初始化项目，由ModelHub XC社区提供模型
Model: BrandonHowe/Qwen3-8b-urban-qwen-seed1-20260930-CPT-final-step-1500 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
22
README.md
Normal file
22
README.md
Normal file
@@ -0,0 +1,22 @@
|
||||
---
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
base_model: Qwen/Qwen3-8B-Base
|
||||
datasets:
|
||||
- CompassioninMachineLearning/urban_12738_cleaned
|
||||
tags:
|
||||
- continued-pretraining
|
||||
- bf16
|
||||
---
|
||||
|
||||
# Qwen3-8b-urban-qwen-seed1-20260930-CPT-final-step-1500
|
||||
|
||||
Standalone merged BF16 model from epoch 3.970178926441352, step 1500.
|
||||
|
||||
Dataset: `CompassioninMachineLearning/urban_12738_cleaned` at `ef7c0e742df63ea319e35d02d9f6ba63d6e7c68d`.
|
||||
|
||||
Training: 10,072 distinct documents plus 2,000 repeat exposures per epoch; 200 disjoint validation documents.
|
||||
|
||||
Merged with Unsloth's native `save_pretrained_merged(save_method="merged_16bit")`. Weights are validated BF16 and packaged losslessly into eight safetensors shards. No adapter is required to load this model.
|
||||
|
||||
See `run_manifest.json` for base revision, document selection hashes, training parameters and export validation. Training does not establish an improvement in compassion; evaluate that separately.
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set content = message.content %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in message.content %}
|
||||
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"torch_dtype": "bfloat16",
|
||||
"eos_token_id": 151643,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936,
|
||||
"_name_or_path": "Qwen/Qwen3-8B-Base"
|
||||
}
|
||||
15
export_validation.json
Normal file
15
export_validation.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"weight_shards": 8,
|
||||
"weight_tensors": 399,
|
||||
"weight_bytes": 16381470720,
|
||||
"tensor_dtypes": [
|
||||
"BF16"
|
||||
],
|
||||
"finite_weights": true,
|
||||
"packaging_changes_tensor_values": false,
|
||||
"serialization_method": "huggingface_hub.save_torch_state_dict",
|
||||
"max_shard_size": 2224710480,
|
||||
"base_model": "Qwen/Qwen3-8B-Base",
|
||||
"base_revision": "49e3418fbbbca6ecbdf9608b4d22e5a407081db4",
|
||||
"merge_method": "Unsloth save_pretrained_merged(save_method=\"merged_16bit\")"
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"eos_token_id": [
|
||||
151643
|
||||
],
|
||||
"max_length": 32768,
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151654,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00008.safetensors
Normal file
3
model-00001-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f7cf74d2ea10dec6091a77021964ea51486d26f20db2f7917618ad5a823635c6
|
||||
size 2217783232
|
||||
3
model-00002-of-00008.safetensors
Normal file
3
model-00002-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ced6db7ee0023c53c4a0642db786a46357af799f7761fb3827ac538939d60bbe
|
||||
size 2164369920
|
||||
3
model-00003-of-00008.safetensors
Normal file
3
model-00003-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2782b5405d693fbc95f7dc3991779c6e6e2beb4e407869ac5260c078eb913af0
|
||||
size 2130797504
|
||||
3
model-00004-of-00008.safetensors
Normal file
3
model-00004-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:46bbdc5513c21871514dcdbdab031d2b475506160f0567bb17981718688eda78
|
||||
size 2164369360
|
||||
3
model-00005-of-00008.safetensors
Normal file
3
model-00005-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f0413c89b2ea47ae69a00a0fe7a1c943fdd44d32e06f5af98a43092c265e9939
|
||||
size 2214701400
|
||||
3
model-00006-of-00008.safetensors
Normal file
3
model-00006-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1f7299378f546791999560efc482b3b0e9d1346406ad934ed1fdcef8993098a5
|
||||
size 2130797504
|
||||
3
model-00007-of-00008.safetensors
Normal file
3
model-00007-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e0f9f4ed28dd72094d866c92074d1c179093892c606289cd9c91d1045bcd6877
|
||||
size 2114037960
|
||||
3
model-00008-of-00008.safetensors
Normal file
3
model-00008-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c97f901eba0786ddecd9a97556ae8e0edaa7f77dbf704306f83f7bf3ec62f91
|
||||
size 1244659840
|
||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16381470720
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.norm.weight": "model-00007-of-00008.safetensors",
|
||||
"lm_head.weight": "model-00008-of-00008.safetensors"
|
||||
}
|
||||
}
|
||||
516
run_manifest.json
Normal file
516
run_manifest.json
Normal file
@@ -0,0 +1,516 @@
|
||||
{
|
||||
"model": "Qwen/Qwen3-8B-Base",
|
||||
"model_revision": "49e3418fbbbca6ecbdf9608b4d22e5a407081db4",
|
||||
"dataset": "CompassioninMachineLearning/urban_12738_cleaned",
|
||||
"dataset_revision": "ef7c0e742df63ea319e35d02d9f6ba63d6e7c68d",
|
||||
"dataset_text_column": "output",
|
||||
"selection_hashes": {
|
||||
"train": "0c277f32a1dc30143b94eb2091d4c6a4967e5810a6182829af0ea487fe239c79",
|
||||
"validation": "dab93b63e8224211e4a1951a1ac547f1e119d4ac3677245bd918ae46fd51108d"
|
||||
},
|
||||
"dataset_selection": {
|
||||
"seed": 3407,
|
||||
"source_rows": 12738,
|
||||
"unique_train_rows": 10072,
|
||||
"replay_rows": 2000,
|
||||
"validation_rows": 200,
|
||||
"holdout_rows": 200,
|
||||
"train_tokens_per_epoch": 13979166,
|
||||
"validation_tokens": 231046
|
||||
},
|
||||
"packages": {
|
||||
"unsloth": "2026.9.2",
|
||||
"unsloth-zoo": "2026.9.1",
|
||||
"transformers": "4.57.6",
|
||||
"trl": "0.22.2",
|
||||
"datasets": "4.3.0",
|
||||
"huggingface_hub": "0.36.2",
|
||||
"tokenizers": "0.22.2",
|
||||
"peft": "0.20.0",
|
||||
"accelerate": "1.14.0",
|
||||
"bitsandbytes": "0.50.2",
|
||||
"wandb": "0.28.1",
|
||||
"torch": "2.11.0+cu128",
|
||||
"torchvision": "0.26.0+cu128",
|
||||
"torchaudio": "2.11.0+cu128",
|
||||
"triton": "3.6.0",
|
||||
"xformers": "0.0.35"
|
||||
},
|
||||
"environment_packages": [
|
||||
{
|
||||
"name": "accelerate",
|
||||
"version": "1.14.0"
|
||||
},
|
||||
{
|
||||
"name": "aiohappyeyeballs",
|
||||
"version": "2.7.1"
|
||||
},
|
||||
{
|
||||
"name": "aiohttp",
|
||||
"version": "3.14.3"
|
||||
},
|
||||
{
|
||||
"name": "aiosignal",
|
||||
"version": "1.4.0"
|
||||
},
|
||||
{
|
||||
"name": "annotated-doc",
|
||||
"version": "0.0.5"
|
||||
},
|
||||
{
|
||||
"name": "annotated-types",
|
||||
"version": "0.8.0"
|
||||
},
|
||||
{
|
||||
"name": "anyio",
|
||||
"version": "4.15.1"
|
||||
},
|
||||
{
|
||||
"name": "attrs",
|
||||
"version": "26.1.0"
|
||||
},
|
||||
{
|
||||
"name": "bitsandbytes",
|
||||
"version": "0.50.2"
|
||||
},
|
||||
{
|
||||
"name": "certifi",
|
||||
"version": "2026.7.22"
|
||||
},
|
||||
{
|
||||
"name": "charset-normalizer",
|
||||
"version": "3.5.1"
|
||||
},
|
||||
{
|
||||
"name": "click",
|
||||
"version": "8.5.0"
|
||||
},
|
||||
{
|
||||
"name": "cuda-bindings",
|
||||
"version": "12.9.7"
|
||||
},
|
||||
{
|
||||
"name": "cuda-pathfinder",
|
||||
"version": "1.6.0"
|
||||
},
|
||||
{
|
||||
"name": "cuda-toolkit",
|
||||
"version": "12.8.1"
|
||||
},
|
||||
{
|
||||
"name": "cut-cross-entropy",
|
||||
"version": "25.1.1"
|
||||
},
|
||||
{
|
||||
"name": "datasets",
|
||||
"version": "4.3.0"
|
||||
},
|
||||
{
|
||||
"name": "diffusers",
|
||||
"version": "0.39.0"
|
||||
},
|
||||
{
|
||||
"name": "dill",
|
||||
"version": "0.4.0"
|
||||
},
|
||||
{
|
||||
"name": "docstring_parser",
|
||||
"version": "0.18.0"
|
||||
},
|
||||
{
|
||||
"name": "filelock",
|
||||
"version": "3.32.3"
|
||||
},
|
||||
{
|
||||
"name": "frozenlist",
|
||||
"version": "1.8.0"
|
||||
},
|
||||
{
|
||||
"name": "fsspec",
|
||||
"version": "2025.9.0"
|
||||
},
|
||||
{
|
||||
"name": "h11",
|
||||
"version": "0.16.0"
|
||||
},
|
||||
{
|
||||
"name": "hf_transfer",
|
||||
"version": "0.1.9"
|
||||
},
|
||||
{
|
||||
"name": "hf-xet",
|
||||
"version": "1.6.0"
|
||||
},
|
||||
{
|
||||
"name": "httpcore",
|
||||
"version": "1.0.9"
|
||||
},
|
||||
{
|
||||
"name": "httpx",
|
||||
"version": "0.28.1"
|
||||
},
|
||||
{
|
||||
"name": "huggingface_hub",
|
||||
"version": "0.36.2"
|
||||
},
|
||||
{
|
||||
"name": "idna",
|
||||
"version": "3.20"
|
||||
},
|
||||
{
|
||||
"name": "importlib_metadata",
|
||||
"version": "9.0.1"
|
||||
},
|
||||
{
|
||||
"name": "Jinja2",
|
||||
"version": "3.1.6"
|
||||
},
|
||||
{
|
||||
"name": "markdown-it-py",
|
||||
"version": "4.2.0"
|
||||
},
|
||||
{
|
||||
"name": "MarkupSafe",
|
||||
"version": "3.0.3"
|
||||
},
|
||||
{
|
||||
"name": "mdurl",
|
||||
"version": "0.1.2"
|
||||
},
|
||||
{
|
||||
"name": "mpmath",
|
||||
"version": "1.3.0"
|
||||
},
|
||||
{
|
||||
"name": "msgspec",
|
||||
"version": "0.22.0"
|
||||
},
|
||||
{
|
||||
"name": "multidict",
|
||||
"version": "6.9.1"
|
||||
},
|
||||
{
|
||||
"name": "multiprocess",
|
||||
"version": "0.70.16"
|
||||
},
|
||||
{
|
||||
"name": "nest-asyncio",
|
||||
"version": "1.6.0"
|
||||
},
|
||||
{
|
||||
"name": "networkx",
|
||||
"version": "3.6.1"
|
||||
},
|
||||
{
|
||||
"name": "numpy",
|
||||
"version": "2.5.2"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-cublas-cu12",
|
||||
"version": "12.8.4.1"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-cuda-cupti-cu12",
|
||||
"version": "12.8.90"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-cuda-nvrtc-cu12",
|
||||
"version": "12.8.93"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-cuda-runtime-cu12",
|
||||
"version": "12.8.90"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-cudnn-cu12",
|
||||
"version": "9.19.0.56"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-cufft-cu12",
|
||||
"version": "11.3.3.83"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-cufile-cu12",
|
||||
"version": "1.13.1.3"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-curand-cu12",
|
||||
"version": "10.3.9.90"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-cusolver-cu12",
|
||||
"version": "11.7.3.90"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-cusparse-cu12",
|
||||
"version": "12.5.8.93"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-cusparselt-cu12",
|
||||
"version": "0.7.1"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-nccl-cu12",
|
||||
"version": "2.28.9"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-nvjitlink-cu12",
|
||||
"version": "12.8.93"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-nvshmem-cu12",
|
||||
"version": "3.4.5"
|
||||
},
|
||||
{
|
||||
"name": "nvidia-nvtx-cu12",
|
||||
"version": "12.8.90"
|
||||
},
|
||||
{
|
||||
"name": "packaging",
|
||||
"version": "26.3"
|
||||
},
|
||||
{
|
||||
"name": "pandas",
|
||||
"version": "3.0.6"
|
||||
},
|
||||
{
|
||||
"name": "peft",
|
||||
"version": "0.20.0"
|
||||
},
|
||||
{
|
||||
"name": "pillow",
|
||||
"version": "12.3.0"
|
||||
},
|
||||
{
|
||||
"name": "pip",
|
||||
"version": "26.2.1"
|
||||
},
|
||||
{
|
||||
"name": "platformdirs",
|
||||
"version": "4.12.2"
|
||||
},
|
||||
{
|
||||
"name": "propcache",
|
||||
"version": "0.5.4"
|
||||
},
|
||||
{
|
||||
"name": "protobuf",
|
||||
"version": "7.36.2"
|
||||
},
|
||||
{
|
||||
"name": "psutil",
|
||||
"version": "7.2.2"
|
||||
},
|
||||
{
|
||||
"name": "pyarrow",
|
||||
"version": "25.0.1"
|
||||
},
|
||||
{
|
||||
"name": "pydantic",
|
||||
"version": "2.13.5"
|
||||
},
|
||||
{
|
||||
"name": "pydantic_core",
|
||||
"version": "2.46.5"
|
||||
},
|
||||
{
|
||||
"name": "Pygments",
|
||||
"version": "2.21.0"
|
||||
},
|
||||
{
|
||||
"name": "python-dateutil",
|
||||
"version": "2.9.0.post0"
|
||||
},
|
||||
{
|
||||
"name": "PyYAML",
|
||||
"version": "6.0.3"
|
||||
},
|
||||
{
|
||||
"name": "regex",
|
||||
"version": "2026.9.29"
|
||||
},
|
||||
{
|
||||
"name": "requests",
|
||||
"version": "2.34.2"
|
||||
},
|
||||
{
|
||||
"name": "rich",
|
||||
"version": "15.0.0"
|
||||
},
|
||||
{
|
||||
"name": "safetensors",
|
||||
"version": "0.8.0"
|
||||
},
|
||||
{
|
||||
"name": "sentencepiece",
|
||||
"version": "0.2.2"
|
||||
},
|
||||
{
|
||||
"name": "sentry-sdk",
|
||||
"version": "2.71.0"
|
||||
},
|
||||
{
|
||||
"name": "setuptools",
|
||||
"version": "78.1.0"
|
||||
},
|
||||
{
|
||||
"name": "shellingham",
|
||||
"version": "1.5.4"
|
||||
},
|
||||
{
|
||||
"name": "six",
|
||||
"version": "1.17.0"
|
||||
},
|
||||
{
|
||||
"name": "structlog",
|
||||
"version": "26.1.0"
|
||||
},
|
||||
{
|
||||
"name": "sympy",
|
||||
"version": "1.14.0"
|
||||
},
|
||||
{
|
||||
"name": "tokenizers",
|
||||
"version": "0.22.2"
|
||||
},
|
||||
{
|
||||
"name": "torch",
|
||||
"version": "2.11.0+cu128"
|
||||
},
|
||||
{
|
||||
"name": "torchao",
|
||||
"version": "0.18.0"
|
||||
},
|
||||
{
|
||||
"name": "torchaudio",
|
||||
"version": "2.11.0+cu128"
|
||||
},
|
||||
{
|
||||
"name": "torchvision",
|
||||
"version": "0.26.0+cu128"
|
||||
},
|
||||
{
|
||||
"name": "tqdm",
|
||||
"version": "4.70.1"
|
||||
},
|
||||
{
|
||||
"name": "transformers",
|
||||
"version": "4.57.6"
|
||||
},
|
||||
{
|
||||
"name": "triton",
|
||||
"version": "3.6.0"
|
||||
},
|
||||
{
|
||||
"name": "trl",
|
||||
"version": "0.22.2"
|
||||
},
|
||||
{
|
||||
"name": "typeguard",
|
||||
"version": "4.6.0"
|
||||
},
|
||||
{
|
||||
"name": "typer",
|
||||
"version": "0.27.2"
|
||||
},
|
||||
{
|
||||
"name": "typing_extensions",
|
||||
"version": "4.16.0"
|
||||
},
|
||||
{
|
||||
"name": "typing-inspection",
|
||||
"version": "0.4.4"
|
||||
},
|
||||
{
|
||||
"name": "tyro",
|
||||
"version": "1.0.16"
|
||||
},
|
||||
{
|
||||
"name": "unsloth",
|
||||
"version": "2026.9.2"
|
||||
},
|
||||
{
|
||||
"name": "unsloth_zoo",
|
||||
"version": "2026.9.1"
|
||||
},
|
||||
{
|
||||
"name": "urllib3",
|
||||
"version": "2.8.0"
|
||||
},
|
||||
{
|
||||
"name": "wandb",
|
||||
"version": "0.28.1"
|
||||
},
|
||||
{
|
||||
"name": "wheel",
|
||||
"version": "0.48.0"
|
||||
},
|
||||
{
|
||||
"name": "xformers",
|
||||
"version": "0.0.35"
|
||||
},
|
||||
{
|
||||
"name": "xxhash",
|
||||
"version": "4.0.1"
|
||||
},
|
||||
{
|
||||
"name": "yarl",
|
||||
"version": "1.25.1"
|
||||
},
|
||||
{
|
||||
"name": "zipp",
|
||||
"version": "4.1.0"
|
||||
}
|
||||
],
|
||||
"python": "3.12.3",
|
||||
"cuda": "12.8",
|
||||
"gpu": "NVIDIA H100 80GB HBM3",
|
||||
"activation_checkpointing": "offload",
|
||||
"run_id": "urban-qwen-seed1-20260930",
|
||||
"timing_test": false,
|
||||
"collection_slug": "",
|
||||
"local_only": false,
|
||||
"push_to_hub": true,
|
||||
"merged_namespace": "BrandonHowe",
|
||||
"training": {
|
||||
"learning_rate": 5e-05,
|
||||
"embedding_learning_rate": 5e-06,
|
||||
"num_train_epochs": 5,
|
||||
"warmup_ratio": 0.05,
|
||||
"lr_scheduler_type": "cosine",
|
||||
"weight_decay": 0.01,
|
||||
"per_device_train_batch_size": 4,
|
||||
"gradient_accumulation_steps": 8,
|
||||
"per_device_eval_batch_size": 4,
|
||||
"seed": 1,
|
||||
"max_length": 8192
|
||||
},
|
||||
"adapter": {
|
||||
"rank": 128,
|
||||
"alpha": 64,
|
||||
"dropout": 0.05,
|
||||
"rslora": true,
|
||||
"random_state": 1
|
||||
},
|
||||
"execution": {
|
||||
"mode": "full",
|
||||
"max_steps": -1
|
||||
},
|
||||
"completed_epoch": 3.970178926441352,
|
||||
"global_step": 1500,
|
||||
"merged_export": {
|
||||
"weight_shards": 8,
|
||||
"weight_tensors": 399,
|
||||
"weight_bytes": 16381470720,
|
||||
"tensor_dtypes": [
|
||||
"BF16"
|
||||
],
|
||||
"finite_weights": true,
|
||||
"packaging_changes_tensor_values": false,
|
||||
"serialization_method": "huggingface_hub.save_torch_state_dict",
|
||||
"max_shard_size": 2224710480,
|
||||
"base_model": "Qwen/Qwen3-8B-Base",
|
||||
"base_revision": "49e3418fbbbca6ecbdf9608b4d22e5a407081db4",
|
||||
"merge_method": "Unsloth save_pretrained_merged(save_method=\"merged_16bit\")"
|
||||
}
|
||||
}
|
||||
25
special_tokens_map.json
Normal file
25
special_tokens_map.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|vision_pad|>"
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
241
tokenizer_config.json
Normal file
241
tokenizer_config.json
Normal file
@@ -0,0 +1,241 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|vision_pad|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}"
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user