Replace Design.md-only checkpoint with tool-using DesignCoder 4B AdamW step200
Browse files- README.md +41 -74
- adapter/adapter_config.json +0 -51
- adapter/adapter_model.safetensors +0 -3
- adapter/chat_template.jinja +0 -154
- adapter/processor_config.json +0 -60
- adapter/tokenizer_config.json +0 -34
- config.json +6 -2
- generation_config.json +4 -2
- merge_validation.json +0 -32
- model-00001-of-00002.safetensors +0 -3
- model-00002-of-00002.safetensors +0 -3
- adapter/tokenizer.json → model.safetensors +2 -2
- model.safetensors.index.json +0 -731
- training_summary.json +39 -24
- upload_manifest.json +13 -79
README.md
CHANGED
|
@@ -1,92 +1,59 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
library_name: transformers
|
| 4 |
base_model: Qwen/Qwen3.5-4B
|
|
|
|
| 5 |
pipeline_tag: image-text-to-text
|
| 6 |
-
tags:
|
| 7 |
-
- designcoder
|
| 8 |
-
- qwen3_5
|
| 9 |
-
- sft
|
| 10 |
-
- lora
|
| 11 |
-
- merged
|
| 12 |
-
- web-design
|
| 13 |
---
|
| 14 |
|
| 15 |
-
# DesignCoder 4B — AdamW
|
| 16 |
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
|
| 26 |
-
##
|
| 27 |
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
| Dataset identifier | `design_sft_sharegpt_with_think` |
|
| 35 |
-
| LoRA | rank 64, alpha 128, dropout 0.05 |
|
| 36 |
-
| Learning rate | `1e-4`, cosine schedule, warmup ratio 0.03 |
|
| 37 |
-
| Training batch | 1 per device, 8 accumulation steps, effective batch 8 |
|
| 38 |
-
| Training cutoff | 16384 tokens |
|
| 39 |
-
| Export | FP32 LoRA merge with `safe_merge=True`, then BF16 safetensors |
|
| 40 |
|
| 41 |
-
The
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
|
|
|
|
|
|
| 45 |
|
| 46 |
-
|
| 47 |
-
Their SHA256 is
|
| 48 |
-
`7d8305739df470c3d7906241a14ae37b342e1ba61f34b3d0341e69b97f85f12b`.
|
| 49 |
-
The adapter config uses the public base-model ID and pinned revision instead of
|
| 50 |
-
the original local filesystem path. Do not apply this adapter to the already
|
| 51 |
-
merged model at the repository root.
|
| 52 |
|
| 53 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
|
| 55 |
-
|
| 56 |
|
| 57 |
-
|
| 58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
model = Qwen3_5ForConditionalGeneration.from_pretrained(
|
| 63 |
-
model_id, dtype="auto", device_map="auto"
|
| 64 |
-
)
|
| 65 |
-
messages = [{"role": "user", "content": "Build a minimal portfolio homepage."}]
|
| 66 |
-
text = tokenizer.apply_chat_template(
|
| 67 |
-
messages, tokenize=False, add_generation_prompt=True, enable_thinking=True
|
| 68 |
-
)
|
| 69 |
-
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
| 70 |
-
output = model.generate(**inputs, max_new_tokens=1024)
|
| 71 |
-
print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))
|
| 72 |
```
|
| 73 |
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
- All source adapter tensors were compared against their loaded values.
|
| 79 |
-
- FP32 inference before and after the LoRA merge was compared on a short text prompt.
|
| 80 |
-
- The BF16 export was reloaded and its logits were checked for exact equality
|
| 81 |
-
with the in-memory BF16 model on that prompt.
|
| 82 |
-
- Tokenizer, processor and model configuration loading were checked.
|
| 83 |
-
- [`merge_validation.json`](merge_validation.json) contains the numerical results;
|
| 84 |
-
[`training_summary.json`](training_summary.json) records training metadata;
|
| 85 |
-
[`upload_manifest.json`](upload_manifest.json) records source and artifact hashes.
|
| 86 |
-
|
| 87 |
-
These checks validate export integrity. No new benchmark, GPU inference or
|
| 88 |
-
vLLM end-to-end RL evaluation was performed for this upload.
|
| 89 |
-
|
| 90 |
-
## License
|
| 91 |
-
|
| 92 |
-
Apache-2.0, following the Qwen3.5-4B base model. See [LICENSE](LICENSE).
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
base_model: Qwen/Qwen3.5-4B
|
| 4 |
+
library_name: transformers
|
| 5 |
pipeline_tag: image-text-to-text
|
| 6 |
+
tags: [designcoder, tool-use, web-design, sft]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
+
# DesignCoder 4B — AdamW step200
|
| 10 |
|
| 11 |
+
Full BF16 tool-using DesignCoder checkpoint, selected from
|
| 12 |
+
`xingxm/DesignCoder/designcoder_qwen3.5_4b_adamw_bs256_data41287_step200`.
|
| 13 |
+
This is an SFT initialization for DesignCoder RL. Its original weights, tokenizer,
|
| 14 |
+
processor and chat template are preserved byte-for-byte, without quantization or LoRA merging.
|
| 15 |
|
| 16 |
+
The source run uses Qwen3.5-4B, AdamW (learning rate 2e-5), global batch 256 and
|
| 17 |
+
41,287 DesignCoder v2 trajectories. The export is step200, epoch 1.5066.
|
| 18 |
+
The source model card records training on 8 nodes x 8 H20.
|
| 19 |
|
| 20 |
+
## Tool protocol and inference
|
| 21 |
|
| 22 |
+
Use the system prompt and tools in
|
| 23 |
+
[DesignCoder runtime](https://github.com/ZitengXue/DesignCoder/tree/main/examples/designcoder/runtime).
|
| 24 |
+
Landing: `design_search -> websearch -> HTML/CSS/JS`.
|
| 25 |
+
Dashboard: `design_search -> HTML/CSS/JS`.
|
| 26 |
+
Calls are written as `<tools>tool_name(...)</tools>`, followed by tool observations.
|
| 27 |
+
The final answer contains `<code lang="html">`, `<code lang="css">` and `<code lang="js">` blocks.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
+
The original inference defaults are sampling with temperature 0.6, top_p 0.95,
|
| 30 |
+
top_k 20, repetition_penalty 1.0 and thinking enabled. Tool turns allow 1,536
|
| 31 |
+
new tokens; the final turn requests 32,768 tokens, capped by remaining room
|
| 32 |
+
in the 32,768-token context. Websearch requests four candidates per query.
|
| 33 |
+
Use `examples/designcoder/runtime/infer_designcoder.py` or the aligned RL agent;
|
| 34 |
+
a plain single-turn prompt does not reproduce the tool protocol.
|
| 35 |
|
| 36 |
+
## Evaluation provenance
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
+
The retained 200-case evaluation scores 83.2948 under the explicitly named
|
| 39 |
+
`fixed-assets-layout-v1` aggregation. The corresponding 4B Muon step200 scores
|
| 40 |
+
76.2119 under the same aggregation. The original judge identity is not recorded.
|
| 41 |
+
Older model-card numbers use other aggregation definitions and should not be mixed.
|
| 42 |
+
No new benchmark or GPU evaluation is claimed by this upload.
|
| 43 |
|
| 44 |
+
## Replacement and verification
|
| 45 |
|
| 46 |
+
This replaces the mistakenly selected Design.md-only AdamW step12588 checkpoint.
|
| 47 |
+
That previous model remains in Git history and the archive tag
|
| 48 |
+
`archive-designmd-4b-step12588-20261109`. The new root has one full
|
| 49 |
+
`model.safetensors`; it has no adapter or old weight shards.
|
| 50 |
+
`upload_manifest.json` records SHA256 values of every copied inference file.
|
| 51 |
+
`training_summary.json` records the checkpoint identity and source evidence.
|
| 52 |
|
| 53 |
+
```bash
|
| 54 |
+
hf download chjdl1816/designcoder-mc --local-dir models/designcoder-4b-adamw-step200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
```
|
| 56 |
|
| 57 |
+
Use a clean local directory when switching from an earlier export.
|
| 58 |
+
The model architecture is `Qwen3_5ForConditionalGeneration`.
|
| 59 |
+
DesignEvaluator is a separate frozen 9B model and is not included here.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter/adapter_config.json
DELETED
|
@@ -1,51 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alora_invocation_tokens": null,
|
| 3 |
-
"alpha_pattern": {},
|
| 4 |
-
"arrow_config": null,
|
| 5 |
-
"auto_mapping": null,
|
| 6 |
-
"base_model_name_or_path": "Qwen/Qwen3.5-4B",
|
| 7 |
-
"bias": "none",
|
| 8 |
-
"corda_config": null,
|
| 9 |
-
"ensure_weight_tying": false,
|
| 10 |
-
"eva_config": null,
|
| 11 |
-
"exclude_modules": null,
|
| 12 |
-
"fan_in_fan_out": false,
|
| 13 |
-
"inference_mode": true,
|
| 14 |
-
"init_lora_weights": true,
|
| 15 |
-
"layer_replication": null,
|
| 16 |
-
"layers_pattern": null,
|
| 17 |
-
"layers_to_transform": null,
|
| 18 |
-
"loftq_config": {},
|
| 19 |
-
"lora_alpha": 128,
|
| 20 |
-
"lora_bias": false,
|
| 21 |
-
"lora_dropout": 0.05,
|
| 22 |
-
"megatron_config": null,
|
| 23 |
-
"megatron_core": "megatron.core",
|
| 24 |
-
"modules_to_save": null,
|
| 25 |
-
"peft_type": "LORA",
|
| 26 |
-
"peft_version": "0.18.1",
|
| 27 |
-
"qalora_group_size": 16,
|
| 28 |
-
"r": 64,
|
| 29 |
-
"rank_pattern": {},
|
| 30 |
-
"revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
|
| 31 |
-
"target_modules": [
|
| 32 |
-
"down_proj",
|
| 33 |
-
"up_proj",
|
| 34 |
-
"o_proj",
|
| 35 |
-
"in_proj_z",
|
| 36 |
-
"in_proj_a",
|
| 37 |
-
"v_proj",
|
| 38 |
-
"gate_proj",
|
| 39 |
-
"k_proj",
|
| 40 |
-
"in_proj_qkv",
|
| 41 |
-
"q_proj",
|
| 42 |
-
"out_proj",
|
| 43 |
-
"in_proj_b"
|
| 44 |
-
],
|
| 45 |
-
"target_parameters": null,
|
| 46 |
-
"task_type": "CAUSAL_LM",
|
| 47 |
-
"trainable_token_indices": null,
|
| 48 |
-
"use_dora": false,
|
| 49 |
-
"use_qalora": false,
|
| 50 |
-
"use_rslora": false
|
| 51 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter/adapter_model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7d8305739df470c3d7906241a14ae37b342e1ba61f34b3d0341e69b97f85f12b
|
| 3 |
-
size 519513832
|
|
|
|
|
|
|
|
|
|
|
|
adapter/chat_template.jinja
DELETED
|
@@ -1,154 +0,0 @@
|
|
| 1 |
-
{%- set image_count = namespace(value=0) %}
|
| 2 |
-
{%- set video_count = namespace(value=0) %}
|
| 3 |
-
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
-
{%- if content is string %}
|
| 5 |
-
{{- content }}
|
| 6 |
-
{%- elif content is iterable and content is not mapping %}
|
| 7 |
-
{%- for item in content %}
|
| 8 |
-
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
-
{%- if is_system_content %}
|
| 10 |
-
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
-
{%- endif %}
|
| 12 |
-
{%- if do_vision_count %}
|
| 13 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
-
{%- endif %}
|
| 15 |
-
{%- if add_vision_id %}
|
| 16 |
-
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
-
{%- endif %}
|
| 18 |
-
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
-
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
-
{%- if is_system_content %}
|
| 21 |
-
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if do_vision_count %}
|
| 24 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
-
{%- endif %}
|
| 26 |
-
{%- if add_vision_id %}
|
| 27 |
-
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
-
{%- endif %}
|
| 29 |
-
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
-
{%- elif 'text' in item %}
|
| 31 |
-
{{- item.text }}
|
| 32 |
-
{%- else %}
|
| 33 |
-
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{%- endfor %}
|
| 36 |
-
{%- elif content is none or content is undefined %}
|
| 37 |
-
{{- '' }}
|
| 38 |
-
{%- else %}
|
| 39 |
-
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
-
{%- endif %}
|
| 41 |
-
{%- endmacro %}
|
| 42 |
-
{%- if not messages %}
|
| 43 |
-
{{- raise_exception('No messages provided.') }}
|
| 44 |
-
{%- endif %}
|
| 45 |
-
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
-
{{- '<|im_start|>system\n' }}
|
| 47 |
-
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
-
{%- for tool in tools %}
|
| 49 |
-
{{- "\n" }}
|
| 50 |
-
{{- tool | tojson }}
|
| 51 |
-
{%- endfor %}
|
| 52 |
-
{{- "\n</tools>" }}
|
| 53 |
-
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
-
{%- if messages[0].role == 'system' %}
|
| 55 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
-
{%- if content %}
|
| 57 |
-
{{- '\n\n' + content }}
|
| 58 |
-
{%- endif %}
|
| 59 |
-
{%- endif %}
|
| 60 |
-
{{- '<|im_end|>\n' }}
|
| 61 |
-
{%- else %}
|
| 62 |
-
{%- if messages[0].role == 'system' %}
|
| 63 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
-
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
-
{%- endif %}
|
| 66 |
-
{%- endif %}
|
| 67 |
-
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
-
{%- for message in messages[::-1] %}
|
| 69 |
-
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
-
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
-
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
-
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
-
{%- set ns.multi_step_tool = false %}
|
| 74 |
-
{%- set ns.last_query_index = index %}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{%- endif %}
|
| 77 |
-
{%- endfor %}
|
| 78 |
-
{%- if ns.multi_step_tool %}
|
| 79 |
-
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
-
{%- endif %}
|
| 81 |
-
{%- for message in messages %}
|
| 82 |
-
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
-
{%- if message.role == "system" %}
|
| 84 |
-
{%- if not loop.first %}
|
| 85 |
-
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
-
{%- endif %}
|
| 87 |
-
{%- elif message.role == "user" %}
|
| 88 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
-
{%- elif message.role == "assistant" %}
|
| 90 |
-
{%- set reasoning_content = '' %}
|
| 91 |
-
{%- if message.reasoning_content is string %}
|
| 92 |
-
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
-
{%- else %}
|
| 94 |
-
{%- if '</think>' in content %}
|
| 95 |
-
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
-
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
-
{%- endif %}
|
| 98 |
-
{%- endif %}
|
| 99 |
-
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
-
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
-
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
-
{%- else %}
|
| 103 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
-
{%- endif %}
|
| 105 |
-
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
-
{%- for tool_call in message.tool_calls %}
|
| 107 |
-
{%- if tool_call.function is defined %}
|
| 108 |
-
{%- set tool_call = tool_call.function %}
|
| 109 |
-
{%- endif %}
|
| 110 |
-
{%- if loop.first %}
|
| 111 |
-
{%- if content|trim %}
|
| 112 |
-
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
-
{%- else %}
|
| 114 |
-
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
-
{%- endif %}
|
| 116 |
-
{%- else %}
|
| 117 |
-
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
-
{%- endif %}
|
| 119 |
-
{%- if tool_call.arguments is defined %}
|
| 120 |
-
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
-
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
-
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
-
{{- args_value }}
|
| 124 |
-
{{- '\n</parameter>\n' }}
|
| 125 |
-
{%- endfor %}
|
| 126 |
-
{%- endif %}
|
| 127 |
-
{{- '</function>\n</tool_call>' }}
|
| 128 |
-
{%- endfor %}
|
| 129 |
-
{%- endif %}
|
| 130 |
-
{{- '<|im_end|>\n' }}
|
| 131 |
-
{%- elif message.role == "tool" %}
|
| 132 |
-
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
-
{{- '<|im_start|>user' }}
|
| 134 |
-
{%- endif %}
|
| 135 |
-
{{- '\n<tool_response>\n' }}
|
| 136 |
-
{{- content }}
|
| 137 |
-
{{- '\n</tool_response>' }}
|
| 138 |
-
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
-
{{- '<|im_end|>\n' }}
|
| 140 |
-
{%- elif loop.last %}
|
| 141 |
-
{{- '<|im_end|>\n' }}
|
| 142 |
-
{%- endif %}
|
| 143 |
-
{%- else %}
|
| 144 |
-
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
-
{%- endif %}
|
| 146 |
-
{%- endfor %}
|
| 147 |
-
{%- if add_generation_prompt %}
|
| 148 |
-
{{- '<|im_start|>assistant\n' }}
|
| 149 |
-
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
-
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
-
{%- else %}
|
| 152 |
-
{{- '<think>\n' }}
|
| 153 |
-
{%- endif %}
|
| 154 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter/processor_config.json
DELETED
|
@@ -1,60 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"image_processor": {
|
| 3 |
-
"do_convert_rgb": true,
|
| 4 |
-
"do_normalize": true,
|
| 5 |
-
"do_rescale": true,
|
| 6 |
-
"do_resize": true,
|
| 7 |
-
"image_mean": [
|
| 8 |
-
0.5,
|
| 9 |
-
0.5,
|
| 10 |
-
0.5
|
| 11 |
-
],
|
| 12 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
-
"image_std": [
|
| 14 |
-
0.5,
|
| 15 |
-
0.5,
|
| 16 |
-
0.5
|
| 17 |
-
],
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"patch_size": 16,
|
| 20 |
-
"resample": 3,
|
| 21 |
-
"rescale_factor": 0.00392156862745098,
|
| 22 |
-
"size": {
|
| 23 |
-
"longest_edge": 16777216,
|
| 24 |
-
"shortest_edge": 65536
|
| 25 |
-
},
|
| 26 |
-
"temporal_patch_size": 2
|
| 27 |
-
},
|
| 28 |
-
"processor_class": "Qwen3VLProcessor",
|
| 29 |
-
"video_processor": {
|
| 30 |
-
"do_convert_rgb": true,
|
| 31 |
-
"do_normalize": true,
|
| 32 |
-
"do_rescale": true,
|
| 33 |
-
"do_resize": true,
|
| 34 |
-
"do_sample_frames": true,
|
| 35 |
-
"fps": 2,
|
| 36 |
-
"image_mean": [
|
| 37 |
-
0.5,
|
| 38 |
-
0.5,
|
| 39 |
-
0.5
|
| 40 |
-
],
|
| 41 |
-
"image_std": [
|
| 42 |
-
0.5,
|
| 43 |
-
0.5,
|
| 44 |
-
0.5
|
| 45 |
-
],
|
| 46 |
-
"max_frames": 768,
|
| 47 |
-
"merge_size": 2,
|
| 48 |
-
"min_frames": 4,
|
| 49 |
-
"patch_size": 16,
|
| 50 |
-
"resample": 3,
|
| 51 |
-
"rescale_factor": 0.00392156862745098,
|
| 52 |
-
"return_metadata": false,
|
| 53 |
-
"size": {
|
| 54 |
-
"longest_edge": 25165824,
|
| 55 |
-
"shortest_edge": 4096
|
| 56 |
-
},
|
| 57 |
-
"temporal_patch_size": 2,
|
| 58 |
-
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
-
}
|
| 60 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter/tokenizer_config.json
DELETED
|
@@ -1,34 +0,0 @@
|
|
| 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 |
-
"local_files_only": false,
|
| 14 |
-
"model_max_length": 262144,
|
| 15 |
-
"model_specific_special_tokens": {
|
| 16 |
-
"audio_bos_token": "<|audio_start|>",
|
| 17 |
-
"audio_eos_token": "<|audio_end|>",
|
| 18 |
-
"audio_token": "<|audio_pad|>",
|
| 19 |
-
"image_token": "<|image_pad|>",
|
| 20 |
-
"video_token": "<|video_pad|>",
|
| 21 |
-
"vision_bos_token": "<|vision_start|>",
|
| 22 |
-
"vision_eos_token": "<|vision_end|>"
|
| 23 |
-
},
|
| 24 |
-
"pad_token": "<|endoftext|>",
|
| 25 |
-
"padding_side": "right",
|
| 26 |
-
"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+",
|
| 27 |
-
"processor_class": "Qwen3VLProcessor",
|
| 28 |
-
"split_special_tokens": false,
|
| 29 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 30 |
-
"unk_token": null,
|
| 31 |
-
"video_token": "<|video_pad|>",
|
| 32 |
-
"vision_bos_token": "<|vision_start|>",
|
| 33 |
-
"vision_eos_token": "<|vision_end|>"
|
| 34 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -3,8 +3,11 @@
|
|
| 3 |
"Qwen3_5ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
"dtype": "bfloat16",
|
|
|
|
|
|
|
| 6 |
"image_token_id": 248056,
|
| 7 |
"model_type": "qwen3_5",
|
|
|
|
| 8 |
"text_config": {
|
| 9 |
"attention_bias": false,
|
| 10 |
"attention_dropout": 0.0,
|
|
@@ -81,16 +84,17 @@
|
|
| 81 |
"rope_type": "default"
|
| 82 |
},
|
| 83 |
"tie_word_embeddings": true,
|
| 84 |
-
"use_cache":
|
| 85 |
"vocab_size": 248320
|
| 86 |
},
|
| 87 |
"tie_word_embeddings": true,
|
| 88 |
"transformers_version": "5.8.0",
|
|
|
|
| 89 |
"video_token_id": 248057,
|
| 90 |
"vision_config": {
|
| 91 |
"deepstack_visual_indexes": [],
|
| 92 |
"depth": 24,
|
| 93 |
-
"dtype": "
|
| 94 |
"hidden_act": "gelu_pytorch_tanh",
|
| 95 |
"hidden_size": 1024,
|
| 96 |
"in_channels": 3,
|
|
|
|
| 3 |
"Qwen3_5ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"hidden_size": 2560,
|
| 8 |
"image_token_id": 248056,
|
| 9 |
"model_type": "qwen3_5",
|
| 10 |
+
"pad_token_id": 248044,
|
| 11 |
"text_config": {
|
| 12 |
"attention_bias": false,
|
| 13 |
"attention_dropout": 0.0,
|
|
|
|
| 84 |
"rope_type": "default"
|
| 85 |
},
|
| 86 |
"tie_word_embeddings": true,
|
| 87 |
+
"use_cache": false,
|
| 88 |
"vocab_size": 248320
|
| 89 |
},
|
| 90 |
"tie_word_embeddings": true,
|
| 91 |
"transformers_version": "5.8.0",
|
| 92 |
+
"use_cache": false,
|
| 93 |
"video_token_id": 248057,
|
| 94 |
"vision_config": {
|
| 95 |
"deepstack_visual_indexes": [],
|
| 96 |
"depth": 24,
|
| 97 |
+
"dtype": "bfloat16",
|
| 98 |
"hidden_act": "gelu_pytorch_tanh",
|
| 99 |
"hidden_size": 1024,
|
| 100 |
"in_channels": 3,
|
generation_config.json
CHANGED
|
@@ -1,7 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"
|
| 4 |
-
|
|
|
|
|
|
|
| 5 |
"pad_token_id": 248044,
|
| 6 |
"transformers_version": "5.8.0",
|
| 7 |
"use_cache": true
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248046,
|
| 5 |
+
248044
|
| 6 |
+
],
|
| 7 |
"pad_token_id": 248044,
|
| 8 |
"transformers_version": "5.8.0",
|
| 9 |
"use_cache": true
|
merge_validation.json
DELETED
|
@@ -1,32 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"method": "PEFT merge_and_unload(safe_merge=True), FP32 merge then BF16 export",
|
| 3 |
-
"device": "cpu",
|
| 4 |
-
"versions": {
|
| 5 |
-
"torch": "2.6.0+cu124",
|
| 6 |
-
"transformers": "5.8.0",
|
| 7 |
-
"peft": "0.18.1",
|
| 8 |
-
"safetensors": "0.7.0"
|
| 9 |
-
},
|
| 10 |
-
"adapter_tensor_count": 496,
|
| 11 |
-
"all_adapter_tensors_loaded_exactly": true,
|
| 12 |
-
"merged_parameter_count": 4539265536,
|
| 13 |
-
"fp32_pre_post_merge_max_logit_error": 2.4020672e-05,
|
| 14 |
-
"fp32_pre_post_merge_all_argmax_equal": true,
|
| 15 |
-
"bf16_export_reload_logits_bitwise_equal": true,
|
| 16 |
-
"fp32_runtime_buffers_preserved": [
|
| 17 |
-
"model.visual.rotary_pos_emb.inv_freq",
|
| 18 |
-
"model.language_model.rotary_emb.inv_freq",
|
| 19 |
-
"model.language_model.rotary_emb.original_inv_freq"
|
| 20 |
-
],
|
| 21 |
-
"tokenizer_vocab_matches_base_and_checkpoint": true,
|
| 22 |
-
"processor_class": "Qwen3VLProcessor",
|
| 23 |
-
"base_and_merged_loading_checks_passed": true,
|
| 24 |
-
"execution_evidence": [
|
| 25 |
-
"16:37:42 All 496 adapter tensors loaded exactly; checking forward before merge",
|
| 26 |
-
"16:38:20 Merge validated: max logit error=2.4020672e-05; all token argmax equal",
|
| 27 |
-
"16:39:20 Export reload is exact; tokenizer and processor load successfully"
|
| 28 |
-
],
|
| 29 |
-
"validation_script_sha256": "453e8386a079b6dd651c1f19c5e61e0886a0799a94d9e0482703f4da09bc0a90",
|
| 30 |
-
"metadata_note": "Completed validation metadata from successful assertion log after JSON serialization of an empty loading-info set failed. Numerical error is rounded as printed in that log.",
|
| 31 |
-
"scope": "One short text prompt; no benchmark or GPU/vLLM validation."
|
| 32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model-00001-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e3b3dd2707eed9c76ac07079b6e64796691611d24fa8bc640b6c91b8842f6a0f
|
| 3 |
-
size 4972947968
|
|
|
|
|
|
|
|
|
|
|
|
model-00002-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:53d6f86f7467068482f57c1a2dce90da326aeb549b3d0a5de364a3438921fa34
|
| 3 |
-
size 4105672464
|
|
|
|
|
|
|
|
|
|
|
|
adapter/tokenizer.json → model.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9216d2612b2d8fcc0f5ad81c1ff8ff891c3564bbe93a1672104a2a44b43061c
|
| 3 |
+
size 9078620536
|
model.safetensors.index.json
DELETED
|
@@ -1,731 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"metadata": {
|
| 3 |
-
"total_parameters": 4539265536,
|
| 4 |
-
"total_size": 9078531072
|
| 5 |
-
},
|
| 6 |
-
"weight_map": {
|
| 7 |
-
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
-
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
-
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 10 |
-
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 11 |
-
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 12 |
-
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 13 |
-
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 14 |
-
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 15 |
-
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 16 |
-
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
-
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
-
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
-
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
-
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
-
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
-
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
-
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 24 |
-
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 25 |
-
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 26 |
-
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 27 |
-
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 28 |
-
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 29 |
-
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 30 |
-
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
-
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
-
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
-
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
-
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
-
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
-
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
-
"model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 38 |
-
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 39 |
-
"model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 40 |
-
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 41 |
-
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 42 |
-
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 43 |
-
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 44 |
-
"model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
-
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
-
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
-
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
-
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
-
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
-
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
-
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
-
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
-
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
-
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
-
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
-
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
-
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
-
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
-
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
-
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
-
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
-
"model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 63 |
-
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 64 |
-
"model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 65 |
-
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 66 |
-
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 67 |
-
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 68 |
-
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 69 |
-
"model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
-
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
-
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
-
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
-
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
-
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
-
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
-
"model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 77 |
-
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 78 |
-
"model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 79 |
-
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 80 |
-
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 81 |
-
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 82 |
-
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 83 |
-
"model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
-
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
-
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
-
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
-
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
-
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
-
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
-
"model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 91 |
-
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 92 |
-
"model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 93 |
-
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 94 |
-
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 95 |
-
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 96 |
-
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 97 |
-
"model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
-
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
-
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
-
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
-
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
-
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
-
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
-
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
-
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
-
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
-
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
-
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
-
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
-
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
-
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
-
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
-
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
-
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
-
"model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 116 |
-
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 117 |
-
"model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 118 |
-
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 119 |
-
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 120 |
-
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 121 |
-
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 122 |
-
"model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
-
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
-
"model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
-
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
-
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
-
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 128 |
-
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
-
"model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 130 |
-
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 131 |
-
"model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 132 |
-
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 133 |
-
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 134 |
-
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 135 |
-
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 136 |
-
"model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 137 |
-
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
-
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
-
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
-
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
-
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 142 |
-
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 143 |
-
"model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 144 |
-
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 145 |
-
"model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 146 |
-
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 147 |
-
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 148 |
-
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 149 |
-
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 150 |
-
"model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 151 |
-
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
-
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
-
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
-
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
-
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
-
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
-
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
-
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
-
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
-
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
-
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
-
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
-
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
-
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
-
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
-
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
-
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
-
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 169 |
-
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 170 |
-
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 171 |
-
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 172 |
-
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 173 |
-
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 174 |
-
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 175 |
-
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 176 |
-
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
-
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
-
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
-
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
-
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
-
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
-
"model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 183 |
-
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 184 |
-
"model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 185 |
-
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 186 |
-
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 187 |
-
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 188 |
-
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 189 |
-
"model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
-
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
-
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
-
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
-
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
-
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
-
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
-
"model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 197 |
-
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 198 |
-
"model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 199 |
-
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 200 |
-
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 201 |
-
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 202 |
-
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 203 |
-
"model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
-
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
-
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
-
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
-
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
-
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 209 |
-
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 210 |
-
"model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 211 |
-
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 212 |
-
"model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 213 |
-
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 214 |
-
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 215 |
-
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 216 |
-
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 217 |
-
"model.language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
-
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
-
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
-
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
-
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
-
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
-
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
-
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
-
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
-
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
-
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
-
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
-
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
-
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
-
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 232 |
-
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
-
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
-
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
-
"model.language_model.layers.24.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 236 |
-
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 237 |
-
"model.language_model.layers.24.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 238 |
-
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 239 |
-
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 240 |
-
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 241 |
-
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 242 |
-
"model.language_model.layers.24.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 243 |
-
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
-
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
-
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
-
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
-
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
-
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
-
"model.language_model.layers.25.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 250 |
-
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 251 |
-
"model.language_model.layers.25.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 252 |
-
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 253 |
-
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 254 |
-
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 255 |
-
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 256 |
-
"model.language_model.layers.25.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
-
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
-
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
-
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
-
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
-
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 262 |
-
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 263 |
-
"model.language_model.layers.26.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 264 |
-
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 265 |
-
"model.language_model.layers.26.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 266 |
-
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 267 |
-
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 268 |
-
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 269 |
-
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 270 |
-
"model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 271 |
-
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 272 |
-
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
-
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
-
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
-
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
-
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
-
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
-
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
-
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
-
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
-
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
-
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
-
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
-
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
-
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
-
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
-
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
-
"model.language_model.layers.28.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 289 |
-
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 290 |
-
"model.language_model.layers.28.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 291 |
-
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 292 |
-
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 293 |
-
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 294 |
-
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 295 |
-
"model.language_model.layers.28.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
-
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
-
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
-
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
-
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
-
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
-
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
-
"model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 303 |
-
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 304 |
-
"model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 305 |
-
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 306 |
-
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 307 |
-
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 308 |
-
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 309 |
-
"model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
-
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
-
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
-
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
-
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
-
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
-
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 316 |
-
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
-
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
-
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
-
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
-
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
-
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
-
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
-
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
-
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
-
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
-
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 327 |
-
"model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 328 |
-
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 329 |
-
"model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 330 |
-
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 331 |
-
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 332 |
-
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 333 |
-
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 334 |
-
"model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 335 |
-
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
-
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
-
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
-
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
-
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 340 |
-
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 341 |
-
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
-
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
-
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
-
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 345 |
-
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 346 |
-
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
-
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
-
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
-
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
-
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
-
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 352 |
-
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 353 |
-
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 354 |
-
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 355 |
-
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 356 |
-
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 357 |
-
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 358 |
-
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 359 |
-
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
-
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
-
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
-
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
-
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
-
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
-
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
-
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 367 |
-
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 368 |
-
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 369 |
-
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 370 |
-
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 371 |
-
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 372 |
-
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 373 |
-
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
-
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
-
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
-
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
-
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
-
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 379 |
-
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
-
"model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 381 |
-
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 382 |
-
"model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 383 |
-
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 384 |
-
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 385 |
-
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 386 |
-
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 387 |
-
"model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
-
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
-
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
-
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
-
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
-
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
-
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
-
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
-
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
-
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
-
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
-
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
-
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
-
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
-
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
-
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
-
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
-
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 405 |
-
"model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 406 |
-
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 407 |
-
"model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 408 |
-
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 409 |
-
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 410 |
-
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 411 |
-
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 412 |
-
"model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 413 |
-
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
-
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
-
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
-
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
-
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 418 |
-
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 419 |
-
"model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 420 |
-
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 421 |
-
"model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 422 |
-
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 423 |
-
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 424 |
-
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 425 |
-
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 426 |
-
"model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 427 |
-
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
-
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
-
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
-
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
-
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 432 |
-
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 433 |
-
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 434 |
-
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 435 |
-
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 436 |
-
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 437 |
-
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 438 |
-
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 439 |
-
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 440 |
-
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 441 |
-
"model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 442 |
-
"model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 443 |
-
"model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 444 |
-
"model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 445 |
-
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 446 |
-
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 447 |
-
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 448 |
-
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 449 |
-
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 450 |
-
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 451 |
-
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 452 |
-
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 453 |
-
"model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 454 |
-
"model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 455 |
-
"model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 456 |
-
"model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 457 |
-
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 458 |
-
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 459 |
-
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 460 |
-
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 461 |
-
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 462 |
-
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 463 |
-
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 464 |
-
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 465 |
-
"model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 466 |
-
"model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 467 |
-
"model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 468 |
-
"model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 469 |
-
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 470 |
-
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 471 |
-
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 472 |
-
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 473 |
-
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 474 |
-
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 475 |
-
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 476 |
-
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 477 |
-
"model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 478 |
-
"model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 479 |
-
"model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 480 |
-
"model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 481 |
-
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 482 |
-
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 483 |
-
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 484 |
-
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 485 |
-
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 486 |
-
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 487 |
-
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 488 |
-
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 489 |
-
"model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 490 |
-
"model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 491 |
-
"model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 492 |
-
"model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 493 |
-
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 494 |
-
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 495 |
-
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 496 |
-
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 497 |
-
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 498 |
-
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 499 |
-
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 500 |
-
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 501 |
-
"model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 502 |
-
"model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 503 |
-
"model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 504 |
-
"model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 505 |
-
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 506 |
-
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 507 |
-
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 508 |
-
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 509 |
-
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 510 |
-
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 511 |
-
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 512 |
-
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 513 |
-
"model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 514 |
-
"model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 515 |
-
"model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 516 |
-
"model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 517 |
-
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 518 |
-
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 519 |
-
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 520 |
-
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 521 |
-
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 522 |
-
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 523 |
-
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 524 |
-
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 525 |
-
"model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 526 |
-
"model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 527 |
-
"model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 528 |
-
"model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 529 |
-
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 530 |
-
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 531 |
-
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 532 |
-
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 533 |
-
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 534 |
-
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 535 |
-
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 536 |
-
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 537 |
-
"model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 538 |
-
"model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 539 |
-
"model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 540 |
-
"model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 541 |
-
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 542 |
-
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 543 |
-
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 544 |
-
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 545 |
-
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 546 |
-
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 547 |
-
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 548 |
-
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 549 |
-
"model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 550 |
-
"model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 551 |
-
"model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 552 |
-
"model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 553 |
-
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 554 |
-
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 555 |
-
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 556 |
-
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 557 |
-
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 558 |
-
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 559 |
-
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 560 |
-
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 561 |
-
"model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 562 |
-
"model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 563 |
-
"model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 564 |
-
"model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 565 |
-
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 566 |
-
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 567 |
-
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 568 |
-
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 569 |
-
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 570 |
-
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 571 |
-
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 572 |
-
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 573 |
-
"model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 574 |
-
"model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 575 |
-
"model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 576 |
-
"model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 577 |
-
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 578 |
-
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 579 |
-
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 580 |
-
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 581 |
-
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 582 |
-
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 583 |
-
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 584 |
-
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 585 |
-
"model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 586 |
-
"model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 587 |
-
"model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 588 |
-
"model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 589 |
-
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 590 |
-
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 591 |
-
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 592 |
-
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 593 |
-
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 594 |
-
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 595 |
-
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 596 |
-
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 597 |
-
"model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 598 |
-
"model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 599 |
-
"model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 600 |
-
"model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 601 |
-
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 602 |
-
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 603 |
-
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 604 |
-
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 605 |
-
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 606 |
-
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 607 |
-
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 608 |
-
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 609 |
-
"model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 610 |
-
"model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 611 |
-
"model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 612 |
-
"model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 613 |
-
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 614 |
-
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 615 |
-
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 616 |
-
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 617 |
-
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 618 |
-
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 619 |
-
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 620 |
-
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 621 |
-
"model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 622 |
-
"model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 623 |
-
"model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 624 |
-
"model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 625 |
-
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 626 |
-
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 627 |
-
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 628 |
-
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 629 |
-
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 630 |
-
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 631 |
-
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 632 |
-
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 633 |
-
"model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 634 |
-
"model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 635 |
-
"model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 636 |
-
"model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 637 |
-
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 638 |
-
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 639 |
-
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 640 |
-
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 641 |
-
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 642 |
-
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 643 |
-
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 644 |
-
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 645 |
-
"model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 646 |
-
"model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 647 |
-
"model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 648 |
-
"model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 649 |
-
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 650 |
-
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 651 |
-
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 652 |
-
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 653 |
-
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 654 |
-
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 655 |
-
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 656 |
-
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 657 |
-
"model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 658 |
-
"model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 659 |
-
"model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 660 |
-
"model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 661 |
-
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 662 |
-
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
-
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 664 |
-
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 665 |
-
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 666 |
-
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 667 |
-
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 668 |
-
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 669 |
-
"model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 670 |
-
"model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 671 |
-
"model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 672 |
-
"model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 673 |
-
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 674 |
-
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 675 |
-
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 676 |
-
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 677 |
-
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 678 |
-
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 679 |
-
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 680 |
-
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 681 |
-
"model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 682 |
-
"model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 683 |
-
"model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 684 |
-
"model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 685 |
-
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 686 |
-
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 687 |
-
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 688 |
-
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 689 |
-
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 690 |
-
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 691 |
-
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 692 |
-
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 693 |
-
"model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 694 |
-
"model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 695 |
-
"model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 696 |
-
"model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 697 |
-
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 698 |
-
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 699 |
-
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 700 |
-
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 701 |
-
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 702 |
-
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 703 |
-
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 704 |
-
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 705 |
-
"model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 706 |
-
"model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 707 |
-
"model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 708 |
-
"model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 709 |
-
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 710 |
-
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 711 |
-
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 712 |
-
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 713 |
-
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 714 |
-
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 715 |
-
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 716 |
-
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 717 |
-
"model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 718 |
-
"model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 719 |
-
"model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 720 |
-
"model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 721 |
-
"model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 722 |
-
"model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 723 |
-
"model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 724 |
-
"model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 725 |
-
"model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 726 |
-
"model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 727 |
-
"model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 728 |
-
"model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 729 |
-
"model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 730 |
-
}
|
| 731 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_summary.json
CHANGED
|
@@ -1,29 +1,44 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"base_model": "Qwen/Qwen3.5-4B",
|
| 3 |
-
"
|
| 4 |
-
"
|
|
|
|
|
|
|
|
|
|
| 5 |
"stage": "sft",
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
"
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
"train_samples_per_second": 1.016,
|
| 26 |
-
"train_steps_per_second": 0.127
|
| 27 |
},
|
| 28 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"model": "DesignCoder 4B AdamW step200",
|
| 3 |
"base_model": "Qwen/Qwen3.5-4B",
|
| 4 |
+
"source_repo": "xingxm/DesignCoder",
|
| 5 |
+
"source_subfolder": "designcoder_qwen3.5_4b_adamw_bs256_data41287_step200",
|
| 6 |
+
"source_local_directory": "/data/xueziteng/LlamaFactory-DesignCoder/DesignCoder/designcoder_qwen3.5_4b_adamw_bs256_data41287_step200",
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"epoch": 1.5066162570888468,
|
| 9 |
"stage": "sft",
|
| 10 |
+
"finetuning_type": "full",
|
| 11 |
+
"optimizer": "AdamW",
|
| 12 |
+
"learning_rate": 2e-05,
|
| 13 |
+
"global_batch_size": 256,
|
| 14 |
+
"dataset": "designcoder_sft_v2_train",
|
| 15 |
+
"dataset_rows": 41287,
|
| 16 |
+
"training_hardware": "8 nodes x 8 H20 (source model card)",
|
| 17 |
+
"stored_parameters": 4539265536,
|
| 18 |
+
"weights_precision": "BF16",
|
| 19 |
+
"protocol": {
|
| 20 |
+
"landing": [
|
| 21 |
+
"design_search",
|
| 22 |
+
"websearch",
|
| 23 |
+
"html_css_js"
|
| 24 |
+
],
|
| 25 |
+
"dashboard": [
|
| 26 |
+
"design_search",
|
| 27 |
+
"html_css_js"
|
| 28 |
+
]
|
|
|
|
|
|
|
| 29 |
},
|
| 30 |
+
"metadata_sources": [
|
| 31 |
+
"source README.md",
|
| 32 |
+
"trainer_state.json",
|
| 33 |
+
"safetensors tensor headers"
|
| 34 |
+
],
|
| 35 |
+
"benchmark": {
|
| 36 |
+
"name": "Bench200",
|
| 37 |
+
"n": 200,
|
| 38 |
+
"scoring_policy": "fixed-assets-layout-v1",
|
| 39 |
+
"overall": 83.29480723189961,
|
| 40 |
+
"judge": "unrecorded",
|
| 41 |
+
"source": "outputs/fixed-assets-layout-v1-20260926/summary.json"
|
| 42 |
+
},
|
| 43 |
+
"export": "Original full checkpoint copied byte-for-byte; no merge or quantization."
|
| 44 |
}
|
upload_manifest.json
CHANGED
|
@@ -1,83 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"source_checkpoint": "qwen35-4b-design/lora-r64-sft/checkpoint-12588",
|
| 4 |
-
"source_adapter_sha256": "7d8305739df470c3d7906241a14ae37b342e1ba61f34b3d0341e69b97f85f12b",
|
| 5 |
-
"base_model": "Qwen/Qwen3.5-4B",
|
| 6 |
-
"base_revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
|
| 7 |
-
"source_base_files": {
|
| 8 |
-
"model.safetensors-00001-of-00002.safetensors": {
|
| 9 |
-
"bytes": 5329398688,
|
| 10 |
-
"sha256": "26a93f066e1916adb13453dae5a0c707c0fbc71299ed98779571a907b8e74c61"
|
| 11 |
-
},
|
| 12 |
-
"model.safetensors-00002-of-00002.safetensors": {
|
| 13 |
-
"bytes": 3990429408,
|
| 14 |
-
"sha256": "cb544bd9bfae93dc59b0f22b292f5933573854a7f9b97835c67060d7d910e188"
|
| 15 |
-
},
|
| 16 |
-
"config.json": {
|
| 17 |
-
"bytes": 3161,
|
| 18 |
-
"sha256": "ddc63e1c717afa86c865bb5e01313d89d72bb53b97ad4a8a03ba8510c0621670"
|
| 19 |
-
}
|
| 20 |
-
},
|
| 21 |
"files": {
|
| 22 |
-
"LICENSE": {
|
| 23 |
-
"bytes": 11544,
|
| 24 |
-
"sha256": "bbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a"
|
| 25 |
-
},
|
| 26 |
-
"adapter/adapter_config.json": {
|
| 27 |
-
"bytes": 1172,
|
| 28 |
-
"sha256": "7bd5a23542725c33d35bef0a9f6e75508265641ed29c547e1187951b89ceea12"
|
| 29 |
-
},
|
| 30 |
-
"adapter/adapter_model.safetensors": {
|
| 31 |
-
"bytes": 519513832,
|
| 32 |
-
"sha256": "7d8305739df470c3d7906241a14ae37b342e1ba61f34b3d0341e69b97f85f12b"
|
| 33 |
-
},
|
| 34 |
-
"adapter/chat_template.jinja": {
|
| 35 |
-
"bytes": 7756,
|
| 36 |
-
"sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715"
|
| 37 |
-
},
|
| 38 |
-
"adapter/processor_config.json": {
|
| 39 |
-
"bytes": 1191,
|
| 40 |
-
"sha256": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1"
|
| 41 |
-
},
|
| 42 |
-
"adapter/tokenizer.json": {
|
| 43 |
-
"bytes": 19989325,
|
| 44 |
-
"sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523"
|
| 45 |
-
},
|
| 46 |
-
"adapter/tokenizer_config.json": {
|
| 47 |
-
"bytes": 1192,
|
| 48 |
-
"sha256": "4a5bac6704ca726f9a48fe654a01eb5ea4d01d9d498aaf23035c74fa2a4f240a"
|
| 49 |
-
},
|
| 50 |
-
"chat_template.jinja": {
|
| 51 |
-
"bytes": 7756,
|
| 52 |
-
"sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715"
|
| 53 |
-
},
|
| 54 |
"config.json": {
|
| 55 |
-
"bytes":
|
| 56 |
-
"sha256": "
|
| 57 |
},
|
| 58 |
"generation_config.json": {
|
| 59 |
"bytes": 163,
|
| 60 |
-
"sha256": "
|
| 61 |
-
},
|
| 62 |
-
"merge_validation.json": {
|
| 63 |
-
"bytes": 1492,
|
| 64 |
-
"sha256": "73e05cf2b79cfed0a5be5139a53fb5d21e072d796b99fb555439b651f313f392"
|
| 65 |
-
},
|
| 66 |
-
"model-00001-of-00002.safetensors": {
|
| 67 |
-
"bytes": 4972947968,
|
| 68 |
-
"sha256": "e3b3dd2707eed9c76ac07079b6e64796691611d24fa8bc640b6c91b8842f6a0f"
|
| 69 |
-
},
|
| 70 |
-
"model-00002-of-00002.safetensors": {
|
| 71 |
-
"bytes": 4105672464,
|
| 72 |
-
"sha256": "53d6f86f7467068482f57c1a2dce90da326aeb549b3d0a5de364a3438921fa34"
|
| 73 |
-
},
|
| 74 |
-
"model.safetensors.index.json": {
|
| 75 |
-
"bytes": 66236,
|
| 76 |
-
"sha256": "df59e0e8f68ce1841a11ec0ba05e468a1413a7c5df5d1fa1e8b29a911a1b29d1"
|
| 77 |
},
|
| 78 |
-
"
|
| 79 |
-
"bytes":
|
| 80 |
-
"sha256": "
|
| 81 |
},
|
| 82 |
"tokenizer.json": {
|
| 83 |
"bytes": 19989325,
|
|
@@ -87,13 +21,13 @@
|
|
| 87 |
"bytes": 1192,
|
| 88 |
"sha256": "4a5bac6704ca726f9a48fe654a01eb5ea4d01d9d498aaf23035c74fa2a4f240a"
|
| 89 |
},
|
| 90 |
-
"
|
| 91 |
-
"bytes":
|
| 92 |
-
"sha256": "
|
| 93 |
},
|
| 94 |
-
"
|
| 95 |
-
"bytes":
|
| 96 |
-
"sha256": "
|
| 97 |
}
|
| 98 |
}
|
| 99 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"source": "/data/xueziteng/LlamaFactory-DesignCoder/DesignCoder/designcoder_qwen3.5_4b_adamw_bs256_data41287_step200",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"files": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"config.json": {
|
| 5 |
+
"bytes": 2926,
|
| 6 |
+
"sha256": "885f7f5909376e3b03176428565835c4b6d8ed8febe94867f3482f3789e4548e"
|
| 7 |
},
|
| 8 |
"generation_config.json": {
|
| 9 |
"bytes": 163,
|
| 10 |
+
"sha256": "c6d7b111043eeefcd620e30bf0963fa5bac15bd0c8392d9326ce4ec5e1577458"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
},
|
| 12 |
+
"model.safetensors": {
|
| 13 |
+
"bytes": 9078620536,
|
| 14 |
+
"sha256": "d9216d2612b2d8fcc0f5ad81c1ff8ff891c3564bbe93a1672104a2a44b43061c"
|
| 15 |
},
|
| 16 |
"tokenizer.json": {
|
| 17 |
"bytes": 19989325,
|
|
|
|
| 21 |
"bytes": 1192,
|
| 22 |
"sha256": "4a5bac6704ca726f9a48fe654a01eb5ea4d01d9d498aaf23035c74fa2a4f240a"
|
| 23 |
},
|
| 24 |
+
"processor_config.json": {
|
| 25 |
+
"bytes": 1191,
|
| 26 |
+
"sha256": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1"
|
| 27 |
},
|
| 28 |
+
"chat_template.jinja": {
|
| 29 |
+
"bytes": 7756,
|
| 30 |
+
"sha256": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715"
|
| 31 |
}
|
| 32 |
}
|
| 33 |
}
|