 |
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 124 |
"model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 125 |
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 126 |
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -135,15 +151,18 @@
|
|
| 135 |
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 136 |
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 138 |
"model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 139 |
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 140 |
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
"model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 142 |
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 143 |
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 144 |
"model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 145 |
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 146 |
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 147 |
"model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 148 |
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 149 |
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -158,15 +177,18 @@
|
|
| 158 |
"model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 159 |
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 161 |
"model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 162 |
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 163 |
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
"model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 165 |
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 166 |
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 167 |
"model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 168 |
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 169 |
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 170 |
"model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 171 |
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 172 |
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -181,15 +203,18 @@
|
|
| 181 |
"model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 182 |
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 184 |
"model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 185 |
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 186 |
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
"model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 188 |
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 189 |
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 190 |
"model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 191 |
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 192 |
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 193 |
"model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 194 |
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 195 |
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -204,15 +229,18 @@
|
|
| 204 |
"model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 205 |
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 207 |
"model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 208 |
"model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 209 |
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
"model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 211 |
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 212 |
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 213 |
"model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 214 |
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 215 |
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 216 |
"model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 217 |
"model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 218 |
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -227,15 +255,18 @@
|
|
| 227 |
"model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 228 |
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 230 |
"model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 231 |
"model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 232 |
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
"model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 234 |
"model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 235 |
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 236 |
"model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 237 |
"model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 238 |
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 239 |
"model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 240 |
"model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 241 |
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -250,15 +281,18 @@
|
|
| 250 |
"model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 251 |
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 253 |
"model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 254 |
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 255 |
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
"model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 257 |
"model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 258 |
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 259 |
"model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 260 |
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 261 |
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 262 |
"model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 263 |
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 264 |
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -273,15 +307,18 @@
|
|
| 273 |
"model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 274 |
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 276 |
"model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 277 |
"model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 278 |
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
"model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 280 |
"model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 281 |
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 282 |
"model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 283 |
"model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 284 |
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 285 |
"model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 286 |
"model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 287 |
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -296,15 +333,18 @@
|
|
| 296 |
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 297 |
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 299 |
"model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 300 |
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 301 |
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 302 |
"model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 303 |
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 304 |
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 305 |
"model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 306 |
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 307 |
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 308 |
"model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 309 |
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 310 |
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -319,15 +359,18 @@
|
|
| 319 |
"model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 320 |
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 322 |
"model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 323 |
"model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 324 |
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
"model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 326 |
"model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 327 |
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 328 |
"model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 329 |
"model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 330 |
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 331 |
"model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 332 |
"model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 333 |
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -342,15 +385,18 @@
|
|
| 342 |
"model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 343 |
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 345 |
"model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 346 |
"model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 347 |
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
"model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 349 |
"model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 350 |
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 351 |
"model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 352 |
"model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 353 |
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 354 |
"model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 355 |
"model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 356 |
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -365,15 +411,18 @@
|
|
| 365 |
"model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 366 |
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 368 |
"model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 369 |
"model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 370 |
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
"model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 372 |
"model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 373 |
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 374 |
"model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 375 |
"model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 376 |
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 377 |
"model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 378 |
"model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 379 |
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -388,15 +437,18 @@
|
|
| 388 |
"model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 389 |
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 391 |
"model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 392 |
"model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 393 |
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
"model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 395 |
"model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 396 |
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 397 |
"model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 398 |
"model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 399 |
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 400 |
"model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 401 |
"model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 402 |
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -411,15 +463,18 @@
|
|
| 411 |
"model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 412 |
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 414 |
"model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 415 |
"model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 416 |
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
"model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 418 |
"model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 419 |
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 420 |
"model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 421 |
"model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 422 |
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 423 |
"model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 424 |
"model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 425 |
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -434,110 +489,125 @@
|
|
| 434 |
"model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 435 |
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 437 |
"model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 438 |
"model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 439 |
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 440 |
"model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 441 |
"model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 442 |
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 443 |
"model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 444 |
"model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 445 |
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 446 |
"model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 447 |
"model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 448 |
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 449 |
-
"model.layers.26.input_layernorm.weight": "model-
|
| 450 |
-
"model.layers.26.mlp.down_proj.biases": "model-
|
| 451 |
-
"model.layers.26.mlp.down_proj.scales": "model-
|
| 452 |
-
"model.layers.26.mlp.down_proj.weight": "model-
|
| 453 |
"model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 454 |
"model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 455 |
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 456 |
-
"model.layers.26.mlp.up_proj.biases": "model-
|
| 457 |
-
"model.layers.26.mlp.up_proj.scales": "model-
|
| 458 |
-
"model.layers.26.mlp.up_proj.weight": "model-
|
| 459 |
-
"model.layers.26.post_attention_layernorm.weight": "model-
|
|
|
|
| 460 |
"model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 461 |
"model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 462 |
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 463 |
"model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 464 |
"model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 465 |
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 466 |
"model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 467 |
"model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 468 |
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 469 |
"model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 470 |
"model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 471 |
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 472 |
-
"model.layers.27.input_layernorm.weight": "model-
|
| 473 |
-
"model.layers.27.mlp.down_proj.biases": "model-
|
| 474 |
-
"model.layers.27.mlp.down_proj.scales": "model-
|
| 475 |
-
"model.layers.27.mlp.down_proj.weight": "model-
|
| 476 |
-
"model.layers.27.mlp.gate_proj.biases": "model-
|
| 477 |
-
"model.layers.27.mlp.gate_proj.scales": "model-
|
| 478 |
-
"model.layers.27.mlp.gate_proj.weight": "model-
|
| 479 |
-
"model.layers.27.mlp.up_proj.biases": "model-
|
| 480 |
-
"model.layers.27.mlp.up_proj.scales": "model-
|
| 481 |
-
"model.layers.27.mlp.up_proj.weight": "model-
|
| 482 |
-
"model.layers.27.post_attention_layernorm.weight": "model-
|
| 483 |
-
"model.layers.27.self_attn.k_proj.
|
| 484 |
-
"model.layers.27.self_attn.k_proj.
|
| 485 |
-
"model.layers.27.self_attn.k_proj.
|
| 486 |
-
"model.layers.27.self_attn.
|
| 487 |
-
"model.layers.27.self_attn.o_proj.
|
| 488 |
-
"model.layers.27.self_attn.o_proj.
|
| 489 |
-
"model.layers.27.self_attn.
|
| 490 |
-
"model.layers.27.self_attn.q_proj.
|
| 491 |
-
"model.layers.27.self_attn.q_proj.
|
| 492 |
-
"model.layers.27.self_attn.
|
| 493 |
-
"model.layers.27.self_attn.
|
| 494 |
-
"model.layers.27.self_attn.v_proj.
|
| 495 |
-
"model.layers.
|
| 496 |
-
"model.layers.
|
| 497 |
-
"model.layers.
|
| 498 |
-
"model.layers.28.
|
| 499 |
-
"model.layers.28.mlp.
|
| 500 |
-
"model.layers.28.mlp.
|
| 501 |
-
"model.layers.28.mlp.
|
| 502 |
-
"model.layers.28.mlp.
|
| 503 |
-
"model.layers.28.mlp.
|
| 504 |
-
"model.layers.28.mlp.
|
| 505 |
-
"model.layers.28.
|
| 506 |
-
"model.layers.28.
|
| 507 |
-
"model.layers.28.
|
| 508 |
-
"model.layers.28.
|
| 509 |
-
"model.layers.28.self_attn.
|
| 510 |
-
"model.layers.28.self_attn.
|
| 511 |
-
"model.layers.28.self_attn.
|
| 512 |
-
"model.layers.28.self_attn.
|
| 513 |
-
"model.layers.28.self_attn.
|
| 514 |
-
"model.layers.28.self_attn.
|
| 515 |
-
"model.layers.28.self_attn.
|
| 516 |
-
"model.layers.28.self_attn.
|
| 517 |
-
"model.layers.28.self_attn.
|
| 518 |
-
"model.layers.
|
| 519 |
-
"model.layers.
|
| 520 |
-
"model.layers.
|
| 521 |
-
"model.layers.
|
| 522 |
-
"model.layers.
|
| 523 |
-
"model.layers.
|
| 524 |
-
"model.layers.29.
|
| 525 |
-
"model.layers.29.mlp.
|
| 526 |
-
"model.layers.29.mlp.
|
| 527 |
-
"model.layers.29.mlp.
|
| 528 |
-
"model.layers.29.
|
| 529 |
-
"model.layers.29.
|
| 530 |
-
"model.layers.29.
|
| 531 |
-
"model.layers.29.
|
| 532 |
-
"model.layers.29.
|
| 533 |
-
"model.layers.29.
|
| 534 |
-
"model.layers.29.
|
| 535 |
-
"model.layers.29.self_attn.
|
| 536 |
-
"model.layers.29.self_attn.
|
| 537 |
-
"model.layers.29.self_attn.
|
| 538 |
-
"model.layers.29.self_attn.
|
| 539 |
-
"model.layers.29.self_attn.
|
| 540 |
-
"model.layers.29.self_attn.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 541 |
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 542 |
"model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 543 |
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
|
@@ -549,64 +619,73 @@
|
|
| 549 |
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 550 |
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 552 |
"model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 553 |
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 554 |
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 555 |
"model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 556 |
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 557 |
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 558 |
"model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 559 |
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 560 |
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 561 |
"model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 562 |
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 563 |
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
-
"model.layers.30.input_layernorm.weight": "model-
|
| 565 |
-
"model.layers.30.mlp.down_proj.biases": "model-
|
| 566 |
-
"model.layers.30.mlp.down_proj.scales": "model-
|
| 567 |
-
"model.layers.30.mlp.down_proj.weight": "model-
|
| 568 |
-
"model.layers.30.mlp.gate_proj.biases": "model-
|
| 569 |
-
"model.layers.30.mlp.gate_proj.scales": "model-
|
| 570 |
-
"model.layers.30.mlp.gate_proj.weight": "model-
|
| 571 |
-
"model.layers.30.mlp.up_proj.biases": "model-
|
| 572 |
-
"model.layers.30.mlp.up_proj.scales": "model-
|
| 573 |
-
"model.layers.30.mlp.up_proj.weight": "model-
|
| 574 |
-
"model.layers.30.post_attention_layernorm.weight": "model-
|
| 575 |
-
"model.layers.30.self_attn.k_proj.
|
| 576 |
-
"model.layers.30.self_attn.k_proj.
|
| 577 |
-
"model.layers.30.self_attn.k_proj.
|
| 578 |
-
"model.layers.30.self_attn.
|
| 579 |
-
"model.layers.30.self_attn.o_proj.
|
| 580 |
-
"model.layers.30.self_attn.o_proj.
|
| 581 |
-
"model.layers.30.self_attn.
|
| 582 |
-
"model.layers.30.self_attn.q_proj.
|
| 583 |
-
"model.layers.30.self_attn.q_proj.
|
| 584 |
-
"model.layers.30.self_attn.
|
| 585 |
-
"model.layers.30.self_attn.
|
| 586 |
-
"model.layers.30.self_attn.v_proj.
|
|
|
|
|
|
|
|
|
|
| 587 |
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 588 |
-
"model.layers.31.mlp.down_proj.biases": "model-
|
| 589 |
-
"model.layers.31.mlp.down_proj.scales": "model-
|
| 590 |
-
"model.layers.31.mlp.down_proj.weight": "model-
|
| 591 |
-
"model.layers.31.mlp.gate_proj.biases": "model-
|
| 592 |
-
"model.layers.31.mlp.gate_proj.scales": "model-
|
| 593 |
-
"model.layers.31.mlp.gate_proj.weight": "model-
|
| 594 |
"model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 595 |
"model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 596 |
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 597 |
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 598 |
-
"model.layers.31.self_attn.k_proj.
|
| 599 |
-
"model.layers.31.self_attn.k_proj.
|
| 600 |
-
"model.layers.31.self_attn.k_proj.
|
| 601 |
-
"model.layers.31.self_attn.
|
| 602 |
-
"model.layers.31.self_attn.o_proj.
|
| 603 |
-
"model.layers.31.self_attn.o_proj.
|
| 604 |
-
"model.layers.31.self_attn.
|
| 605 |
-
"model.layers.31.self_attn.q_proj.
|
| 606 |
-
"model.layers.31.self_attn.q_proj.
|
| 607 |
-
"model.layers.31.self_attn.
|
| 608 |
-
"model.layers.31.self_attn.
|
| 609 |
-
"model.layers.31.self_attn.v_proj.
|
|
|
|
|
|
|
|
|
|
| 610 |
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 611 |
"model.layers.32.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 612 |
"model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
|
@@ -618,15 +697,18 @@
|
|
| 618 |
"model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 619 |
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 620 |
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 621 |
"model.layers.32.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 622 |
"model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 623 |
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 624 |
"model.layers.32.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 625 |
"model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 626 |
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 627 |
"model.layers.32.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 628 |
"model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 629 |
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 630 |
"model.layers.32.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 631 |
"model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 632 |
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -641,15 +723,18 @@
|
|
| 641 |
"model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 642 |
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 643 |
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 644 |
"model.layers.33.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 645 |
"model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 646 |
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 647 |
"model.layers.33.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 648 |
"model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 649 |
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 650 |
"model.layers.33.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 651 |
"model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 652 |
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 653 |
"model.layers.33.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 654 |
"model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 655 |
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -664,15 +749,18 @@
|
|
| 664 |
"model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 665 |
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 666 |
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 667 |
"model.layers.34.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 668 |
"model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 669 |
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 670 |
"model.layers.34.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 671 |
"model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 672 |
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 673 |
"model.layers.34.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 674 |
"model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 675 |
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 676 |
"model.layers.34.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 677 |
"model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 678 |
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -687,15 +775,18 @@
|
|
| 687 |
"model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 688 |
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 689 |
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 690 |
"model.layers.35.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 691 |
"model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 692 |
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 693 |
"model.layers.35.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 694 |
"model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 695 |
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 696 |
"model.layers.35.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 697 |
"model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 698 |
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 699 |
"model.layers.35.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 700 |
"model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 701 |
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -710,15 +801,18 @@
|
|
| 710 |
"model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 711 |
"model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 712 |
"model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 713 |
"model.layers.36.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 714 |
"model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 715 |
"model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 716 |
"model.layers.36.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 717 |
"model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 718 |
"model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 719 |
"model.layers.36.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 720 |
"model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 721 |
"model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 722 |
"model.layers.36.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 723 |
"model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 724 |
"model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -733,15 +827,18 @@
|
|
| 733 |
"model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 734 |
"model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 735 |
"model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 736 |
"model.layers.37.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 737 |
"model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 738 |
"model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 739 |
"model.layers.37.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 740 |
"model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 741 |
"model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 742 |
"model.layers.37.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 743 |
"model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 744 |
"model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 745 |
"model.layers.37.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 746 |
"model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 747 |
"model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -756,15 +853,18 @@
|
|
| 756 |
"model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 757 |
"model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 758 |
"model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 759 |
"model.layers.38.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 760 |
"model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 761 |
"model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 762 |
"model.layers.38.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 763 |
"model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 764 |
"model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 765 |
"model.layers.38.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 766 |
"model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 767 |
"model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 768 |
"model.layers.38.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 769 |
"model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 770 |
"model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -779,15 +879,18 @@
|
|
| 779 |
"model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 780 |
"model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 781 |
"model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 782 |
"model.layers.39.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 783 |
"model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 784 |
"model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 785 |
"model.layers.39.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 786 |
"model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 787 |
"model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 788 |
"model.layers.39.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 789 |
"model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 790 |
"model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 791 |
"model.layers.39.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 792 |
"model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 793 |
"model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -802,18 +905,229 @@
|
|
| 802 |
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 803 |
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 804 |
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 805 |
"model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 806 |
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 807 |
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 808 |
"model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 809 |
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 810 |
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 811 |
"model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 812 |
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 813 |
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 814 |
"model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 815 |
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 816 |
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 817 |
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 818 |
"model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 819 |
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
|
@@ -825,15 +1139,18 @@
|
|
| 825 |
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 826 |
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 827 |
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 828 |
"model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 829 |
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 830 |
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 831 |
"model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 832 |
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 833 |
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 834 |
"model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 835 |
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 836 |
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 837 |
"model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 838 |
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 839 |
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -848,15 +1165,18 @@
|
|
| 848 |
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 849 |
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 850 |
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 851 |
"model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 852 |
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 853 |
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 854 |
"model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 855 |
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 856 |
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 857 |
"model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 858 |
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 859 |
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 860 |
"model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 861 |
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 862 |
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -871,15 +1191,18 @@
|
|
| 871 |
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 872 |
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 873 |
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 874 |
"model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 875 |
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 876 |
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 877 |
"model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 878 |
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 879 |
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 880 |
"model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 881 |
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 882 |
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 883 |
"model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 884 |
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 885 |
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -894,15 +1217,18 @@
|
|
| 894 |
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 895 |
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 896 |
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 897 |
"model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 898 |
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 899 |
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 900 |
"model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 901 |
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 902 |
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 903 |
"model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 904 |
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 905 |
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 906 |
"model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 907 |
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 908 |
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
@@ -917,15 +1243,18 @@
|
|
| 917 |
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 918 |
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 919 |
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 920 |
"model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 921 |
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 922 |
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 923 |
"model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 924 |
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 925 |
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 926 |
"model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 927 |
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 928 |
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 929 |
"model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 930 |
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 931 |
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 8309352448,
|
| 4 |
+
"total_parameters": 14770033664
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"lm_head.biases": "model-00002-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_proj.bias": "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_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
|
| 36 |
"model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 37 |
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 38 |
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 47 |
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 48 |
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 51 |
"model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 52 |
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 53 |
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
"model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 55 |
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 56 |
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 58 |
"model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 59 |
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 60 |
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
"model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 63 |
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 64 |
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 73 |
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 74 |
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
"model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 78 |
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 79 |
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
"model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 81 |
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 82 |
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 84 |
"model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 85 |
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 86 |
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 88 |
"model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 89 |
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 90 |
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 99 |
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 100 |
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
"model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 104 |
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 105 |
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
"model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 107 |
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 108 |
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 110 |
"model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 111 |
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 112 |
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 114 |
"model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 115 |
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 116 |
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 125 |
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 126 |
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 129 |
"model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 130 |
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 131 |
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
"model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 133 |
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 134 |
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 136 |
"model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 137 |
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 138 |
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 140 |
"model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 141 |
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 142 |
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 151 |
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 152 |
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 155 |
"model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 156 |
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 157 |
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
"model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 159 |
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 160 |
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
"model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 163 |
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 164 |
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 166 |
"model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 167 |
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 168 |
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 177 |
"model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 178 |
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 181 |
"model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 182 |
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 183 |
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
"model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 185 |
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 186 |
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 188 |
"model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 189 |
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 190 |
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 192 |
"model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 193 |
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 194 |
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 203 |
"model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 204 |
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 207 |
"model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 208 |
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 209 |
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
"model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 211 |
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 212 |
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 214 |
"model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 215 |
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 216 |
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 218 |
"model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 219 |
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 220 |
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 229 |
"model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 230 |
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 233 |
"model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 234 |
"model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 235 |
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
"model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 237 |
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 238 |
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 240 |
"model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 241 |
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 242 |
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 244 |
"model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 245 |
"model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 246 |
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 255 |
"model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 256 |
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 259 |
"model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 260 |
"model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 261 |
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
"model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 263 |
"model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 264 |
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
"model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 267 |
"model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 268 |
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 270 |
"model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 271 |
"model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 272 |
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 281 |
"model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 282 |
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 285 |
"model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 286 |
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 287 |
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
"model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 289 |
"model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 290 |
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 292 |
"model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 293 |
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 294 |
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 296 |
"model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 297 |
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 298 |
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 307 |
"model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 308 |
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 311 |
"model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 312 |
"model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 313 |
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
"model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 315 |
"model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 316 |
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 318 |
"model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 319 |
"model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 320 |
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 322 |
"model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 323 |
"model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 324 |
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 333 |
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 334 |
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 337 |
"model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 338 |
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 339 |
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
"model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 341 |
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 342 |
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 344 |
"model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 345 |
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 346 |
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 348 |
"model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 349 |
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 350 |
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 359 |
"model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 360 |
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 363 |
"model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 364 |
"model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 365 |
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 366 |
"model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 367 |
"model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 368 |
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 370 |
"model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 371 |
"model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 372 |
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 374 |
"model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 375 |
"model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 376 |
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 385 |
"model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 386 |
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
"model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 390 |
"model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 391 |
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
"model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 393 |
"model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 394 |
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 396 |
"model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 397 |
"model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 398 |
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 400 |
"model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 401 |
"model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 402 |
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 411 |
"model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 412 |
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
"model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 416 |
"model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 417 |
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
"model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 419 |
"model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 420 |
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 422 |
"model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 423 |
"model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 424 |
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 426 |
"model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 427 |
"model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 428 |
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 437 |
"model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 438 |
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 441 |
"model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 442 |
"model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 443 |
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 444 |
"model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 445 |
"model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 446 |
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 448 |
"model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 449 |
"model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 450 |
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 452 |
"model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 453 |
"model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 454 |
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 463 |
"model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 464 |
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 465 |
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 467 |
"model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 468 |
"model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 469 |
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
"model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 471 |
"model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 472 |
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 474 |
"model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 475 |
"model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 476 |
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 478 |
"model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 479 |
"model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 480 |
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 489 |
"model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 490 |
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 491 |
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 493 |
"model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 494 |
"model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 495 |
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
"model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 497 |
"model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 498 |
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 500 |
"model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 501 |
"model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 502 |
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 504 |
"model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 505 |
"model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 506 |
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 511 |
"model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 512 |
"model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 513 |
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 519 |
"model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 520 |
"model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 521 |
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 522 |
"model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 523 |
"model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 524 |
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 526 |
"model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 527 |
"model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 528 |
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 530 |
"model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 531 |
"model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 532 |
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.layers.27.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.layers.27.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.layers.28.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.layers.28.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.layers.28.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.layers.28.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.layers.28.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.layers.28.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.layers.28.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.layers.29.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.layers.29.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.layers.29.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.layers.29.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.layers.29.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.layers.29.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.layers.29.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 611 |
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 612 |
"model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 613 |
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 619 |
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 620 |
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 621 |
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
"model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 624 |
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 625 |
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
"model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 627 |
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 628 |
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 630 |
"model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 631 |
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 632 |
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 634 |
"model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 635 |
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 636 |
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.layers.30.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.layers.30.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.layers.30.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.layers.30.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.layers.30.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.layers.30.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.layers.30.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 663 |
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.layers.31.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.layers.31.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 670 |
"model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 671 |
"model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 672 |
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 673 |
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.layers.31.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.layers.31.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.layers.31.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.layers.31.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 689 |
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 690 |
"model.layers.32.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 691 |
"model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
|
|
|
| 697 |
"model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 698 |
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 699 |
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 701 |
"model.layers.32.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 702 |
"model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 703 |
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 704 |
"model.layers.32.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 705 |
"model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 706 |
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 708 |
"model.layers.32.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 709 |
"model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 710 |
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 712 |
"model.layers.32.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 713 |
"model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 714 |
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 723 |
"model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 724 |
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 725 |
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 727 |
"model.layers.33.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 728 |
"model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 729 |
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 730 |
"model.layers.33.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 731 |
"model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 732 |
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 733 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 734 |
"model.layers.33.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 735 |
"model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 736 |
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 737 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 738 |
"model.layers.33.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 739 |
"model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 740 |
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 749 |
"model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 750 |
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 751 |
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 752 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 753 |
"model.layers.34.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 754 |
"model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 755 |
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 756 |
"model.layers.34.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 757 |
"model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 758 |
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 759 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 760 |
"model.layers.34.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 761 |
"model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 762 |
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 763 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 764 |
"model.layers.34.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 765 |
"model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 766 |
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 775 |
"model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 776 |
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 777 |
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 778 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 779 |
"model.layers.35.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 780 |
"model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 781 |
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 782 |
"model.layers.35.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 783 |
"model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 784 |
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 785 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 786 |
"model.layers.35.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 787 |
"model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 788 |
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 789 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 790 |
"model.layers.35.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 791 |
"model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 792 |
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 801 |
"model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 802 |
"model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 803 |
"model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 804 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 805 |
"model.layers.36.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 806 |
"model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 807 |
"model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 808 |
"model.layers.36.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 809 |
"model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 810 |
"model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 811 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 812 |
"model.layers.36.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 813 |
"model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 814 |
"model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 815 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 816 |
"model.layers.36.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 817 |
"model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 818 |
"model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 827 |
"model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 828 |
"model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 829 |
"model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 830 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 831 |
"model.layers.37.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 832 |
"model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 833 |
"model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 834 |
"model.layers.37.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 835 |
"model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 836 |
"model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 837 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 838 |
"model.layers.37.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 839 |
"model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 840 |
"model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 841 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 842 |
"model.layers.37.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 843 |
"model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 844 |
"model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 853 |
"model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 854 |
"model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 855 |
"model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 856 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 857 |
"model.layers.38.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 858 |
"model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 859 |
"model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 860 |
"model.layers.38.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 861 |
"model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 862 |
"model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 863 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 864 |
"model.layers.38.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 865 |
"model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 866 |
"model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 867 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 868 |
"model.layers.38.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 869 |
"model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 870 |
"model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 879 |
"model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 880 |
"model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 881 |
"model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 882 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 883 |
"model.layers.39.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 884 |
"model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 885 |
"model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 886 |
"model.layers.39.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 887 |
"model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 888 |
"model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 889 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 890 |
"model.layers.39.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 891 |
"model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 892 |
"model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 893 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 894 |
"model.layers.39.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 895 |
"model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 896 |
"model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 905 |
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 906 |
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 907 |
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 908 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 909 |
"model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 910 |
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 911 |
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 912 |
"model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 913 |
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 914 |
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 915 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 916 |
"model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 917 |
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 918 |
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 919 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 920 |
"model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 921 |
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 922 |
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 923 |
+
"model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 924 |
+
"model.layers.40.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 925 |
+
"model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 926 |
+
"model.layers.40.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 927 |
+
"model.layers.40.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 928 |
+
"model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 929 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 930 |
+
"model.layers.40.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 931 |
+
"model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 932 |
+
"model.layers.40.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 933 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 934 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 935 |
+
"model.layers.40.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 936 |
+
"model.layers.40.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 937 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 938 |
+
"model.layers.40.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 939 |
+
"model.layers.40.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 940 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 941 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 942 |
+
"model.layers.40.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 943 |
+
"model.layers.40.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 944 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 945 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 946 |
+
"model.layers.40.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 947 |
+
"model.layers.40.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 948 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 949 |
+
"model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 950 |
+
"model.layers.41.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 951 |
+
"model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 952 |
+
"model.layers.41.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 953 |
+
"model.layers.41.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 954 |
+
"model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 955 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 956 |
+
"model.layers.41.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 957 |
+
"model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 958 |
+
"model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 959 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 960 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 961 |
+
"model.layers.41.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 962 |
+
"model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 963 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 964 |
+
"model.layers.41.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 965 |
+
"model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 966 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 967 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 968 |
+
"model.layers.41.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 969 |
+
"model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 970 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 971 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 972 |
+
"model.layers.41.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 973 |
+
"model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 974 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 975 |
+
"model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 976 |
+
"model.layers.42.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 977 |
+
"model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 978 |
+
"model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 979 |
+
"model.layers.42.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 980 |
+
"model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 981 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 982 |
+
"model.layers.42.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 983 |
+
"model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 984 |
+
"model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 985 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 986 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 987 |
+
"model.layers.42.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 988 |
+
"model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 989 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 990 |
+
"model.layers.42.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 991 |
+
"model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 992 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 993 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 994 |
+
"model.layers.42.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 995 |
+
"model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 996 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 997 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 998 |
+
"model.layers.42.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 999 |
+
"model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1000 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 1001 |
+
"model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1002 |
+
"model.layers.43.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 1003 |
+
"model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 1004 |
+
"model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 1005 |
+
"model.layers.43.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 1006 |
+
"model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 1007 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 1008 |
+
"model.layers.43.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 1009 |
+
"model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 1010 |
+
"model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 1011 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1012 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 1013 |
+
"model.layers.43.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 1014 |
+
"model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 1015 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 1016 |
+
"model.layers.43.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 1017 |
+
"model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 1018 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 1019 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 1020 |
+
"model.layers.43.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 1021 |
+
"model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 1022 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 1023 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 1024 |
+
"model.layers.43.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 1025 |
+
"model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1026 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 1027 |
+
"model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1028 |
+
"model.layers.44.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 1029 |
+
"model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 1030 |
+
"model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 1031 |
+
"model.layers.44.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 1032 |
+
"model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 1033 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 1034 |
+
"model.layers.44.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 1035 |
+
"model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 1036 |
+
"model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 1037 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1038 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 1039 |
+
"model.layers.44.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 1040 |
+
"model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 1041 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 1042 |
+
"model.layers.44.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 1043 |
+
"model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 1044 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 1045 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 1046 |
+
"model.layers.44.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 1047 |
+
"model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 1048 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 1049 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 1050 |
+
"model.layers.44.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 1051 |
+
"model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1052 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 1053 |
+
"model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1054 |
+
"model.layers.45.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 1055 |
+
"model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 1056 |
+
"model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 1057 |
+
"model.layers.45.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 1058 |
+
"model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 1059 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 1060 |
+
"model.layers.45.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 1061 |
+
"model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 1062 |
+
"model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 1063 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1064 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 1065 |
+
"model.layers.45.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 1066 |
+
"model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 1067 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 1068 |
+
"model.layers.45.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 1069 |
+
"model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 1070 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 1071 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 1072 |
+
"model.layers.45.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 1073 |
+
"model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 1074 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 1075 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 1076 |
+
"model.layers.45.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 1077 |
+
"model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1078 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 1079 |
+
"model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1080 |
+
"model.layers.46.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 1081 |
+
"model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 1082 |
+
"model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 1083 |
+
"model.layers.46.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 1084 |
+
"model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 1085 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 1086 |
+
"model.layers.46.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 1087 |
+
"model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 1088 |
+
"model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 1089 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1090 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 1091 |
+
"model.layers.46.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 1092 |
+
"model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 1093 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 1094 |
+
"model.layers.46.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 1095 |
+
"model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 1096 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 1097 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 1098 |
+
"model.layers.46.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 1099 |
+
"model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 1100 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 1101 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 1102 |
+
"model.layers.46.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 1103 |
+
"model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1104 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 1105 |
+
"model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1106 |
+
"model.layers.47.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
|
| 1107 |
+
"model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 1108 |
+
"model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 1109 |
+
"model.layers.47.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
|
| 1110 |
+
"model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 1111 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 1112 |
+
"model.layers.47.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
|
| 1113 |
+
"model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 1114 |
+
"model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 1115 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1116 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 1117 |
+
"model.layers.47.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
|
| 1118 |
+
"model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 1119 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 1120 |
+
"model.layers.47.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
|
| 1121 |
+
"model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 1122 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 1123 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 1124 |
+
"model.layers.47.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
|
| 1125 |
+
"model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 1126 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 1127 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 1128 |
+
"model.layers.47.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
|
| 1129 |
+
"model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1130 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 1131 |
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1132 |
"model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
|
| 1133 |
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 1139 |
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 1140 |
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1141 |
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1142 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 1143 |
"model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 1144 |
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 1145 |
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 1146 |
"model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 1147 |
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 1148 |
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 1149 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 1150 |
"model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 1151 |
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 1152 |
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 1153 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 1154 |
"model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 1155 |
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1156 |
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1165 |
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 1166 |
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1167 |
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1168 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 1169 |
"model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 1170 |
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 1171 |
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 1172 |
"model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 1173 |
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 1174 |
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 1175 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 1176 |
"model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 1177 |
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 1178 |
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 1179 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 1180 |
"model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 1181 |
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1182 |
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1191 |
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 1192 |
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1193 |
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1194 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 1195 |
"model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 1196 |
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 1197 |
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 1198 |
"model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 1199 |
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 1200 |
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 1201 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 1202 |
"model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 1203 |
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 1204 |
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 1205 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 1206 |
"model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 1207 |
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1208 |
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1217 |
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 1218 |
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1219 |
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1220 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 1221 |
"model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 1222 |
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 1223 |
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 1224 |
"model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 1225 |
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 1226 |
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 1227 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 1228 |
"model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 1229 |
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 1230 |
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 1231 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 1232 |
"model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 1233 |
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1234 |
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1243 |
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 1244 |
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 1245 |
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 1246 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 1247 |
"model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
|
| 1248 |
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 1249 |
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 1250 |
"model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
|
| 1251 |
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 1252 |
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 1253 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 1254 |
"model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
|
| 1255 |
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 1256 |
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 1257 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 1258 |
"model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
|
| 1259 |
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 1260 |
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
special_tokens_map.json
CHANGED
|
@@ -1,27 +1,28 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"eos_token": {
|
| 10 |
"content": "<|im_end|>",
|
| 11 |
-
"lstrip":
|
| 12 |
"normalized": false,
|
| 13 |
-
"rstrip":
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "<|
|
| 18 |
-
"lstrip": true,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": true,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
-
"unk_token": {
|
| 24 |
-
"content": "�",
|
| 25 |
"lstrip": false,
|
| 26 |
"normalized": false,
|
| 27 |
"rstrip": false,
|
|
|
|
| 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": "<|PAD_TOKEN|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"lstrip": false,
|
| 27 |
"normalized": false,
|
| 28 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,791 +1,216 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
-
"
|
| 5 |
-
"content": "
|
| 6 |
"lstrip": false,
|
| 7 |
"normalized": false,
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
-
"
|
| 13 |
-
"content": "<|dummy_0|>",
|
| 14 |
-
"lstrip": true,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": true,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"100257": {
|
| 21 |
-
"content": "<|endoftext|>",
|
| 22 |
-
"lstrip": true,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": true,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
},
|
| 28 |
-
"100258": {
|
| 29 |
-
"content": "<|fim_prefix|>",
|
| 30 |
-
"lstrip": true,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": true,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
},
|
| 36 |
-
"100259": {
|
| 37 |
-
"content": "<|fim_middle|>",
|
| 38 |
-
"lstrip": true,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"rstrip": true,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": true
|
| 43 |
-
},
|
| 44 |
-
"100260": {
|
| 45 |
-
"content": "<|fim_suffix|>",
|
| 46 |
-
"lstrip": true,
|
| 47 |
-
"normalized": false,
|
| 48 |
-
"rstrip": true,
|
| 49 |
-
"single_word": false,
|
| 50 |
-
"special": true
|
| 51 |
-
},
|
| 52 |
-
"100261": {
|
| 53 |
-
"content": "<|dummy_1|>",
|
| 54 |
-
"lstrip": true,
|
| 55 |
-
"normalized": false,
|
| 56 |
-
"rstrip": true,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": true
|
| 59 |
-
},
|
| 60 |
-
"100262": {
|
| 61 |
-
"content": "<|dummy_2|>",
|
| 62 |
-
"lstrip": true,
|
| 63 |
-
"normalized": false,
|
| 64 |
-
"rstrip": true,
|
| 65 |
-
"single_word": false,
|
| 66 |
-
"special": true
|
| 67 |
-
},
|
| 68 |
-
"100263": {
|
| 69 |
-
"content": "<|dummy_3|>",
|
| 70 |
-
"lstrip": true,
|
| 71 |
-
"normalized": false,
|
| 72 |
-
"rstrip": true,
|
| 73 |
-
"single_word": false,
|
| 74 |
-
"special": true
|
| 75 |
-
},
|
| 76 |
-
"100264": {
|
| 77 |
"content": "<|im_start|>",
|
| 78 |
-
"lstrip":
|
| 79 |
"normalized": false,
|
| 80 |
-
"rstrip":
|
| 81 |
"single_word": false,
|
| 82 |
"special": true
|
| 83 |
},
|
| 84 |
-
"
|
| 85 |
"content": "<|im_end|>",
|
| 86 |
-
"lstrip":
|
| 87 |
-
"normalized": false,
|
| 88 |
-
"rstrip": true,
|
| 89 |
-
"single_word": false,
|
| 90 |
-
"special": true
|
| 91 |
-
},
|
| 92 |
-
"100266": {
|
| 93 |
-
"content": "<|im_sep|>",
|
| 94 |
-
"lstrip": true,
|
| 95 |
-
"normalized": false,
|
| 96 |
-
"rstrip": true,
|
| 97 |
-
"single_word": false,
|
| 98 |
-
"special": true
|
| 99 |
-
},
|
| 100 |
-
"100267": {
|
| 101 |
-
"content": "<|dummy_4|>",
|
| 102 |
-
"lstrip": true,
|
| 103 |
-
"normalized": false,
|
| 104 |
-
"rstrip": true,
|
| 105 |
-
"single_word": false,
|
| 106 |
-
"special": true
|
| 107 |
-
},
|
| 108 |
-
"100268": {
|
| 109 |
-
"content": "<|dummy_5|>",
|
| 110 |
-
"lstrip": true,
|
| 111 |
-
"normalized": false,
|
| 112 |
-
"rstrip": true,
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"special": true
|
| 115 |
-
},
|
| 116 |
-
"100269": {
|
| 117 |
-
"content": "<|dummy_6|>",
|
| 118 |
-
"lstrip": true,
|
| 119 |
-
"normalized": false,
|
| 120 |
-
"rstrip": true,
|
| 121 |
-
"single_word": false,
|
| 122 |
-
"special": true
|
| 123 |
-
},
|
| 124 |
-
"100270": {
|
| 125 |
-
"content": "<|dummy_7|>",
|
| 126 |
-
"lstrip": true,
|
| 127 |
-
"normalized": false,
|
| 128 |
-
"rstrip": true,
|
| 129 |
-
"single_word": false,
|
| 130 |
-
"special": true
|
| 131 |
-
},
|
| 132 |
-
"100271": {
|
| 133 |
-
"content": "<|dummy_8|>",
|
| 134 |
-
"lstrip": true,
|
| 135 |
-
"normalized": false,
|
| 136 |
-
"rstrip": true,
|
| 137 |
-
"single_word": false,
|
| 138 |
-
"special": true
|
| 139 |
-
},
|
| 140 |
-
"100272": {
|
| 141 |
-
"content": "<|dummy_9|>",
|
| 142 |
-
"lstrip": true,
|
| 143 |
-
"normalized": false,
|
| 144 |
-
"rstrip": true,
|
| 145 |
-
"single_word": false,
|
| 146 |
-
"special": true
|
| 147 |
-
},
|
| 148 |
-
"100273": {
|
| 149 |
-
"content": "<|dummy_10|>",
|
| 150 |
-
"lstrip": true,
|
| 151 |
-
"normalized": false,
|
| 152 |
-
"rstrip": true,
|
| 153 |
-
"single_word": false,
|
| 154 |
-
"special": true
|
| 155 |
-
},
|
| 156 |
-
"100274": {
|
| 157 |
-
"content": "<|dummy_11|>",
|
| 158 |
-
"lstrip": true,
|
| 159 |
-
"normalized": false,
|
| 160 |
-
"rstrip": true,
|
| 161 |
-
"single_word": false,
|
| 162 |
-
"special": true
|
| 163 |
-
},
|
| 164 |
-
"100275": {
|
| 165 |
-
"content": "<|dummy_12|>",
|
| 166 |
-
"lstrip": true,
|
| 167 |
-
"normalized": false,
|
| 168 |
-
"rstrip": true,
|
| 169 |
-
"single_word": false,
|
| 170 |
-
"special": true
|
| 171 |
-
},
|
| 172 |
-
"100276": {
|
| 173 |
-
"content": "<|endofprompt|>",
|
| 174 |
-
"lstrip": true,
|
| 175 |
-
"normalized": false,
|
| 176 |
-
"rstrip": true,
|
| 177 |
-
"single_word": false,
|
| 178 |
-
"special": true
|
| 179 |
-
},
|
| 180 |
-
"100277": {
|
| 181 |
-
"content": "<|dummy_13|>",
|
| 182 |
-
"lstrip": true,
|
| 183 |
-
"normalized": false,
|
| 184 |
-
"rstrip": true,
|
| 185 |
-
"single_word": false,
|
| 186 |
-
"special": true
|
| 187 |
-
},
|
| 188 |
-
"100278": {
|
| 189 |
-
"content": "<|dummy_14|>",
|
| 190 |
-
"lstrip": true,
|
| 191 |
-
"normalized": false,
|
| 192 |
-
"rstrip": true,
|
| 193 |
-
"single_word": false,
|
| 194 |
-
"special": true
|
| 195 |
-
},
|
| 196 |
-
"100279": {
|
| 197 |
-
"content": "<|dummy_15|>",
|
| 198 |
-
"lstrip": true,
|
| 199 |
-
"normalized": false,
|
| 200 |
-
"rstrip": true,
|
| 201 |
-
"single_word": false,
|
| 202 |
-
"special": true
|
| 203 |
-
},
|
| 204 |
-
"100280": {
|
| 205 |
-
"content": "<|dummy_16|>",
|
| 206 |
-
"lstrip": true,
|
| 207 |
-
"normalized": false,
|
| 208 |
-
"rstrip": true,
|
| 209 |
-
"single_word": false,
|
| 210 |
-
"special": true
|
| 211 |
-
},
|
| 212 |
-
"100281": {
|
| 213 |
-
"content": "<|dummy_17|>",
|
| 214 |
-
"lstrip": true,
|
| 215 |
-
"normalized": false,
|
| 216 |
-
"rstrip": true,
|
| 217 |
-
"single_word": false,
|
| 218 |
-
"special": true
|
| 219 |
-
},
|
| 220 |
-
"100282": {
|
| 221 |
-
"content": "<|dummy_18|>",
|
| 222 |
-
"lstrip": true,
|
| 223 |
-
"normalized": false,
|
| 224 |
-
"rstrip": true,
|
| 225 |
-
"single_word": false,
|
| 226 |
-
"special": true
|
| 227 |
-
},
|
| 228 |
-
"100283": {
|
| 229 |
-
"content": "<|dummy_19|>",
|
| 230 |
-
"lstrip": true,
|
| 231 |
-
"normalized": false,
|
| 232 |
-
"rstrip": true,
|
| 233 |
-
"single_word": false,
|
| 234 |
-
"special": true
|
| 235 |
-
},
|
| 236 |
-
"100284": {
|
| 237 |
-
"content": "<|dummy_20|>",
|
| 238 |
-
"lstrip": true,
|
| 239 |
-
"normalized": false,
|
| 240 |
-
"rstrip": true,
|
| 241 |
-
"single_word": false,
|
| 242 |
-
"special": true
|
| 243 |
-
},
|
| 244 |
-
"100285": {
|
| 245 |
-
"content": "<|dummy_21|>",
|
| 246 |
-
"lstrip": true,
|
| 247 |
-
"normalized": false,
|
| 248 |
-
"rstrip": true,
|
| 249 |
-
"single_word": false,
|
| 250 |
-
"special": true
|
| 251 |
-
},
|
| 252 |
-
"100286": {
|
| 253 |
-
"content": "<|dummy_22|>",
|
| 254 |
-
"lstrip": true,
|
| 255 |
-
"normalized": false,
|
| 256 |
-
"rstrip": true,
|
| 257 |
-
"single_word": false,
|
| 258 |
-
"special": true
|
| 259 |
-
},
|
| 260 |
-
"100287": {
|
| 261 |
-
"content": "<|dummy_23|>",
|
| 262 |
-
"lstrip": true,
|
| 263 |
-
"normalized": false,
|
| 264 |
-
"rstrip": true,
|
| 265 |
-
"single_word": false,
|
| 266 |
-
"special": true
|
| 267 |
-
},
|
| 268 |
-
"100288": {
|
| 269 |
-
"content": "<|dummy_24|>",
|
| 270 |
-
"lstrip": true,
|
| 271 |
-
"normalized": false,
|
| 272 |
-
"rstrip": true,
|
| 273 |
-
"single_word": false,
|
| 274 |
-
"special": true
|
| 275 |
-
},
|
| 276 |
-
"100289": {
|
| 277 |
-
"content": "<|dummy_25|>",
|
| 278 |
-
"lstrip": true,
|
| 279 |
-
"normalized": false,
|
| 280 |
-
"rstrip": true,
|
| 281 |
-
"single_word": false,
|
| 282 |
-
"special": true
|
| 283 |
-
},
|
| 284 |
-
"100290": {
|
| 285 |
-
"content": "<|dummy_26|>",
|
| 286 |
-
"lstrip": true,
|
| 287 |
-
"normalized": false,
|
| 288 |
-
"rstrip": true,
|
| 289 |
-
"single_word": false,
|
| 290 |
-
"special": true
|
| 291 |
-
},
|
| 292 |
-
"100291": {
|
| 293 |
-
"content": "<|dummy_27|>",
|
| 294 |
-
"lstrip": true,
|
| 295 |
-
"normalized": false,
|
| 296 |
-
"rstrip": true,
|
| 297 |
-
"single_word": false,
|
| 298 |
-
"special": true
|
| 299 |
-
},
|
| 300 |
-
"100292": {
|
| 301 |
-
"content": "<|dummy_28|>",
|
| 302 |
-
"lstrip": true,
|
| 303 |
-
"normalized": false,
|
| 304 |
-
"rstrip": true,
|
| 305 |
-
"single_word": false,
|
| 306 |
-
"special": true
|
| 307 |
-
},
|
| 308 |
-
"100293": {
|
| 309 |
-
"content": "<|dummy_29|>",
|
| 310 |
-
"lstrip": true,
|
| 311 |
-
"normalized": false,
|
| 312 |
-
"rstrip": true,
|
| 313 |
-
"single_word": false,
|
| 314 |
-
"special": true
|
| 315 |
-
},
|
| 316 |
-
"100294": {
|
| 317 |
-
"content": "<|dummy_30|>",
|
| 318 |
-
"lstrip": true,
|
| 319 |
-
"normalized": false,
|
| 320 |
-
"rstrip": true,
|
| 321 |
-
"single_word": false,
|
| 322 |
-
"special": true
|
| 323 |
-
},
|
| 324 |
-
"100295": {
|
| 325 |
-
"content": "<|dummy_31|>",
|
| 326 |
-
"lstrip": true,
|
| 327 |
-
"normalized": false,
|
| 328 |
-
"rstrip": true,
|
| 329 |
-
"single_word": false,
|
| 330 |
-
"special": true
|
| 331 |
-
},
|
| 332 |
-
"100296": {
|
| 333 |
-
"content": "<|dummy_32|>",
|
| 334 |
-
"lstrip": true,
|
| 335 |
-
"normalized": false,
|
| 336 |
-
"rstrip": true,
|
| 337 |
-
"single_word": false,
|
| 338 |
-
"special": true
|
| 339 |
-
},
|
| 340 |
-
"100297": {
|
| 341 |
-
"content": "<|dummy_33|>",
|
| 342 |
-
"lstrip": true,
|
| 343 |
-
"normalized": false,
|
| 344 |
-
"rstrip": true,
|
| 345 |
-
"single_word": false,
|
| 346 |
-
"special": true
|
| 347 |
-
},
|
| 348 |
-
"100298": {
|
| 349 |
-
"content": "<|dummy_34|>",
|
| 350 |
-
"lstrip": true,
|
| 351 |
-
"normalized": false,
|
| 352 |
-
"rstrip": true,
|
| 353 |
-
"single_word": false,
|
| 354 |
-
"special": true
|
| 355 |
-
},
|
| 356 |
-
"100299": {
|
| 357 |
-
"content": "<|dummy_35|>",
|
| 358 |
-
"lstrip": true,
|
| 359 |
-
"normalized": false,
|
| 360 |
-
"rstrip": true,
|
| 361 |
-
"single_word": false,
|
| 362 |
-
"special": true
|
| 363 |
-
},
|
| 364 |
-
"100300": {
|
| 365 |
-
"content": "<|dummy_36|>",
|
| 366 |
-
"lstrip": true,
|
| 367 |
-
"normalized": false,
|
| 368 |
-
"rstrip": true,
|
| 369 |
-
"single_word": false,
|
| 370 |
-
"special": true
|
| 371 |
-
},
|
| 372 |
-
"100301": {
|
| 373 |
-
"content": "<|dummy_37|>",
|
| 374 |
-
"lstrip": true,
|
| 375 |
-
"normalized": false,
|
| 376 |
-
"rstrip": true,
|
| 377 |
-
"single_word": false,
|
| 378 |
-
"special": true
|
| 379 |
-
},
|
| 380 |
-
"100302": {
|
| 381 |
-
"content": "<|dummy_38|>",
|
| 382 |
-
"lstrip": true,
|
| 383 |
-
"normalized": false,
|
| 384 |
-
"rstrip": true,
|
| 385 |
-
"single_word": false,
|
| 386 |
-
"special": true
|
| 387 |
-
},
|
| 388 |
-
"100303": {
|
| 389 |
-
"content": "<|dummy_39|>",
|
| 390 |
-
"lstrip": true,
|
| 391 |
-
"normalized": false,
|
| 392 |
-
"rstrip": true,
|
| 393 |
-
"single_word": false,
|
| 394 |
-
"special": true
|
| 395 |
-
},
|
| 396 |
-
"100304": {
|
| 397 |
-
"content": "<|dummy_40|>",
|
| 398 |
-
"lstrip": true,
|
| 399 |
-
"normalized": false,
|
| 400 |
-
"rstrip": true,
|
| 401 |
-
"single_word": false,
|
| 402 |
-
"special": true
|
| 403 |
-
},
|
| 404 |
-
"100305": {
|
| 405 |
-
"content": "<|dummy_41|>",
|
| 406 |
-
"lstrip": true,
|
| 407 |
-
"normalized": false,
|
| 408 |
-
"rstrip": true,
|
| 409 |
-
"single_word": false,
|
| 410 |
-
"special": true
|
| 411 |
-
},
|
| 412 |
-
"100306": {
|
| 413 |
-
"content": "<|dummy_42|>",
|
| 414 |
-
"lstrip": true,
|
| 415 |
-
"normalized": false,
|
| 416 |
-
"rstrip": true,
|
| 417 |
-
"single_word": false,
|
| 418 |
-
"special": true
|
| 419 |
-
},
|
| 420 |
-
"100307": {
|
| 421 |
-
"content": "<|dummy_43|>",
|
| 422 |
-
"lstrip": true,
|
| 423 |
-
"normalized": false,
|
| 424 |
-
"rstrip": true,
|
| 425 |
-
"single_word": false,
|
| 426 |
-
"special": true
|
| 427 |
-
},
|
| 428 |
-
"100308": {
|
| 429 |
-
"content": "<|dummy_44|>",
|
| 430 |
-
"lstrip": true,
|
| 431 |
-
"normalized": false,
|
| 432 |
-
"rstrip": true,
|
| 433 |
-
"single_word": false,
|
| 434 |
-
"special": true
|
| 435 |
-
},
|
| 436 |
-
"100309": {
|
| 437 |
-
"content": "<|dummy_45|>",
|
| 438 |
-
"lstrip": true,
|
| 439 |
-
"normalized": false,
|
| 440 |
-
"rstrip": true,
|
| 441 |
-
"single_word": false,
|
| 442 |
-
"special": true
|
| 443 |
-
},
|
| 444 |
-
"100310": {
|
| 445 |
-
"content": "<|dummy_46|>",
|
| 446 |
-
"lstrip": true,
|
| 447 |
-
"normalized": false,
|
| 448 |
-
"rstrip": true,
|
| 449 |
-
"single_word": false,
|
| 450 |
-
"special": true
|
| 451 |
-
},
|
| 452 |
-
"100311": {
|
| 453 |
-
"content": "<|dummy_47|>",
|
| 454 |
-
"lstrip": true,
|
| 455 |
-
"normalized": false,
|
| 456 |
-
"rstrip": true,
|
| 457 |
-
"single_word": false,
|
| 458 |
-
"special": true
|
| 459 |
-
},
|
| 460 |
-
"100312": {
|
| 461 |
-
"content": "<|dummy_48|>",
|
| 462 |
-
"lstrip": true,
|
| 463 |
-
"normalized": false,
|
| 464 |
-
"rstrip": true,
|
| 465 |
-
"single_word": false,
|
| 466 |
-
"special": true
|
| 467 |
-
},
|
| 468 |
-
"100313": {
|
| 469 |
-
"content": "<|dummy_49|>",
|
| 470 |
-
"lstrip": true,
|
| 471 |
-
"normalized": false,
|
| 472 |
-
"rstrip": true,
|
| 473 |
-
"single_word": false,
|
| 474 |
-
"special": true
|
| 475 |
-
},
|
| 476 |
-
"100314": {
|
| 477 |
-
"content": "<|dummy_50|>",
|
| 478 |
-
"lstrip": true,
|
| 479 |
-
"normalized": false,
|
| 480 |
-
"rstrip": true,
|
| 481 |
-
"single_word": false,
|
| 482 |
-
"special": true
|
| 483 |
-
},
|
| 484 |
-
"100315": {
|
| 485 |
-
"content": "<|dummy_51|>",
|
| 486 |
-
"lstrip": true,
|
| 487 |
-
"normalized": false,
|
| 488 |
-
"rstrip": true,
|
| 489 |
-
"single_word": false,
|
| 490 |
-
"special": true
|
| 491 |
-
},
|
| 492 |
-
"100316": {
|
| 493 |
-
"content": "<|dummy_52|>",
|
| 494 |
-
"lstrip": true,
|
| 495 |
-
"normalized": false,
|
| 496 |
-
"rstrip": true,
|
| 497 |
-
"single_word": false,
|
| 498 |
-
"special": true
|
| 499 |
-
},
|
| 500 |
-
"100317": {
|
| 501 |
-
"content": "<|dummy_53|>",
|
| 502 |
-
"lstrip": true,
|
| 503 |
-
"normalized": false,
|
| 504 |
-
"rstrip": true,
|
| 505 |
-
"single_word": false,
|
| 506 |
-
"special": true
|
| 507 |
-
},
|
| 508 |
-
"100318": {
|
| 509 |
-
"content": "<|dummy_54|>",
|
| 510 |
-
"lstrip": true,
|
| 511 |
-
"normalized": false,
|
| 512 |
-
"rstrip": true,
|
| 513 |
-
"single_word": false,
|
| 514 |
-
"special": true
|
| 515 |
-
},
|
| 516 |
-
"100319": {
|
| 517 |
-
"content": "<|dummy_55|>",
|
| 518 |
-
"lstrip": true,
|
| 519 |
-
"normalized": false,
|
| 520 |
-
"rstrip": true,
|
| 521 |
-
"single_word": false,
|
| 522 |
-
"special": true
|
| 523 |
-
},
|
| 524 |
-
"100320": {
|
| 525 |
-
"content": "<|dummy_56|>",
|
| 526 |
-
"lstrip": true,
|
| 527 |
-
"normalized": false,
|
| 528 |
-
"rstrip": true,
|
| 529 |
-
"single_word": false,
|
| 530 |
-
"special": true
|
| 531 |
-
},
|
| 532 |
-
"100321": {
|
| 533 |
-
"content": "<|dummy_57|>",
|
| 534 |
-
"lstrip": true,
|
| 535 |
-
"normalized": false,
|
| 536 |
-
"rstrip": true,
|
| 537 |
-
"single_word": false,
|
| 538 |
-
"special": true
|
| 539 |
-
},
|
| 540 |
-
"100322": {
|
| 541 |
-
"content": "<|dummy_58|>",
|
| 542 |
-
"lstrip": true,
|
| 543 |
-
"normalized": false,
|
| 544 |
-
"rstrip": true,
|
| 545 |
-
"single_word": false,
|
| 546 |
-
"special": true
|
| 547 |
-
},
|
| 548 |
-
"100323": {
|
| 549 |
-
"content": "<|dummy_59|>",
|
| 550 |
-
"lstrip": true,
|
| 551 |
-
"normalized": false,
|
| 552 |
-
"rstrip": true,
|
| 553 |
-
"single_word": false,
|
| 554 |
-
"special": true
|
| 555 |
-
},
|
| 556 |
-
"100324": {
|
| 557 |
-
"content": "<|dummy_60|>",
|
| 558 |
-
"lstrip": true,
|
| 559 |
-
"normalized": false,
|
| 560 |
-
"rstrip": true,
|
| 561 |
-
"single_word": false,
|
| 562 |
-
"special": true
|
| 563 |
-
},
|
| 564 |
-
"100325": {
|
| 565 |
-
"content": "<|dummy_61|>",
|
| 566 |
-
"lstrip": true,
|
| 567 |
-
"normalized": false,
|
| 568 |
-
"rstrip": true,
|
| 569 |
-
"single_word": false,
|
| 570 |
-
"special": true
|
| 571 |
-
},
|
| 572 |
-
"100326": {
|
| 573 |
-
"content": "<|dummy_62|>",
|
| 574 |
-
"lstrip": true,
|
| 575 |
-
"normalized": false,
|
| 576 |
-
"rstrip": true,
|
| 577 |
-
"single_word": false,
|
| 578 |
-
"special": true
|
| 579 |
-
},
|
| 580 |
-
"100327": {
|
| 581 |
-
"content": "<|dummy_63|>",
|
| 582 |
-
"lstrip": true,
|
| 583 |
-
"normalized": false,
|
| 584 |
-
"rstrip": true,
|
| 585 |
-
"single_word": false,
|
| 586 |
-
"special": true
|
| 587 |
-
},
|
| 588 |
-
"100328": {
|
| 589 |
-
"content": "<|dummy_64|>",
|
| 590 |
-
"lstrip": true,
|
| 591 |
-
"normalized": false,
|
| 592 |
-
"rstrip": true,
|
| 593 |
-
"single_word": false,
|
| 594 |
-
"special": true
|
| 595 |
-
},
|
| 596 |
-
"100329": {
|
| 597 |
-
"content": "<|dummy_65|>",
|
| 598 |
-
"lstrip": true,
|
| 599 |
-
"normalized": false,
|
| 600 |
-
"rstrip": true,
|
| 601 |
-
"single_word": false,
|
| 602 |
-
"special": true
|
| 603 |
-
},
|
| 604 |
-
"100330": {
|
| 605 |
-
"content": "<|dummy_66|>",
|
| 606 |
-
"lstrip": true,
|
| 607 |
-
"normalized": false,
|
| 608 |
-
"rstrip": true,
|
| 609 |
-
"single_word": false,
|
| 610 |
-
"special": true
|
| 611 |
-
},
|
| 612 |
-
"100331": {
|
| 613 |
-
"content": "<|dummy_67|>",
|
| 614 |
-
"lstrip": true,
|
| 615 |
"normalized": false,
|
| 616 |
-
"rstrip":
|
| 617 |
"single_word": false,
|
| 618 |
"special": true
|
| 619 |
},
|
| 620 |
-
"
|
| 621 |
-
"content": "<|
|
| 622 |
-
"lstrip":
|
| 623 |
"normalized": false,
|
| 624 |
-
"rstrip":
|
| 625 |
"single_word": false,
|
| 626 |
"special": true
|
| 627 |
},
|
| 628 |
-
"
|
| 629 |
-
"content": "<|
|
| 630 |
-
"lstrip":
|
| 631 |
"normalized": false,
|
| 632 |
-
"rstrip":
|
| 633 |
"single_word": false,
|
| 634 |
"special": true
|
| 635 |
},
|
| 636 |
-
"
|
| 637 |
-
"content": "<|
|
| 638 |
-
"lstrip":
|
| 639 |
"normalized": false,
|
| 640 |
-
"rstrip":
|
| 641 |
"single_word": false,
|
| 642 |
"special": true
|
| 643 |
},
|
| 644 |
-
"
|
| 645 |
-
"content": "<|
|
| 646 |
-
"lstrip":
|
| 647 |
"normalized": false,
|
| 648 |
-
"rstrip":
|
| 649 |
"single_word": false,
|
| 650 |
"special": true
|
| 651 |
},
|
| 652 |
-
"
|
| 653 |
-
"content": "<|
|
| 654 |
-
"lstrip":
|
| 655 |
"normalized": false,
|
| 656 |
-
"rstrip":
|
| 657 |
"single_word": false,
|
| 658 |
"special": true
|
| 659 |
},
|
| 660 |
-
"
|
| 661 |
-
"content": "<|
|
| 662 |
-
"lstrip":
|
| 663 |
"normalized": false,
|
| 664 |
-
"rstrip":
|
| 665 |
"single_word": false,
|
| 666 |
"special": true
|
| 667 |
},
|
| 668 |
-
"
|
| 669 |
-
"content": "<|
|
| 670 |
-
"lstrip":
|
| 671 |
"normalized": false,
|
| 672 |
-
"rstrip":
|
| 673 |
"single_word": false,
|
| 674 |
"special": true
|
| 675 |
},
|
| 676 |
-
"
|
| 677 |
-
"content": "<|
|
| 678 |
-
"lstrip":
|
| 679 |
"normalized": false,
|
| 680 |
-
"rstrip":
|
| 681 |
"single_word": false,
|
| 682 |
"special": true
|
| 683 |
},
|
| 684 |
-
"
|
| 685 |
-
"content": "<|
|
| 686 |
-
"lstrip":
|
| 687 |
"normalized": false,
|
| 688 |
-
"rstrip":
|
| 689 |
"single_word": false,
|
| 690 |
"special": true
|
| 691 |
},
|
| 692 |
-
"
|
| 693 |
-
"content": "<|
|
| 694 |
-
"lstrip":
|
| 695 |
"normalized": false,
|
| 696 |
-
"rstrip":
|
| 697 |
"single_word": false,
|
| 698 |
"special": true
|
| 699 |
},
|
| 700 |
-
"
|
| 701 |
-
"content": "<|
|
| 702 |
-
"lstrip":
|
| 703 |
"normalized": false,
|
| 704 |
-
"rstrip":
|
| 705 |
"single_word": false,
|
| 706 |
"special": true
|
| 707 |
},
|
| 708 |
-
"
|
| 709 |
-
"content": "
|
| 710 |
-
"lstrip":
|
| 711 |
"normalized": false,
|
| 712 |
-
"rstrip":
|
| 713 |
"single_word": false,
|
| 714 |
-
"special":
|
| 715 |
},
|
| 716 |
-
"
|
| 717 |
-
"content": "
|
| 718 |
-
"lstrip":
|
| 719 |
"normalized": false,
|
| 720 |
-
"rstrip":
|
| 721 |
"single_word": false,
|
| 722 |
-
"special":
|
| 723 |
},
|
| 724 |
-
"
|
| 725 |
-
"content": "<|
|
| 726 |
-
"lstrip":
|
| 727 |
"normalized": false,
|
| 728 |
-
"rstrip":
|
| 729 |
"single_word": false,
|
| 730 |
-
"special":
|
| 731 |
},
|
| 732 |
-
"
|
| 733 |
-
"content": "<|
|
| 734 |
-
"lstrip":
|
| 735 |
"normalized": false,
|
| 736 |
-
"rstrip":
|
| 737 |
"single_word": false,
|
| 738 |
-
"special":
|
| 739 |
},
|
| 740 |
-
"
|
| 741 |
-
"content": "<|
|
| 742 |
-
"lstrip":
|
| 743 |
"normalized": false,
|
| 744 |
-
"rstrip":
|
| 745 |
"single_word": false,
|
| 746 |
-
"special":
|
| 747 |
},
|
| 748 |
-
"
|
| 749 |
-
"content": "<|
|
| 750 |
-
"lstrip":
|
| 751 |
"normalized": false,
|
| 752 |
-
"rstrip":
|
| 753 |
"single_word": false,
|
| 754 |
-
"special":
|
| 755 |
},
|
| 756 |
-
"
|
| 757 |
-
"content": "<|
|
| 758 |
-
"lstrip":
|
| 759 |
"normalized": false,
|
| 760 |
-
"rstrip":
|
| 761 |
"single_word": false,
|
| 762 |
-
"special":
|
| 763 |
},
|
| 764 |
-
"
|
| 765 |
-
"content": "<|
|
| 766 |
-
"lstrip":
|
| 767 |
"normalized": false,
|
| 768 |
-
"rstrip":
|
| 769 |
"single_word": false,
|
| 770 |
-
"special":
|
| 771 |
},
|
| 772 |
-
"
|
| 773 |
-
"content": "<|
|
| 774 |
-
"lstrip":
|
| 775 |
"normalized": false,
|
| 776 |
-
"rstrip":
|
| 777 |
"single_word": false,
|
| 778 |
"special": true
|
| 779 |
}
|
| 780 |
},
|
| 781 |
-
"
|
| 782 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 783 |
"clean_up_tokenization_spaces": false,
|
| 784 |
"eos_token": "<|im_end|>",
|
|
|
|
| 785 |
"extra_special_tokens": {},
|
| 786 |
-
"model_max_length":
|
| 787 |
-
"pad_token": "<|
|
| 788 |
"padding_side": "left",
|
| 789 |
-
"
|
| 790 |
-
"
|
|
|
|
| 791 |
}
|
|
|
|
| 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": "<|PAD_TOKEN|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
"single_word": false,
|
| 187 |
"special": true
|
| 188 |
}
|
| 189 |
},
|
| 190 |
+
"additional_special_tokens": [
|
| 191 |
+
"<|im_start|>",
|
| 192 |
+
"<|im_end|>",
|
| 193 |
+
"<|object_ref_start|>",
|
| 194 |
+
"<|object_ref_end|>",
|
| 195 |
+
"<|box_start|>",
|
| 196 |
+
"<|box_end|>",
|
| 197 |
+
"<|quad_start|>",
|
| 198 |
+
"<|quad_end|>",
|
| 199 |
+
"<|vision_start|>",
|
| 200 |
+
"<|vision_end|>",
|
| 201 |
+
"<|vision_pad|>",
|
| 202 |
+
"<|image_pad|>",
|
| 203 |
+
"<|video_pad|>"
|
| 204 |
+
],
|
| 205 |
+
"bos_token": null,
|
| 206 |
"clean_up_tokenization_spaces": false,
|
| 207 |
"eos_token": "<|im_end|>",
|
| 208 |
+
"errors": "replace",
|
| 209 |
"extra_special_tokens": {},
|
| 210 |
+
"model_max_length": 131072,
|
| 211 |
+
"pad_token": "<|PAD_TOKEN|>",
|
| 212 |
"padding_side": "left",
|
| 213 |
+
"split_special_tokens": false,
|
| 214 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 215 |
+
"unk_token": null
|
| 216 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|