Upload distilled distill branch artifact
Browse files- .gitattributes +1 -0
- README.md +24 -0
- chat_template.jinja +88 -0
- config.json +185 -0
- generation_config.json +9 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +435 -0
- slice.log +412 -0
- student_layer_map.json +106 -0
- student_slice_manifest.json +8 -0
- student_slice_summary.json +41 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -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
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- qwen
|
| 6 |
+
- distilled
|
| 7 |
+
- sliced-model
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# techhermit/qwen35-slice14b-base
|
| 11 |
+
|
| 12 |
+
This repository contains the sliced 14B base checkpoint used for the
|
| 13 |
+
distillation branch.
|
| 14 |
+
|
| 15 |
+
## Provenance
|
| 16 |
+
|
| 17 |
+
- Base model: `Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled`
|
| 18 |
+
- Slice target: 32 transformer layers
|
| 19 |
+
- Purpose: serve as the structural base for the adapter release repo
|
| 20 |
+
|
| 21 |
+
## Usage
|
| 22 |
+
|
| 23 |
+
Load this repo as a normal Transformers checkpoint. Then apply the adapter from
|
| 24 |
+
the release repo if you want the distilled behavior-tuned variant.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant
|
| 86 |
+
<think>
|
| 87 |
+
' }}
|
| 88 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attn_output_gate": true,
|
| 8 |
+
"bos_token_id": null,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 248046,
|
| 11 |
+
"full_attention_interval": 4,
|
| 12 |
+
"head_dim": 256,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 5120,
|
| 15 |
+
"image_token_id": 248056,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 17408,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"linear_attention",
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"linear_conv_kernel_dim": 4,
|
| 53 |
+
"linear_key_head_dim": 128,
|
| 54 |
+
"linear_num_key_heads": 16,
|
| 55 |
+
"linear_num_value_heads": 48,
|
| 56 |
+
"linear_value_head_dim": 128,
|
| 57 |
+
"mamba_ssm_dtype": "float32",
|
| 58 |
+
"max_position_embeddings": 262144,
|
| 59 |
+
"mlp_only_layers": [],
|
| 60 |
+
"model_name": "qwen/Qwen3.5-27B",
|
| 61 |
+
"model_type": "qwen3_5",
|
| 62 |
+
"mtp_num_hidden_layers": 1,
|
| 63 |
+
"mtp_use_dedicated_embeddings": false,
|
| 64 |
+
"num_attention_heads": 24,
|
| 65 |
+
"num_hidden_layers": 32,
|
| 66 |
+
"num_key_value_heads": 4,
|
| 67 |
+
"pad_token_id": 248044,
|
| 68 |
+
"partial_rotary_factor": 0.25,
|
| 69 |
+
"rms_norm_eps": 1e-06,
|
| 70 |
+
"rope_parameters": {
|
| 71 |
+
"mrope_interleaved": true,
|
| 72 |
+
"mrope_section": [
|
| 73 |
+
11,
|
| 74 |
+
11,
|
| 75 |
+
10
|
| 76 |
+
],
|
| 77 |
+
"partial_rotary_factor": 0.25,
|
| 78 |
+
"rope_theta": 10000000,
|
| 79 |
+
"rope_type": "default"
|
| 80 |
+
},
|
| 81 |
+
"text_config": {
|
| 82 |
+
"attention_bias": false,
|
| 83 |
+
"attention_dropout": 0.0,
|
| 84 |
+
"attn_output_gate": true,
|
| 85 |
+
"bos_token_id": null,
|
| 86 |
+
"dtype": "bfloat16",
|
| 87 |
+
"eos_token_id": 248044,
|
| 88 |
+
"full_attention_interval": 4,
|
| 89 |
+
"head_dim": 256,
|
| 90 |
+
"hidden_act": "silu",
|
| 91 |
+
"hidden_size": 5120,
|
| 92 |
+
"initializer_range": 0.02,
|
| 93 |
+
"intermediate_size": 17408,
|
| 94 |
+
"layer_types": [
|
| 95 |
+
"linear_attention",
|
| 96 |
+
"linear_attention",
|
| 97 |
+
"linear_attention",
|
| 98 |
+
"linear_attention",
|
| 99 |
+
"linear_attention",
|
| 100 |
+
"linear_attention",
|
| 101 |
+
"linear_attention",
|
| 102 |
+
"linear_attention",
|
| 103 |
+
"linear_attention",
|
| 104 |
+
"linear_attention",
|
| 105 |
+
"linear_attention",
|
| 106 |
+
"linear_attention",
|
| 107 |
+
"linear_attention",
|
| 108 |
+
"linear_attention",
|
| 109 |
+
"linear_attention",
|
| 110 |
+
"linear_attention",
|
| 111 |
+
"linear_attention",
|
| 112 |
+
"full_attention",
|
| 113 |
+
"linear_attention",
|
| 114 |
+
"full_attention",
|
| 115 |
+
"linear_attention",
|
| 116 |
+
"full_attention",
|
| 117 |
+
"linear_attention",
|
| 118 |
+
"full_attention",
|
| 119 |
+
"linear_attention",
|
| 120 |
+
"full_attention",
|
| 121 |
+
"linear_attention",
|
| 122 |
+
"full_attention",
|
| 123 |
+
"linear_attention",
|
| 124 |
+
"full_attention",
|
| 125 |
+
"linear_attention",
|
| 126 |
+
"full_attention"
|
| 127 |
+
],
|
| 128 |
+
"linear_conv_kernel_dim": 4,
|
| 129 |
+
"linear_key_head_dim": 128,
|
| 130 |
+
"linear_num_key_heads": 16,
|
| 131 |
+
"linear_num_value_heads": 48,
|
| 132 |
+
"linear_value_head_dim": 128,
|
| 133 |
+
"mamba_ssm_dtype": "float32",
|
| 134 |
+
"max_position_embeddings": 262144,
|
| 135 |
+
"mlp_only_layers": [],
|
| 136 |
+
"model_type": "qwen3_5_text",
|
| 137 |
+
"mtp_num_hidden_layers": 1,
|
| 138 |
+
"mtp_use_dedicated_embeddings": false,
|
| 139 |
+
"num_attention_heads": 24,
|
| 140 |
+
"num_hidden_layers": 32,
|
| 141 |
+
"num_key_value_heads": 4,
|
| 142 |
+
"pad_token_id": null,
|
| 143 |
+
"partial_rotary_factor": 0.25,
|
| 144 |
+
"rms_norm_eps": 1e-06,
|
| 145 |
+
"rope_parameters": {
|
| 146 |
+
"mrope_interleaved": true,
|
| 147 |
+
"mrope_section": [
|
| 148 |
+
11,
|
| 149 |
+
11,
|
| 150 |
+
10
|
| 151 |
+
],
|
| 152 |
+
"partial_rotary_factor": 0.25,
|
| 153 |
+
"rope_theta": 10000000,
|
| 154 |
+
"rope_type": "default"
|
| 155 |
+
},
|
| 156 |
+
"tie_word_embeddings": false,
|
| 157 |
+
"use_cache": true,
|
| 158 |
+
"vocab_size": 248320
|
| 159 |
+
},
|
| 160 |
+
"tie_word_embeddings": false,
|
| 161 |
+
"transformers_version": "5.5.0",
|
| 162 |
+
"unsloth_version": "2026.3.3",
|
| 163 |
+
"use_cache": true,
|
| 164 |
+
"video_token_id": 248057,
|
| 165 |
+
"vision_config": {
|
| 166 |
+
"deepstack_visual_indexes": [],
|
| 167 |
+
"depth": 27,
|
| 168 |
+
"dtype": "bfloat16",
|
| 169 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 170 |
+
"hidden_size": 1152,
|
| 171 |
+
"in_channels": 3,
|
| 172 |
+
"initializer_range": 0.02,
|
| 173 |
+
"intermediate_size": 4304,
|
| 174 |
+
"model_type": "qwen3_5",
|
| 175 |
+
"num_heads": 16,
|
| 176 |
+
"num_position_embeddings": 2304,
|
| 177 |
+
"out_hidden_size": 5120,
|
| 178 |
+
"patch_size": 16,
|
| 179 |
+
"spatial_merge_size": 2,
|
| 180 |
+
"temporal_patch_size": 2
|
| 181 |
+
},
|
| 182 |
+
"vision_end_token_id": 248054,
|
| 183 |
+
"vision_start_token_id": 248053,
|
| 184 |
+
"vocab_size": 248320
|
| 185 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 248046,
|
| 4 |
+
"output_attentions": false,
|
| 5 |
+
"output_hidden_states": false,
|
| 6 |
+
"pad_token_id": 248044,
|
| 7 |
+
"transformers_version": "5.5.0",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
model-00001-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0967f474f883eebf99d6cd0f4f9ad74a915f2fe3300df6555761da47ee6d0da
|
| 3 |
+
size 4905439696
|
model-00002-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81934646ade1aad8f975ba1885ab0a660d2bc508b335b481170f914fbbbb177d
|
| 3 |
+
size 4946303592
|
model-00003-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c58eb7e1950fd795cc93e8fd015217102c814635f76875ff8582f3f4d12c8303
|
| 3 |
+
size 4955909848
|
model-00004-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:584839a59f4a8467f926d6df565f675c649cd345ec2c7c4e79fff9a107d1b207
|
| 3 |
+
size 4943108600
|
model-00005-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26b385b1caa3c990155be40d94a0ba9e1537ae3690f244ea3d0bf986102edff9
|
| 3 |
+
size 4889716984
|
model-00006-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e364322bd85642dd692d59889bfad00f57597fae9dfb45cb3f43053807e35bd3
|
| 3 |
+
size 4798379064
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,435 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 14719400192,
|
| 4 |
+
"total_size": 29438808832
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00006-of-00006.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 10 |
+
"model.layers.0.linear_attn.A_log": "model-00001-of-00006.safetensors",
|
| 11 |
+
"model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00006.safetensors",
|
| 12 |
+
"model.layers.0.linear_attn.dt_bias": "model-00001-of-00006.safetensors",
|
| 13 |
+
"model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00006.safetensors",
|
| 14 |
+
"model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00006.safetensors",
|
| 15 |
+
"model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00006.safetensors",
|
| 16 |
+
"model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00006.safetensors",
|
| 17 |
+
"model.layers.0.linear_attn.norm.weight": "model-00001-of-00006.safetensors",
|
| 18 |
+
"model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
| 19 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 20 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 21 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 22 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 23 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 24 |
+
"model.layers.1.linear_attn.A_log": "model-00001-of-00006.safetensors",
|
| 25 |
+
"model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00006.safetensors",
|
| 26 |
+
"model.layers.1.linear_attn.dt_bias": "model-00001-of-00006.safetensors",
|
| 27 |
+
"model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00006.safetensors",
|
| 28 |
+
"model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00006.safetensors",
|
| 29 |
+
"model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00006.safetensors",
|
| 30 |
+
"model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00006.safetensors",
|
| 31 |
+
"model.layers.1.linear_attn.norm.weight": "model-00001-of-00006.safetensors",
|
| 32 |
+
"model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
| 33 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 34 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 35 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 36 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 37 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 38 |
+
"model.layers.10.linear_attn.A_log": "model-00003-of-00006.safetensors",
|
| 39 |
+
"model.layers.10.linear_attn.conv1d.weight": "model-00003-of-00006.safetensors",
|
| 40 |
+
"model.layers.10.linear_attn.dt_bias": "model-00003-of-00006.safetensors",
|
| 41 |
+
"model.layers.10.linear_attn.in_proj_a.weight": "model-00003-of-00006.safetensors",
|
| 42 |
+
"model.layers.10.linear_attn.in_proj_b.weight": "model-00003-of-00006.safetensors",
|
| 43 |
+
"model.layers.10.linear_attn.in_proj_qkv.weight": "model-00003-of-00006.safetensors",
|
| 44 |
+
"model.layers.10.linear_attn.in_proj_z.weight": "model-00003-of-00006.safetensors",
|
| 45 |
+
"model.layers.10.linear_attn.norm.weight": "model-00003-of-00006.safetensors",
|
| 46 |
+
"model.layers.10.linear_attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 47 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 48 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 49 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 50 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 51 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 52 |
+
"model.layers.11.linear_attn.A_log": "model-00003-of-00006.safetensors",
|
| 53 |
+
"model.layers.11.linear_attn.conv1d.weight": "model-00003-of-00006.safetensors",
|
| 54 |
+
"model.layers.11.linear_attn.dt_bias": "model-00003-of-00006.safetensors",
|
| 55 |
+
"model.layers.11.linear_attn.in_proj_a.weight": "model-00003-of-00006.safetensors",
|
| 56 |
+
"model.layers.11.linear_attn.in_proj_b.weight": "model-00003-of-00006.safetensors",
|
| 57 |
+
"model.layers.11.linear_attn.in_proj_qkv.weight": "model-00003-of-00006.safetensors",
|
| 58 |
+
"model.layers.11.linear_attn.in_proj_z.weight": "model-00003-of-00006.safetensors",
|
| 59 |
+
"model.layers.11.linear_attn.norm.weight": "model-00003-of-00006.safetensors",
|
| 60 |
+
"model.layers.11.linear_attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 61 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 62 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 63 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 64 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 65 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 66 |
+
"model.layers.12.linear_attn.A_log": "model-00003-of-00006.safetensors",
|
| 67 |
+
"model.layers.12.linear_attn.conv1d.weight": "model-00003-of-00006.safetensors",
|
| 68 |
+
"model.layers.12.linear_attn.dt_bias": "model-00003-of-00006.safetensors",
|
| 69 |
+
"model.layers.12.linear_attn.in_proj_a.weight": "model-00003-of-00006.safetensors",
|
| 70 |
+
"model.layers.12.linear_attn.in_proj_b.weight": "model-00003-of-00006.safetensors",
|
| 71 |
+
"model.layers.12.linear_attn.in_proj_qkv.weight": "model-00003-of-00006.safetensors",
|
| 72 |
+
"model.layers.12.linear_attn.in_proj_z.weight": "model-00003-of-00006.safetensors",
|
| 73 |
+
"model.layers.12.linear_attn.norm.weight": "model-00003-of-00006.safetensors",
|
| 74 |
+
"model.layers.12.linear_attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 75 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 76 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 77 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 78 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 79 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 80 |
+
"model.layers.13.linear_attn.A_log": "model-00003-of-00006.safetensors",
|
| 81 |
+
"model.layers.13.linear_attn.conv1d.weight": "model-00003-of-00006.safetensors",
|
| 82 |
+
"model.layers.13.linear_attn.dt_bias": "model-00003-of-00006.safetensors",
|
| 83 |
+
"model.layers.13.linear_attn.in_proj_a.weight": "model-00003-of-00006.safetensors",
|
| 84 |
+
"model.layers.13.linear_attn.in_proj_b.weight": "model-00003-of-00006.safetensors",
|
| 85 |
+
"model.layers.13.linear_attn.in_proj_qkv.weight": "model-00003-of-00006.safetensors",
|
| 86 |
+
"model.layers.13.linear_attn.in_proj_z.weight": "model-00003-of-00006.safetensors",
|
| 87 |
+
"model.layers.13.linear_attn.norm.weight": "model-00003-of-00006.safetensors",
|
| 88 |
+
"model.layers.13.linear_attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 89 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 90 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 91 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 92 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 93 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 94 |
+
"model.layers.14.linear_attn.A_log": "model-00003-of-00006.safetensors",
|
| 95 |
+
"model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00006.safetensors",
|
| 96 |
+
"model.layers.14.linear_attn.dt_bias": "model-00003-of-00006.safetensors",
|
| 97 |
+
"model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00006.safetensors",
|
| 98 |
+
"model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00006.safetensors",
|
| 99 |
+
"model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00006.safetensors",
|
| 100 |
+
"model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00006.safetensors",
|
| 101 |
+
"model.layers.14.linear_attn.norm.weight": "model-00003-of-00006.safetensors",
|
| 102 |
+
"model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 103 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 104 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 105 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 106 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 107 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 108 |
+
"model.layers.15.linear_attn.A_log": "model-00003-of-00006.safetensors",
|
| 109 |
+
"model.layers.15.linear_attn.conv1d.weight": "model-00003-of-00006.safetensors",
|
| 110 |
+
"model.layers.15.linear_attn.dt_bias": "model-00003-of-00006.safetensors",
|
| 111 |
+
"model.layers.15.linear_attn.in_proj_a.weight": "model-00003-of-00006.safetensors",
|
| 112 |
+
"model.layers.15.linear_attn.in_proj_b.weight": "model-00003-of-00006.safetensors",
|
| 113 |
+
"model.layers.15.linear_attn.in_proj_qkv.weight": "model-00003-of-00006.safetensors",
|
| 114 |
+
"model.layers.15.linear_attn.in_proj_z.weight": "model-00003-of-00006.safetensors",
|
| 115 |
+
"model.layers.15.linear_attn.norm.weight": "model-00003-of-00006.safetensors",
|
| 116 |
+
"model.layers.15.linear_attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 117 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 118 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 119 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 120 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 121 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 122 |
+
"model.layers.16.linear_attn.A_log": "model-00003-of-00006.safetensors",
|
| 123 |
+
"model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00006.safetensors",
|
| 124 |
+
"model.layers.16.linear_attn.dt_bias": "model-00003-of-00006.safetensors",
|
| 125 |
+
"model.layers.16.linear_attn.in_proj_a.weight": "model-00004-of-00006.safetensors",
|
| 126 |
+
"model.layers.16.linear_attn.in_proj_b.weight": "model-00004-of-00006.safetensors",
|
| 127 |
+
"model.layers.16.linear_attn.in_proj_qkv.weight": "model-00004-of-00006.safetensors",
|
| 128 |
+
"model.layers.16.linear_attn.in_proj_z.weight": "model-00004-of-00006.safetensors",
|
| 129 |
+
"model.layers.16.linear_attn.norm.weight": "model-00003-of-00006.safetensors",
|
| 130 |
+
"model.layers.16.linear_attn.out_proj.weight": "model-00004-of-00006.safetensors",
|
| 131 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 132 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 133 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 134 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 135 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 136 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 137 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 138 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 139 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 140 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 141 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 142 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 143 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 144 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 145 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 146 |
+
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 147 |
+
"model.layers.18.linear_attn.A_log": "model-00004-of-00006.safetensors",
|
| 148 |
+
"model.layers.18.linear_attn.conv1d.weight": "model-00004-of-00006.safetensors",
|
| 149 |
+
"model.layers.18.linear_attn.dt_bias": "model-00004-of-00006.safetensors",
|
| 150 |
+
"model.layers.18.linear_attn.in_proj_a.weight": "model-00004-of-00006.safetensors",
|
| 151 |
+
"model.layers.18.linear_attn.in_proj_b.weight": "model-00004-of-00006.safetensors",
|
| 152 |
+
"model.layers.18.linear_attn.in_proj_qkv.weight": "model-00004-of-00006.safetensors",
|
| 153 |
+
"model.layers.18.linear_attn.in_proj_z.weight": "model-00004-of-00006.safetensors",
|
| 154 |
+
"model.layers.18.linear_attn.norm.weight": "model-00004-of-00006.safetensors",
|
| 155 |
+
"model.layers.18.linear_attn.out_proj.weight": "model-00004-of-00006.safetensors",
|
| 156 |
+
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 157 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 158 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 159 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 160 |
+
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 161 |
+
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 162 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 163 |
+
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 164 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 165 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 166 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 167 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 168 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 169 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 170 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 171 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 172 |
+
"model.layers.2.linear_attn.A_log": "model-00001-of-00006.safetensors",
|
| 173 |
+
"model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00006.safetensors",
|
| 174 |
+
"model.layers.2.linear_attn.dt_bias": "model-00001-of-00006.safetensors",
|
| 175 |
+
"model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00006.safetensors",
|
| 176 |
+
"model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00006.safetensors",
|
| 177 |
+
"model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00006.safetensors",
|
| 178 |
+
"model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00006.safetensors",
|
| 179 |
+
"model.layers.2.linear_attn.norm.weight": "model-00001-of-00006.safetensors",
|
| 180 |
+
"model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
| 181 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 182 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 183 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 184 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 185 |
+
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 186 |
+
"model.layers.20.linear_attn.A_log": "model-00004-of-00006.safetensors",
|
| 187 |
+
"model.layers.20.linear_attn.conv1d.weight": "model-00004-of-00006.safetensors",
|
| 188 |
+
"model.layers.20.linear_attn.dt_bias": "model-00004-of-00006.safetensors",
|
| 189 |
+
"model.layers.20.linear_attn.in_proj_a.weight": "model-00004-of-00006.safetensors",
|
| 190 |
+
"model.layers.20.linear_attn.in_proj_b.weight": "model-00004-of-00006.safetensors",
|
| 191 |
+
"model.layers.20.linear_attn.in_proj_qkv.weight": "model-00004-of-00006.safetensors",
|
| 192 |
+
"model.layers.20.linear_attn.in_proj_z.weight": "model-00004-of-00006.safetensors",
|
| 193 |
+
"model.layers.20.linear_attn.norm.weight": "model-00004-of-00006.safetensors",
|
| 194 |
+
"model.layers.20.linear_attn.out_proj.weight": "model-00004-of-00006.safetensors",
|
| 195 |
+
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 196 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 197 |
+
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 198 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 199 |
+
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 200 |
+
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 201 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 202 |
+
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 203 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 204 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
| 205 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 206 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 207 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
| 208 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 209 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 210 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 211 |
+
"model.layers.22.linear_attn.A_log": "model-00004-of-00006.safetensors",
|
| 212 |
+
"model.layers.22.linear_attn.conv1d.weight": "model-00004-of-00006.safetensors",
|
| 213 |
+
"model.layers.22.linear_attn.dt_bias": "model-00004-of-00006.safetensors",
|
| 214 |
+
"model.layers.22.linear_attn.in_proj_a.weight": "model-00004-of-00006.safetensors",
|
| 215 |
+
"model.layers.22.linear_attn.in_proj_b.weight": "model-00004-of-00006.safetensors",
|
| 216 |
+
"model.layers.22.linear_attn.in_proj_qkv.weight": "model-00004-of-00006.safetensors",
|
| 217 |
+
"model.layers.22.linear_attn.in_proj_z.weight": "model-00004-of-00006.safetensors",
|
| 218 |
+
"model.layers.22.linear_attn.norm.weight": "model-00004-of-00006.safetensors",
|
| 219 |
+
"model.layers.22.linear_attn.out_proj.weight": "model-00004-of-00006.safetensors",
|
| 220 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 221 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 222 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 223 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 224 |
+
"model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 225 |
+
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 226 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 227 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 228 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 229 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 230 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 231 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 232 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 233 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 234 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 235 |
+
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 236 |
+
"model.layers.24.linear_attn.A_log": "model-00005-of-00006.safetensors",
|
| 237 |
+
"model.layers.24.linear_attn.conv1d.weight": "model-00005-of-00006.safetensors",
|
| 238 |
+
"model.layers.24.linear_attn.dt_bias": "model-00005-of-00006.safetensors",
|
| 239 |
+
"model.layers.24.linear_attn.in_proj_a.weight": "model-00005-of-00006.safetensors",
|
| 240 |
+
"model.layers.24.linear_attn.in_proj_b.weight": "model-00005-of-00006.safetensors",
|
| 241 |
+
"model.layers.24.linear_attn.in_proj_qkv.weight": "model-00005-of-00006.safetensors",
|
| 242 |
+
"model.layers.24.linear_attn.in_proj_z.weight": "model-00005-of-00006.safetensors",
|
| 243 |
+
"model.layers.24.linear_attn.norm.weight": "model-00005-of-00006.safetensors",
|
| 244 |
+
"model.layers.24.linear_attn.out_proj.weight": "model-00005-of-00006.safetensors",
|
| 245 |
+
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 246 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 247 |
+
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 248 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 249 |
+
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 250 |
+
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 251 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 252 |
+
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 253 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 254 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 255 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 256 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 257 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 258 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 259 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 260 |
+
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 261 |
+
"model.layers.26.linear_attn.A_log": "model-00005-of-00006.safetensors",
|
| 262 |
+
"model.layers.26.linear_attn.conv1d.weight": "model-00005-of-00006.safetensors",
|
| 263 |
+
"model.layers.26.linear_attn.dt_bias": "model-00005-of-00006.safetensors",
|
| 264 |
+
"model.layers.26.linear_attn.in_proj_a.weight": "model-00005-of-00006.safetensors",
|
| 265 |
+
"model.layers.26.linear_attn.in_proj_b.weight": "model-00005-of-00006.safetensors",
|
| 266 |
+
"model.layers.26.linear_attn.in_proj_qkv.weight": "model-00005-of-00006.safetensors",
|
| 267 |
+
"model.layers.26.linear_attn.in_proj_z.weight": "model-00005-of-00006.safetensors",
|
| 268 |
+
"model.layers.26.linear_attn.norm.weight": "model-00005-of-00006.safetensors",
|
| 269 |
+
"model.layers.26.linear_attn.out_proj.weight": "model-00005-of-00006.safetensors",
|
| 270 |
+
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 271 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 272 |
+
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 273 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 274 |
+
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 275 |
+
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 276 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 277 |
+
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 278 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 279 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
| 280 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 281 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 282 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
| 283 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 284 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 285 |
+
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 286 |
+
"model.layers.28.linear_attn.A_log": "model-00005-of-00006.safetensors",
|
| 287 |
+
"model.layers.28.linear_attn.conv1d.weight": "model-00005-of-00006.safetensors",
|
| 288 |
+
"model.layers.28.linear_attn.dt_bias": "model-00005-of-00006.safetensors",
|
| 289 |
+
"model.layers.28.linear_attn.in_proj_a.weight": "model-00005-of-00006.safetensors",
|
| 290 |
+
"model.layers.28.linear_attn.in_proj_b.weight": "model-00005-of-00006.safetensors",
|
| 291 |
+
"model.layers.28.linear_attn.in_proj_qkv.weight": "model-00005-of-00006.safetensors",
|
| 292 |
+
"model.layers.28.linear_attn.in_proj_z.weight": "model-00005-of-00006.safetensors",
|
| 293 |
+
"model.layers.28.linear_attn.norm.weight": "model-00005-of-00006.safetensors",
|
| 294 |
+
"model.layers.28.linear_attn.out_proj.weight": "model-00005-of-00006.safetensors",
|
| 295 |
+
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 296 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 297 |
+
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 298 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 299 |
+
"model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 300 |
+
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 301 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 302 |
+
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 303 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 304 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
| 305 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 306 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 307 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
| 308 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 309 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 310 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 311 |
+
"model.layers.3.linear_attn.A_log": "model-00001-of-00006.safetensors",
|
| 312 |
+
"model.layers.3.linear_attn.conv1d.weight": "model-00001-of-00006.safetensors",
|
| 313 |
+
"model.layers.3.linear_attn.dt_bias": "model-00001-of-00006.safetensors",
|
| 314 |
+
"model.layers.3.linear_attn.in_proj_a.weight": "model-00002-of-00006.safetensors",
|
| 315 |
+
"model.layers.3.linear_attn.in_proj_b.weight": "model-00002-of-00006.safetensors",
|
| 316 |
+
"model.layers.3.linear_attn.in_proj_qkv.weight": "model-00002-of-00006.safetensors",
|
| 317 |
+
"model.layers.3.linear_attn.in_proj_z.weight": "model-00002-of-00006.safetensors",
|
| 318 |
+
"model.layers.3.linear_attn.norm.weight": "model-00001-of-00006.safetensors",
|
| 319 |
+
"model.layers.3.linear_attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
| 320 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 321 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 322 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 323 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 324 |
+
"model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 325 |
+
"model.layers.30.linear_attn.A_log": "model-00006-of-00006.safetensors",
|
| 326 |
+
"model.layers.30.linear_attn.conv1d.weight": "model-00006-of-00006.safetensors",
|
| 327 |
+
"model.layers.30.linear_attn.dt_bias": "model-00006-of-00006.safetensors",
|
| 328 |
+
"model.layers.30.linear_attn.in_proj_a.weight": "model-00006-of-00006.safetensors",
|
| 329 |
+
"model.layers.30.linear_attn.in_proj_b.weight": "model-00006-of-00006.safetensors",
|
| 330 |
+
"model.layers.30.linear_attn.in_proj_qkv.weight": "model-00006-of-00006.safetensors",
|
| 331 |
+
"model.layers.30.linear_attn.in_proj_z.weight": "model-00006-of-00006.safetensors",
|
| 332 |
+
"model.layers.30.linear_attn.norm.weight": "model-00006-of-00006.safetensors",
|
| 333 |
+
"model.layers.30.linear_attn.out_proj.weight": "model-00006-of-00006.safetensors",
|
| 334 |
+
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 335 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 336 |
+
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 337 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 338 |
+
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 339 |
+
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 340 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 341 |
+
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 342 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 343 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
| 344 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 345 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 346 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
| 347 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 348 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 349 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 350 |
+
"model.layers.4.linear_attn.A_log": "model-00002-of-00006.safetensors",
|
| 351 |
+
"model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00006.safetensors",
|
| 352 |
+
"model.layers.4.linear_attn.dt_bias": "model-00002-of-00006.safetensors",
|
| 353 |
+
"model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00006.safetensors",
|
| 354 |
+
"model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00006.safetensors",
|
| 355 |
+
"model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00006.safetensors",
|
| 356 |
+
"model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00006.safetensors",
|
| 357 |
+
"model.layers.4.linear_attn.norm.weight": "model-00002-of-00006.safetensors",
|
| 358 |
+
"model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 359 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 360 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 361 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 362 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 363 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 364 |
+
"model.layers.5.linear_attn.A_log": "model-00002-of-00006.safetensors",
|
| 365 |
+
"model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00006.safetensors",
|
| 366 |
+
"model.layers.5.linear_attn.dt_bias": "model-00002-of-00006.safetensors",
|
| 367 |
+
"model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00006.safetensors",
|
| 368 |
+
"model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00006.safetensors",
|
| 369 |
+
"model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00006.safetensors",
|
| 370 |
+
"model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00006.safetensors",
|
| 371 |
+
"model.layers.5.linear_attn.norm.weight": "model-00002-of-00006.safetensors",
|
| 372 |
+
"model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 373 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 374 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 375 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 376 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 377 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 378 |
+
"model.layers.6.linear_attn.A_log": "model-00002-of-00006.safetensors",
|
| 379 |
+
"model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00006.safetensors",
|
| 380 |
+
"model.layers.6.linear_attn.dt_bias": "model-00002-of-00006.safetensors",
|
| 381 |
+
"model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00006.safetensors",
|
| 382 |
+
"model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00006.safetensors",
|
| 383 |
+
"model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00006.safetensors",
|
| 384 |
+
"model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00006.safetensors",
|
| 385 |
+
"model.layers.6.linear_attn.norm.weight": "model-00002-of-00006.safetensors",
|
| 386 |
+
"model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 387 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 388 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 389 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 390 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 391 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 392 |
+
"model.layers.7.linear_attn.A_log": "model-00002-of-00006.safetensors",
|
| 393 |
+
"model.layers.7.linear_attn.conv1d.weight": "model-00002-of-00006.safetensors",
|
| 394 |
+
"model.layers.7.linear_attn.dt_bias": "model-00002-of-00006.safetensors",
|
| 395 |
+
"model.layers.7.linear_attn.in_proj_a.weight": "model-00002-of-00006.safetensors",
|
| 396 |
+
"model.layers.7.linear_attn.in_proj_b.weight": "model-00002-of-00006.safetensors",
|
| 397 |
+
"model.layers.7.linear_attn.in_proj_qkv.weight": "model-00002-of-00006.safetensors",
|
| 398 |
+
"model.layers.7.linear_attn.in_proj_z.weight": "model-00002-of-00006.safetensors",
|
| 399 |
+
"model.layers.7.linear_attn.norm.weight": "model-00002-of-00006.safetensors",
|
| 400 |
+
"model.layers.7.linear_attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 401 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 402 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 403 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 404 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 405 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 406 |
+
"model.layers.8.linear_attn.A_log": "model-00002-of-00006.safetensors",
|
| 407 |
+
"model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00006.safetensors",
|
| 408 |
+
"model.layers.8.linear_attn.dt_bias": "model-00002-of-00006.safetensors",
|
| 409 |
+
"model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00006.safetensors",
|
| 410 |
+
"model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00006.safetensors",
|
| 411 |
+
"model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00006.safetensors",
|
| 412 |
+
"model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00006.safetensors",
|
| 413 |
+
"model.layers.8.linear_attn.norm.weight": "model-00002-of-00006.safetensors",
|
| 414 |
+
"model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 415 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 416 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 417 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 418 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 419 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 420 |
+
"model.layers.9.linear_attn.A_log": "model-00002-of-00006.safetensors",
|
| 421 |
+
"model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00006.safetensors",
|
| 422 |
+
"model.layers.9.linear_attn.dt_bias": "model-00002-of-00006.safetensors",
|
| 423 |
+
"model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00006.safetensors",
|
| 424 |
+
"model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00006.safetensors",
|
| 425 |
+
"model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00006.safetensors",
|
| 426 |
+
"model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00006.safetensors",
|
| 427 |
+
"model.layers.9.linear_attn.norm.weight": "model-00002-of-00006.safetensors",
|
| 428 |
+
"model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 429 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 430 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 431 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 432 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 433 |
+
"model.norm.weight": "model-00006-of-00006.safetensors"
|
| 434 |
+
}
|
| 435 |
+
}
|
slice.log
ADDED
|
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
DEPRECATED: The legacy builder is deprecated and will be removed in a future release.
|
| 2 |
+
Install the buildx component to build images with BuildKit:
|
| 3 |
+
https://docs.docker.com/go/buildx/
|
| 4 |
+
|
| 5 |
+
Sending build context to Docker daemon 114.7kB
|
| 6 |
+
Step 1/9 : ARG PYTORCH_IMAGE=pytorch/pytorch:2.6.0-cuda12.4-cudnn9-devel
|
| 7 |
+
Step 2/9 : FROM ${PYTORCH_IMAGE}
|
| 8 |
+
2.6.0-cuda12.4-cudnn9-devel: Pulling from pytorch/pytorch
|
| 9 |
+
0a5030f9ea59: Pulling fs layer
|
| 10 |
+
b71b637b97c5: Pulling fs layer
|
| 11 |
+
7021d1b70935: Pulling fs layer
|
| 12 |
+
312a542960e3: Pulling fs layer
|
| 13 |
+
fd9cc1ad8dee: Pulling fs layer
|
| 14 |
+
47b8539d532f: Pulling fs layer
|
| 15 |
+
4f4fb700ef54: Pulling fs layer
|
| 16 |
+
56dc85502937: Pulling fs layer
|
| 17 |
+
8e79813a7b9d: Pulling fs layer
|
| 18 |
+
83525caeeb35: Pulling fs layer
|
| 19 |
+
0d6448aff889: Pulling fs layer
|
| 20 |
+
ec6d5f6c9ed9: Pulling fs layer
|
| 21 |
+
3e14b472177a: Pulling fs layer
|
| 22 |
+
e97dfafebbe6: Pulling fs layer
|
| 23 |
+
0a7674e3e8fe: Pulling fs layer
|
| 24 |
+
b71b637b97c5: Download complete
|
| 25 |
+
47b8539d532f: Download complete
|
| 26 |
+
312a542960e3: Download complete
|
| 27 |
+
83525caeeb35: Download complete
|
| 28 |
+
fd9cc1ad8dee: Download complete
|
| 29 |
+
4f4fb700ef54: Download complete
|
| 30 |
+
56dc85502937: Download complete
|
| 31 |
+
0a5030f9ea59: Download complete
|
| 32 |
+
3e14b472177a: Download complete
|
| 33 |
+
0d6448aff889: Download complete
|
| 34 |
+
7021d1b70935: Download complete
|
| 35 |
+
7021d1b70935: Pull complete
|
| 36 |
+
0d6448aff889: Pull complete
|
| 37 |
+
0a7674e3e8fe: Download complete
|
| 38 |
+
0a7674e3e8fe: Pull complete
|
| 39 |
+
b71b637b97c5: Pull complete
|
| 40 |
+
56dc85502937: Pull complete
|
| 41 |
+
ec6d5f6c9ed9: Download complete
|
| 42 |
+
ec6d5f6c9ed9: Pull complete
|
| 43 |
+
47b8539d532f: Pull complete
|
| 44 |
+
fd9cc1ad8dee: Pull complete
|
| 45 |
+
83525caeeb35: Pull complete
|
| 46 |
+
8e79813a7b9d: Download complete
|
| 47 |
+
e97dfafebbe6: Download complete
|
| 48 |
+
312a542960e3: Pull complete
|
| 49 |
+
3e14b472177a: Pull complete
|
| 50 |
+
8e79813a7b9d: Pull complete
|
| 51 |
+
4f4fb700ef54: Pull complete
|
| 52 |
+
e97dfafebbe6: Pull complete
|
| 53 |
+
0a5030f9ea59: Pull complete
|
| 54 |
+
Digest: sha256:0cf3402e946b7c384ba943ee05c90b4c5a4a05227923921f2b0918c011cfaf56
|
| 55 |
+
Status: Downloaded newer image for pytorch/pytorch:2.6.0-cuda12.4-cudnn9-devel
|
| 56 |
+
---> 0cf3402e946b
|
| 57 |
+
Step 3/9 : ENV DEBIAN_FRONTEND=noninteractive
|
| 58 |
+
---> Running in 763373b24589
|
| 59 |
+
---> Removed intermediate container 763373b24589
|
| 60 |
+
---> a0a6102cf64c
|
| 61 |
+
Step 4/9 : ENV PIP_DISABLE_PIP_VERSION_CHECK=1
|
| 62 |
+
---> Running in 801afd576ce4
|
| 63 |
+
---> Removed intermediate container 801afd576ce4
|
| 64 |
+
---> 56ed7d48bc3a
|
| 65 |
+
Step 5/9 : ENV PYTHONUNBUFFERED=1
|
| 66 |
+
---> Running in 4dd50a0920fe
|
| 67 |
+
---> Removed intermediate container 4dd50a0920fe
|
| 68 |
+
---> 7c45cea384bc
|
| 69 |
+
Step 6/9 : RUN apt-get update && apt-get install -y --no-install-recommends git curl ca-certificates && rm -rf /var/lib/apt/lists/*
|
| 70 |
+
---> Running in a18056f16af6
|
| 71 |
+
Get:1 http://archive.ubuntu.com/ubuntu jammy InRelease [270 kB]
|
| 72 |
+
Get:2 http://security.ubuntu.com/ubuntu jammy-security InRelease [129 kB]
|
| 73 |
+
Get:3 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64 InRelease [1581 B]
|
| 74 |
+
Get:4 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64 Packages [2482 kB]
|
| 75 |
+
Get:5 http://archive.ubuntu.com/ubuntu jammy-updates InRelease [128 kB]
|
| 76 |
+
Get:6 http://archive.ubuntu.com/ubuntu jammy-backports InRelease [127 kB]
|
| 77 |
+
Get:7 http://security.ubuntu.com/ubuntu jammy-security/multiverse amd64 Packages [62.6 kB]
|
| 78 |
+
Get:8 http://archive.ubuntu.com/ubuntu jammy/main amd64 Packages [1792 kB]
|
| 79 |
+
Get:9 http://security.ubuntu.com/ubuntu jammy-security/restricted amd64 Packages [6803 kB]
|
| 80 |
+
Get:10 http://archive.ubuntu.com/ubuntu jammy/multiverse amd64 Packages [266 kB]
|
| 81 |
+
Get:11 http://archive.ubuntu.com/ubuntu jammy/restricted amd64 Packages [164 kB]
|
| 82 |
+
Get:12 http://archive.ubuntu.com/ubuntu jammy/universe amd64 Packages [17.5 MB]
|
| 83 |
+
Get:13 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 Packages [4219 kB]
|
| 84 |
+
Get:14 http://archive.ubuntu.com/ubuntu jammy-updates/universe amd64 Packages [1622 kB]
|
| 85 |
+
Get:15 http://archive.ubuntu.com/ubuntu jammy-updates/restricted amd64 Packages [7125 kB]
|
| 86 |
+
Get:16 http://archive.ubuntu.com/ubuntu jammy-updates/multiverse amd64 Packages [70.9 kB]
|
| 87 |
+
Get:17 http://archive.ubuntu.com/ubuntu jammy-backports/universe amd64 Packages [35.6 kB]
|
| 88 |
+
Get:18 http://archive.ubuntu.com/ubuntu jammy-backports/main amd64 Packages [84.0 kB]
|
| 89 |
+
Get:19 http://security.ubuntu.com/ubuntu jammy-security/main amd64 Packages [3844 kB]
|
| 90 |
+
Get:20 http://security.ubuntu.com/ubuntu jammy-security/universe amd64 Packages [1310 kB]
|
| 91 |
+
Fetched 48.0 MB in 4s (12.9 MB/s)
|
| 92 |
+
Reading package lists...
|
| 93 |
+
Reading package lists...
|
| 94 |
+
Building dependency tree...
|
| 95 |
+
Reading state information...
|
| 96 |
+
ca-certificates is already the newest version (20240203~22.04.1).
|
| 97 |
+
The following additional packages will be installed:
|
| 98 |
+
git-man libbrotli1 libcurl3-gnutls libcurl4 liberror-perl libexpat1
|
| 99 |
+
libnghttp2-14 libpsl5 librtmp1 libssh-4
|
| 100 |
+
Suggested packages:
|
| 101 |
+
gettext-base git-daemon-run | git-daemon-sysvinit git-doc git-email git-gui
|
| 102 |
+
gitk gitweb git-cvs git-mediawiki git-svn
|
| 103 |
+
Recommended packages:
|
| 104 |
+
less ssh-client publicsuffix
|
| 105 |
+
The following NEW packages will be installed:
|
| 106 |
+
curl git git-man libbrotli1 libcurl3-gnutls libcurl4 liberror-perl libexpat1
|
| 107 |
+
libnghttp2-14 libpsl5 librtmp1 libssh-4
|
| 108 |
+
0 upgraded, 12 newly installed, 0 to remove and 89 not upgraded.
|
| 109 |
+
Need to get 5711 kB of archives.
|
| 110 |
+
After this operation, 25.3 MB of additional disk space will be used.
|
| 111 |
+
Get:1 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 libexpat1 amd64 2.4.7-1ubuntu0.7 [92.1 kB]
|
| 112 |
+
Get:2 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 libnghttp2-14 amd64 1.43.0-1ubuntu0.2 [76.9 kB]
|
| 113 |
+
Get:3 http://archive.ubuntu.com/ubuntu jammy/main amd64 libpsl5 amd64 0.21.0-1.2build2 [58.4 kB]
|
| 114 |
+
Get:4 http://archive.ubuntu.com/ubuntu jammy/main amd64 libbrotli1 amd64 1.0.9-2build6 [315 kB]
|
| 115 |
+
Get:5 http://archive.ubuntu.com/ubuntu jammy/main amd64 librtmp1 amd64 2.4+20151223.gitfa8646d.1-2build4 [58.2 kB]
|
| 116 |
+
Get:6 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 libssh-4 amd64 0.9.6-2ubuntu0.22.04.7 [187 kB]
|
| 117 |
+
Get:7 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 libcurl4 amd64 7.81.0-1ubuntu1.23 [290 kB]
|
| 118 |
+
Get:8 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 curl amd64 7.81.0-1ubuntu1.23 [194 kB]
|
| 119 |
+
Get:9 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 libcurl3-gnutls amd64 7.81.0-1ubuntu1.23 [284 kB]
|
| 120 |
+
Get:10 http://archive.ubuntu.com/ubuntu jammy/main amd64 liberror-perl all 0.17029-1 [26.5 kB]
|
| 121 |
+
Get:11 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 git-man all 1:2.34.1-1ubuntu1.17 [954 kB]
|
| 122 |
+
Get:12 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 git amd64 1:2.34.1-1ubuntu1.17 [3174 kB]
|
| 123 |
+
[91mdebconf: delaying package configuration, since apt-utils is not installed
|
| 124 |
+
[0mFetched 5711 kB in 1s (8249 kB/s)
|
| 125 |
+
Selecting previously unselected package libexpat1:amd64.
|
| 126 |
+
(Reading database ...
|
| 127 |
+
Preparing to unpack .../00-libexpat1_2.4.7-1ubuntu0.7_amd64.deb ...
|
| 128 |
+
Unpacking libexpat1:amd64 (2.4.7-1ubuntu0.7) ...
|
| 129 |
+
Selecting previously unselected package libnghttp2-14:amd64.
|
| 130 |
+
Preparing to unpack .../01-libnghttp2-14_1.43.0-1ubuntu0.2_amd64.deb ...
|
| 131 |
+
Unpacking libnghttp2-14:amd64 (1.43.0-1ubuntu0.2) ...
|
| 132 |
+
Selecting previously unselected package libpsl5:amd64.
|
| 133 |
+
Preparing to unpack .../02-libpsl5_0.21.0-1.2build2_amd64.deb ...
|
| 134 |
+
Unpacking libpsl5:amd64 (0.21.0-1.2build2) ...
|
| 135 |
+
Selecting previously unselected package libbrotli1:amd64.
|
| 136 |
+
Preparing to unpack .../03-libbrotli1_1.0.9-2build6_amd64.deb ...
|
| 137 |
+
Unpacking libbrotli1:amd64 (1.0.9-2build6) ...
|
| 138 |
+
Selecting previously unselected package librtmp1:amd64.
|
| 139 |
+
Preparing to unpack .../04-librtmp1_2.4+20151223.gitfa8646d.1-2build4_amd64.deb ...
|
| 140 |
+
Unpacking librtmp1:amd64 (2.4+20151223.gitfa8646d.1-2build4) ...
|
| 141 |
+
Selecting previously unselected package libssh-4:amd64.
|
| 142 |
+
Preparing to unpack .../05-libssh-4_0.9.6-2ubuntu0.22.04.7_amd64.deb ...
|
| 143 |
+
Unpacking libssh-4:amd64 (0.9.6-2ubuntu0.22.04.7) ...
|
| 144 |
+
Selecting previously unselected package libcurl4:amd64.
|
| 145 |
+
Preparing to unpack .../06-libcurl4_7.81.0-1ubuntu1.23_amd64.deb ...
|
| 146 |
+
Unpacking libcurl4:amd64 (7.81.0-1ubuntu1.23) ...
|
| 147 |
+
Selecting previously unselected package curl.
|
| 148 |
+
Preparing to unpack .../07-curl_7.81.0-1ubuntu1.23_amd64.deb ...
|
| 149 |
+
Unpacking curl (7.81.0-1ubuntu1.23) ...
|
| 150 |
+
Selecting previously unselected package libcurl3-gnutls:amd64.
|
| 151 |
+
Preparing to unpack .../08-libcurl3-gnutls_7.81.0-1ubuntu1.23_amd64.deb ...
|
| 152 |
+
Unpacking libcurl3-gnutls:amd64 (7.81.0-1ubuntu1.23) ...
|
| 153 |
+
Selecting previously unselected package liberror-perl.
|
| 154 |
+
Preparing to unpack .../09-liberror-perl_0.17029-1_all.deb ...
|
| 155 |
+
Unpacking liberror-perl (0.17029-1) ...
|
| 156 |
+
Selecting previously unselected package git-man.
|
| 157 |
+
Preparing to unpack .../10-git-man_1%3a2.34.1-1ubuntu1.17_all.deb ...
|
| 158 |
+
Unpacking git-man (1:2.34.1-1ubuntu1.17) ...
|
| 159 |
+
Selecting previously unselected package git.
|
| 160 |
+
Preparing to unpack .../11-git_1%3a2.34.1-1ubuntu1.17_amd64.deb ...
|
| 161 |
+
Unpacking git (1:2.34.1-1ubuntu1.17) ...
|
| 162 |
+
Setting up libexpat1:amd64 (2.4.7-1ubuntu0.7) ...
|
| 163 |
+
Setting up libpsl5:amd64 (0.21.0-1.2build2) ...
|
| 164 |
+
Setting up libbrotli1:amd64 (1.0.9-2build6) ...
|
| 165 |
+
Setting up libnghttp2-14:amd64 (1.43.0-1ubuntu0.2) ...
|
| 166 |
+
Setting up liberror-perl (0.17029-1) ...
|
| 167 |
+
Setting up librtmp1:amd64 (2.4+20151223.gitfa8646d.1-2build4) ...
|
| 168 |
+
Setting up libssh-4:amd64 (0.9.6-2ubuntu0.22.04.7) ...
|
| 169 |
+
Setting up libcurl4:amd64 (7.81.0-1ubuntu1.23) ...
|
| 170 |
+
Setting up git-man (1:2.34.1-1ubuntu1.17) ...
|
| 171 |
+
Setting up curl (7.81.0-1ubuntu1.23) ...
|
| 172 |
+
Setting up libcurl3-gnutls:amd64 (7.81.0-1ubuntu1.23) ...
|
| 173 |
+
Setting up git (1:2.34.1-1ubuntu1.17) ...
|
| 174 |
+
Processing triggers for libc-bin (2.35-0ubuntu3.6) ...
|
| 175 |
+
---> Removed intermediate container a18056f16af6
|
| 176 |
+
---> b77b6d7f78bb
|
| 177 |
+
Step 7/9 : RUN python -m pip install --no-cache-dir accelerate datasets bitsandbytes peft safetensors sentencepiece transformers
|
| 178 |
+
---> Running in 658e2eee1bdf
|
| 179 |
+
Collecting accelerate
|
| 180 |
+
Downloading accelerate-1.13.0-py3-none-any.whl.metadata (19 kB)
|
| 181 |
+
Collecting datasets
|
| 182 |
+
Downloading datasets-4.8.4-py3-none-any.whl.metadata (19 kB)
|
| 183 |
+
Collecting bitsandbytes
|
| 184 |
+
Downloading bitsandbytes-0.49.2-py3-none-manylinux_2_24_x86_64.whl.metadata (10 kB)
|
| 185 |
+
Collecting peft
|
| 186 |
+
Downloading peft-0.18.1-py3-none-any.whl.metadata (14 kB)
|
| 187 |
+
Collecting safetensors
|
| 188 |
+
Downloading safetensors-0.7.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.1 kB)
|
| 189 |
+
Collecting sentencepiece
|
| 190 |
+
Downloading sentencepiece-0.2.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (10 kB)
|
| 191 |
+
Collecting transformers
|
| 192 |
+
Downloading transformers-5.5.0-py3-none-any.whl.metadata (32 kB)
|
| 193 |
+
Requirement already satisfied: numpy>=1.17 in /opt/conda/lib/python3.11/site-packages (from accelerate) (2.2.2)
|
| 194 |
+
Requirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.11/site-packages (from accelerate) (24.2)
|
| 195 |
+
Requirement already satisfied: psutil in /opt/conda/lib/python3.11/site-packages (from accelerate) (6.1.1)
|
| 196 |
+
Requirement already satisfied: pyyaml in /opt/conda/lib/python3.11/site-packages (from accelerate) (6.0.2)
|
| 197 |
+
Requirement already satisfied: torch>=2.0.0 in /opt/conda/lib/python3.11/site-packages (from accelerate) (2.6.0+cu124)
|
| 198 |
+
Collecting huggingface_hub>=0.21.0 (from accelerate)
|
| 199 |
+
Downloading huggingface_hub-1.9.0-py3-none-any.whl.metadata (14 kB)
|
| 200 |
+
Requirement already satisfied: filelock in /opt/conda/lib/python3.11/site-packages (from datasets) (3.17.0)
|
| 201 |
+
Collecting pyarrow>=21.0.0 (from datasets)
|
| 202 |
+
Downloading pyarrow-23.0.1-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (3.1 kB)
|
| 203 |
+
Collecting dill<0.4.2,>=0.3.0 (from datasets)
|
| 204 |
+
Downloading dill-0.4.1-py3-none-any.whl.metadata (10 kB)
|
| 205 |
+
Collecting pandas (from datasets)
|
| 206 |
+
Downloading pandas-3.0.2-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl.metadata (79 kB)
|
| 207 |
+
Requirement already satisfied: requests>=2.32.2 in /opt/conda/lib/python3.11/site-packages (from datasets) (2.32.3)
|
| 208 |
+
Collecting httpx<1.0.0 (from datasets)
|
| 209 |
+
Downloading httpx-0.28.1-py3-none-any.whl.metadata (7.1 kB)
|
| 210 |
+
Requirement already satisfied: tqdm>=4.66.3 in /opt/conda/lib/python3.11/site-packages (from datasets) (4.67.1)
|
| 211 |
+
Collecting xxhash (from datasets)
|
| 212 |
+
Downloading xxhash-3.6.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (13 kB)
|
| 213 |
+
Collecting multiprocess<0.70.20 (from datasets)
|
| 214 |
+
Downloading multiprocess-0.70.19-py311-none-any.whl.metadata (7.5 kB)
|
| 215 |
+
Requirement already satisfied: fsspec<=2026.2.0,>=2023.1.0 in /opt/conda/lib/python3.11/site-packages (from fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (2024.12.0)
|
| 216 |
+
Collecting regex>=2025.10.22 (from transformers)
|
| 217 |
+
Downloading regex-2026.4.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (40 kB)
|
| 218 |
+
Collecting tokenizers<=0.23.0,>=0.22.0 (from transformers)
|
| 219 |
+
Downloading tokenizers-0.22.2-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.3 kB)
|
| 220 |
+
Collecting typer (from transformers)
|
| 221 |
+
Downloading typer-0.24.1-py3-none-any.whl.metadata (16 kB)
|
| 222 |
+
Collecting aiohttp!=4.0.0a0,!=4.0.0a1 (from fsspec[http]<=2026.2.0,>=2023.1.0->datasets)
|
| 223 |
+
Downloading aiohttp-3.13.5-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (8.1 kB)
|
| 224 |
+
Collecting anyio (from httpx<1.0.0->datasets)
|
| 225 |
+
Downloading anyio-4.13.0-py3-none-any.whl.metadata (4.5 kB)
|
| 226 |
+
Requirement already satisfied: certifi in /opt/conda/lib/python3.11/site-packages (from httpx<1.0.0->datasets) (2024.12.14)
|
| 227 |
+
Collecting httpcore==1.* (from httpx<1.0.0->datasets)
|
| 228 |
+
Downloading httpcore-1.0.9-py3-none-any.whl.metadata (21 kB)
|
| 229 |
+
Requirement already satisfied: idna in /opt/conda/lib/python3.11/site-packages (from httpx<1.0.0->datasets) (3.10)
|
| 230 |
+
Collecting h11>=0.16 (from httpcore==1.*->httpx<1.0.0->datasets)
|
| 231 |
+
Downloading h11-0.16.0-py3-none-any.whl.metadata (8.3 kB)
|
| 232 |
+
Collecting hf-xet<2.0.0,>=1.4.3 (from huggingface_hub>=0.21.0->accelerate)
|
| 233 |
+
Downloading hf_xet-1.4.3-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (4.9 kB)
|
| 234 |
+
Requirement already satisfied: typing-extensions>=4.1.0 in /opt/conda/lib/python3.11/site-packages (from huggingface_hub>=0.21.0->accelerate) (4.12.2)
|
| 235 |
+
Requirement already satisfied: charset_normalizer<4,>=2 in /opt/conda/lib/python3.11/site-packages (from requests>=2.32.2->datasets) (3.4.1)
|
| 236 |
+
Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.11/site-packages (from requests>=2.32.2->datasets) (2.3.0)
|
| 237 |
+
Requirement already satisfied: networkx in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (3.4.2)
|
| 238 |
+
Requirement already satisfied: jinja2 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (3.1.5)
|
| 239 |
+
Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (12.4.127)
|
| 240 |
+
Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (12.4.127)
|
| 241 |
+
Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (12.4.127)
|
| 242 |
+
Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (9.1.0.70)
|
| 243 |
+
Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (12.4.5.8)
|
| 244 |
+
Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (11.2.1.3)
|
| 245 |
+
Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (10.3.5.147)
|
| 246 |
+
Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (11.6.1.9)
|
| 247 |
+
Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (12.3.1.170)
|
| 248 |
+
Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (0.6.2)
|
| 249 |
+
Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (2.21.5)
|
| 250 |
+
Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (12.4.127)
|
| 251 |
+
Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (12.4.127)
|
| 252 |
+
Requirement already satisfied: triton==3.2.0 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (3.2.0)
|
| 253 |
+
Requirement already satisfied: sympy==1.13.1 in /opt/conda/lib/python3.11/site-packages (from torch>=2.0.0->accelerate) (1.13.1)
|
| 254 |
+
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /opt/conda/lib/python3.11/site-packages (from sympy==1.13.1->torch>=2.0.0->accelerate) (1.3.0)
|
| 255 |
+
Collecting python-dateutil>=2.8.2 (from pandas->datasets)
|
| 256 |
+
Downloading python_dateutil-2.9.0.post0-py2.py3-none-any.whl.metadata (8.4 kB)
|
| 257 |
+
Collecting click>=8.2.1 (from typer->transformers)
|
| 258 |
+
Downloading click-8.3.2-py3-none-any.whl.metadata (2.6 kB)
|
| 259 |
+
Collecting shellingham>=1.3.0 (from typer->transformers)
|
| 260 |
+
Downloading shellingham-1.5.4-py2.py3-none-any.whl.metadata (3.5 kB)
|
| 261 |
+
Collecting rich>=12.3.0 (from typer->transformers)
|
| 262 |
+
Downloading rich-14.3.3-py3-none-any.whl.metadata (18 kB)
|
| 263 |
+
Collecting annotated-doc>=0.0.2 (from typer->transformers)
|
| 264 |
+
Downloading annotated_doc-0.0.4-py3-none-any.whl.metadata (6.6 kB)
|
| 265 |
+
Collecting aiohappyeyeballs>=2.5.0 (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets)
|
| 266 |
+
Downloading aiohappyeyeballs-2.6.1-py3-none-any.whl.metadata (5.9 kB)
|
| 267 |
+
Collecting aiosignal>=1.4.0 (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets)
|
| 268 |
+
Downloading aiosignal-1.4.0-py3-none-any.whl.metadata (3.7 kB)
|
| 269 |
+
Requirement already satisfied: attrs>=17.3.0 in /opt/conda/lib/python3.11/site-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (25.1.0)
|
| 270 |
+
Collecting frozenlist>=1.1.1 (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets)
|
| 271 |
+
Downloading frozenlist-1.8.0-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl.metadata (20 kB)
|
| 272 |
+
Collecting multidict<7.0,>=4.5 (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets)
|
| 273 |
+
Downloading multidict-6.7.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (5.3 kB)
|
| 274 |
+
Collecting propcache>=0.2.0 (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets)
|
| 275 |
+
Downloading propcache-0.4.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (13 kB)
|
| 276 |
+
Collecting yarl<2.0,>=1.17.0 (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets)
|
| 277 |
+
Downloading yarl-1.23.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (79 kB)
|
| 278 |
+
Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.11/site-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.17.0)
|
| 279 |
+
Collecting markdown-it-py>=2.2.0 (from rich>=12.3.0->typer->transformers)
|
| 280 |
+
Downloading markdown_it_py-4.0.0-py3-none-any.whl.metadata (7.3 kB)
|
| 281 |
+
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /opt/conda/lib/python3.11/site-packages (from rich>=12.3.0->typer->transformers) (2.19.1)
|
| 282 |
+
Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.11/site-packages (from jinja2->torch>=2.0.0->accelerate) (3.0.2)
|
| 283 |
+
Collecting mdurl~=0.1 (from markdown-it-py>=2.2.0->rich>=12.3.0->typer->transformers)
|
| 284 |
+
Downloading mdurl-0.1.2-py3-none-any.whl.metadata (1.6 kB)
|
| 285 |
+
Downloading accelerate-1.13.0-py3-none-any.whl (383 kB)
|
| 286 |
+
Downloading datasets-4.8.4-py3-none-any.whl (526 kB)
|
| 287 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 527.0/527.0 kB 146.9 MB/s eta 0:00:00
|
| 288 |
+
Downloading bitsandbytes-0.49.2-py3-none-manylinux_2_24_x86_64.whl (60.7 MB)
|
| 289 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 60.7/60.7 MB 18.6 MB/s eta 0:00:00
|
| 290 |
+
Downloading peft-0.18.1-py3-none-any.whl (556 kB)
|
| 291 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 557.0/557.0 kB 34.5 MB/s eta 0:00:00
|
| 292 |
+
Downloading safetensors-0.7.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (507 kB)
|
| 293 |
+
Downloading sentencepiece-0.2.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (1.4 MB)
|
| 294 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.4/1.4 MB 22.9 MB/s eta 0:00:00
|
| 295 |
+
Downloading transformers-5.5.0-py3-none-any.whl (10.2 MB)
|
| 296 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 10.2/10.2 MB 19.1 MB/s eta 0:00:00
|
| 297 |
+
Downloading dill-0.4.1-py3-none-any.whl (120 kB)
|
| 298 |
+
Downloading httpx-0.28.1-py3-none-any.whl (73 kB)
|
| 299 |
+
Downloading httpcore-1.0.9-py3-none-any.whl (78 kB)
|
| 300 |
+
Downloading huggingface_hub-1.9.0-py3-none-any.whl (637 kB)
|
| 301 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 637.4/637.4 kB 41.2 MB/s eta 0:00:00
|
| 302 |
+
Downloading multiprocess-0.70.19-py311-none-any.whl (144 kB)
|
| 303 |
+
Downloading pyarrow-23.0.1-cp311-cp311-manylinux_2_28_x86_64.whl (47.6 MB)
|
| 304 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 47.6/47.6 MB 18.9 MB/s eta 0:00:00
|
| 305 |
+
Downloading regex-2026.4.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (799 kB)
|
| 306 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 799.8/799.8 kB 41.5 MB/s eta 0:00:00
|
| 307 |
+
Downloading tokenizers-0.22.2-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.3 MB)
|
| 308 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.3/3.3 MB 21.2 MB/s eta 0:00:00
|
| 309 |
+
Downloading pandas-3.0.2-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (11.3 MB)
|
| 310 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.3/11.3 MB 18.0 MB/s eta 0:00:00
|
| 311 |
+
Downloading typer-0.24.1-py3-none-any.whl (56 kB)
|
| 312 |
+
Downloading xxhash-3.6.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (193 kB)
|
| 313 |
+
Downloading aiohttp-3.13.5-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (1.8 MB)
|
| 314 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.8/1.8 MB 27.4 MB/s eta 0:00:00
|
| 315 |
+
Downloading annotated_doc-0.0.4-py3-none-any.whl (5.3 kB)
|
| 316 |
+
Downloading click-8.3.2-py3-none-any.whl (108 kB)
|
| 317 |
+
Downloading hf_xet-1.4.3-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (4.2 MB)
|
| 318 |
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.2/4.2 MB 21.6 MB/s eta 0:00:00
|
| 319 |
+
Downloading python_dateutil-2.9.0.post0-py2.py3-none-any.whl (229 kB)
|
| 320 |
+
Downloading rich-14.3.3-py3-none-any.whl (310 kB)
|
| 321 |
+
Downloading shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)
|
| 322 |
+
Downloading anyio-4.13.0-py3-none-any.whl (114 kB)
|
| 323 |
+
Downloading aiohappyeyeballs-2.6.1-py3-none-any.whl (15 kB)
|
| 324 |
+
Downloading aiosignal-1.4.0-py3-none-any.whl (7.5 kB)
|
| 325 |
+
Downloading frozenlist-1.8.0-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl (231 kB)
|
| 326 |
+
Downloading h11-0.16.0-py3-none-any.whl (37 kB)
|
| 327 |
+
Downloading markdown_it_py-4.0.0-py3-none-any.whl (87 kB)
|
| 328 |
+
Downloading multidict-6.7.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (246 kB)
|
| 329 |
+
Downloading propcache-0.4.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (210 kB)
|
| 330 |
+
Downloading yarl-1.23.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (102 kB)
|
| 331 |
+
Downloading mdurl-0.1.2-py3-none-any.whl (10.0 kB)
|
| 332 |
+
Installing collected packages: xxhash, shellingham, sentencepiece, safetensors, regex, python-dateutil, pyarrow, propcache, multidict, mdurl, hf-xet, h11, frozenlist, dill, click, anyio, annotated-doc, aiohappyeyeballs, yarl, pandas, multiprocess, markdown-it-py, httpcore, aiosignal, rich, httpx, aiohttp, typer, bitsandbytes, huggingface_hub, tokenizers, datasets, accelerate, transformers, peft
|
| 333 |
+
Attempting uninstall: click
|
| 334 |
+
Found existing installation: click 8.1.8
|
| 335 |
+
Uninstalling click-8.1.8:
|
| 336 |
+
Successfully uninstalled click-8.1.8
|
| 337 |
+
Successfully installed accelerate-1.13.0 aiohappyeyeballs-2.6.1 aiohttp-3.13.5 aiosignal-1.4.0 annotated-doc-0.0.4 anyio-4.13.0 bitsandbytes-0.49.2 click-8.3.2 datasets-4.8.4 dill-0.4.1 frozenlist-1.8.0 h11-0.16.0 hf-xet-1.4.3 httpcore-1.0.9 httpx-0.28.1 huggingface_hub-1.9.0 markdown-it-py-4.0.0 mdurl-0.1.2 multidict-6.7.1 multiprocess-0.70.19 pandas-3.0.2 peft-0.18.1 propcache-0.4.1 pyarrow-23.0.1 python-dateutil-2.9.0.post0 regex-2026.4.4 rich-14.3.3 safetensors-0.7.0 sentencepiece-0.2.1 shellingham-1.5.4 tokenizers-0.22.2 transformers-5.5.0 typer-0.24.1 xxhash-3.6.0 yarl-1.23.0
|
| 338 |
+
[91mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable.It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.
|
| 339 |
+
[0m ---> Removed intermediate container 658e2eee1bdf
|
| 340 |
+
---> 2c3ed59677a4
|
| 341 |
+
Step 8/9 : WORKDIR /workspace
|
| 342 |
+
---> Running in 99dc483a6553
|
| 343 |
+
---> Removed intermediate container 99dc483a6553
|
| 344 |
+
---> a4a590a17bb9
|
| 345 |
+
Step 9/9 : CMD ["/bin/bash"]
|
| 346 |
+
---> Running in 5bd3a8944bd9
|
| 347 |
+
---> Removed intermediate container 5bd3a8944bd9
|
| 348 |
+
---> f1fa43dd205d
|
| 349 |
+
Successfully built f1fa43dd205d
|
| 350 |
+
Successfully tagged automop-distill-student:latest
|
| 351 |
+
|
| 352 |
+
==========
|
| 353 |
+
== CUDA ==
|
| 354 |
+
==========
|
| 355 |
+
|
| 356 |
+
CUDA Version 12.4.1
|
| 357 |
+
|
| 358 |
+
Container image Copyright (c) 2016-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
| 359 |
+
|
| 360 |
+
This container image and its contents are governed by the NVIDIA Deep Learning Container License.
|
| 361 |
+
By pulling and using the container, you accept the terms and conditions of this license:
|
| 362 |
+
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license
|
| 363 |
+
|
| 364 |
+
A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience.
|
| 365 |
+
|
| 366 |
+
|
| 367 |
+
The fast path is not available because one of the required library is not installed. Falling back to torch implementation. To install follow https://github.com/fla-org/flash-linear-attention#installation and https://github.com/Dao-AILab/causal-conv1d
|
| 368 |
+
Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
| 369 |
+
|
| 370 |
+
The tokenizer you are loading from '/workspace/.cache/huggingface/hub/models--Jackrong--Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled/snapshots/9094770e48788ba501437d8e9ecd84a17bf91ce1' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
|
| 371 |
+
Unrecognized keys in `rope_parameters` for 'rope_type'='default': {'mrope_interleaved', 'mrope_section'}
|
| 372 |
+
{
|
| 373 |
+
"source_model": "/workspace/.cache/huggingface/hub/models--Jackrong--Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled/snapshots/9094770e48788ba501437d8e9ecd84a17bf91ce1",
|
| 374 |
+
"output_dir": "/workspace/distill_student_init10",
|
| 375 |
+
"source_layers": 64,
|
| 376 |
+
"target_layers": 32,
|
| 377 |
+
"selected_layers": [
|
| 378 |
+
0,
|
| 379 |
+
2,
|
| 380 |
+
4,
|
| 381 |
+
6,
|
| 382 |
+
8,
|
| 383 |
+
10,
|
| 384 |
+
12,
|
| 385 |
+
14,
|
| 386 |
+
16,
|
| 387 |
+
18,
|
| 388 |
+
20,
|
| 389 |
+
22,
|
| 390 |
+
24,
|
| 391 |
+
26,
|
| 392 |
+
28,
|
| 393 |
+
30,
|
| 394 |
+
33,
|
| 395 |
+
35,
|
| 396 |
+
37,
|
| 397 |
+
39,
|
| 398 |
+
41,
|
| 399 |
+
43,
|
| 400 |
+
45,
|
| 401 |
+
47,
|
| 402 |
+
49,
|
| 403 |
+
51,
|
| 404 |
+
53,
|
| 405 |
+
55,
|
| 406 |
+
57,
|
| 407 |
+
59,
|
| 408 |
+
61,
|
| 409 |
+
63
|
| 410 |
+
],
|
| 411 |
+
"max_shard_size_gb": 5.0
|
| 412 |
+
}
|
student_layer_map.json
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"source_layers": 64,
|
| 3 |
+
"target_layers": 32,
|
| 4 |
+
"selected_layers": [
|
| 5 |
+
0,
|
| 6 |
+
2,
|
| 7 |
+
4,
|
| 8 |
+
6,
|
| 9 |
+
8,
|
| 10 |
+
10,
|
| 11 |
+
12,
|
| 12 |
+
14,
|
| 13 |
+
16,
|
| 14 |
+
18,
|
| 15 |
+
20,
|
| 16 |
+
22,
|
| 17 |
+
24,
|
| 18 |
+
26,
|
| 19 |
+
28,
|
| 20 |
+
30,
|
| 21 |
+
33,
|
| 22 |
+
35,
|
| 23 |
+
37,
|
| 24 |
+
39,
|
| 25 |
+
41,
|
| 26 |
+
43,
|
| 27 |
+
45,
|
| 28 |
+
47,
|
| 29 |
+
49,
|
| 30 |
+
51,
|
| 31 |
+
53,
|
| 32 |
+
55,
|
| 33 |
+
57,
|
| 34 |
+
59,
|
| 35 |
+
61,
|
| 36 |
+
63
|
| 37 |
+
],
|
| 38 |
+
"layer_map": {
|
| 39 |
+
"0": 0,
|
| 40 |
+
"2": 1,
|
| 41 |
+
"4": 2,
|
| 42 |
+
"6": 3,
|
| 43 |
+
"8": 4,
|
| 44 |
+
"10": 5,
|
| 45 |
+
"12": 6,
|
| 46 |
+
"14": 7,
|
| 47 |
+
"16": 8,
|
| 48 |
+
"18": 9,
|
| 49 |
+
"20": 10,
|
| 50 |
+
"22": 11,
|
| 51 |
+
"24": 12,
|
| 52 |
+
"26": 13,
|
| 53 |
+
"28": 14,
|
| 54 |
+
"30": 15,
|
| 55 |
+
"33": 16,
|
| 56 |
+
"35": 17,
|
| 57 |
+
"37": 18,
|
| 58 |
+
"39": 19,
|
| 59 |
+
"41": 20,
|
| 60 |
+
"43": 21,
|
| 61 |
+
"45": 22,
|
| 62 |
+
"47": 23,
|
| 63 |
+
"49": 24,
|
| 64 |
+
"51": 25,
|
| 65 |
+
"53": 26,
|
| 66 |
+
"55": 27,
|
| 67 |
+
"57": 28,
|
| 68 |
+
"59": 29,
|
| 69 |
+
"61": 30,
|
| 70 |
+
"63": 31
|
| 71 |
+
},
|
| 72 |
+
"target_to_source_map": {
|
| 73 |
+
"0": 0,
|
| 74 |
+
"1": 2,
|
| 75 |
+
"2": 4,
|
| 76 |
+
"3": 6,
|
| 77 |
+
"4": 8,
|
| 78 |
+
"5": 10,
|
| 79 |
+
"6": 12,
|
| 80 |
+
"7": 14,
|
| 81 |
+
"8": 16,
|
| 82 |
+
"9": 18,
|
| 83 |
+
"10": 20,
|
| 84 |
+
"11": 22,
|
| 85 |
+
"12": 24,
|
| 86 |
+
"13": 26,
|
| 87 |
+
"14": 28,
|
| 88 |
+
"15": 30,
|
| 89 |
+
"16": 33,
|
| 90 |
+
"17": 35,
|
| 91 |
+
"18": 37,
|
| 92 |
+
"19": 39,
|
| 93 |
+
"20": 41,
|
| 94 |
+
"21": 43,
|
| 95 |
+
"22": 45,
|
| 96 |
+
"23": 47,
|
| 97 |
+
"24": 49,
|
| 98 |
+
"25": 51,
|
| 99 |
+
"26": 53,
|
| 100 |
+
"27": 55,
|
| 101 |
+
"28": 57,
|
| 102 |
+
"29": 59,
|
| 103 |
+
"30": 61,
|
| 104 |
+
"31": 63
|
| 105 |
+
}
|
| 106 |
+
}
|
student_slice_manifest.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"source_model": "/workspace/.cache/huggingface/hub/models--Jackrong--Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled/snapshots/9094770e48788ba501437d8e9ecd84a17bf91ce1",
|
| 3 |
+
"output_dir": "/workspace/distill_student_init10",
|
| 4 |
+
"num_layers": 32,
|
| 5 |
+
"strategy": "uniform",
|
| 6 |
+
"trust_remote_code": false,
|
| 7 |
+
"max_shard_size_gb": 5.0
|
| 8 |
+
}
|
student_slice_summary.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"source_model": "/workspace/.cache/huggingface/hub/models--Jackrong--Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled/snapshots/9094770e48788ba501437d8e9ecd84a17bf91ce1",
|
| 3 |
+
"output_dir": "/workspace/distill_student_init10",
|
| 4 |
+
"source_layers": 64,
|
| 5 |
+
"target_layers": 32,
|
| 6 |
+
"selected_layers": [
|
| 7 |
+
0,
|
| 8 |
+
2,
|
| 9 |
+
4,
|
| 10 |
+
6,
|
| 11 |
+
8,
|
| 12 |
+
10,
|
| 13 |
+
12,
|
| 14 |
+
14,
|
| 15 |
+
16,
|
| 16 |
+
18,
|
| 17 |
+
20,
|
| 18 |
+
22,
|
| 19 |
+
24,
|
| 20 |
+
26,
|
| 21 |
+
28,
|
| 22 |
+
30,
|
| 23 |
+
33,
|
| 24 |
+
35,
|
| 25 |
+
37,
|
| 26 |
+
39,
|
| 27 |
+
41,
|
| 28 |
+
43,
|
| 29 |
+
45,
|
| 30 |
+
47,
|
| 31 |
+
49,
|
| 32 |
+
51,
|
| 33 |
+
53,
|
| 34 |
+
55,
|
| 35 |
+
57,
|
| 36 |
+
59,
|
| 37 |
+
61,
|
| 38 |
+
63
|
| 39 |
+
],
|
| 40 |
+
"max_shard_size_gb": 5.0
|
| 41 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "TokenizersBackend",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|