初始化项目，由ModelHub XC社区提供模型
Model: jvonrad/Qwen-2.5-7B-grpo-nobonus-ablation 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
|
||||
16
README.md
Normal file
16
README.md
Normal file
@@ -0,0 +1,16 @@
|
||||
---
|
||||
base_model: Qwen/Qwen2.5-7B
|
||||
tags:
|
||||
- grpo
|
||||
- cross-lingual
|
||||
- ablation
|
||||
---
|
||||
|
||||
# Qwen-2.5-7B-grpo-nobonus-ablation
|
||||
|
||||
GRPO all_correct_bonus ablation on Qwen2.5-7B, trained on the WIKI-FACT /
|
||||
PolyFact cross-lingual factual-recall task (see
|
||||
[jvonrad/Lost-in-Mistranslation](https://github.com/jvonrad/Lost-in-Mistranslation)).
|
||||
`--all_correct_bonus 0.0` (all other hyperparameters match the paper's main
|
||||
GRPO run). Evaluated in `results/qwen-2.5-7b-grpo-nobonus-ablation_polyfact_consistency.json` and
|
||||
`results/qwen-2.5-7b-grpo-nobonus-ablation_gmmlu_lite_consistency.json` in the repo above.
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) 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' }}
|
||||
{%- endif %}
|
||||
62
config.json
Normal file
62
config.json
Normal file
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 131072,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.13.0",
|
||||
"use_cache": true,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": false,
|
||||
"eos_token_id": 151643,
|
||||
"max_new_tokens": 2048,
|
||||
"transformers_version": "5.13.0"
|
||||
}
|
||||
3
model-00001-of-00016.safetensors
Normal file
3
model-00001-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5be8567a86b9f8fdf251358a5757baf1e45239e4ba2ed2bb04d81d824a7031c5
|
||||
size 1089994880
|
||||
3
model-00002-of-00016.safetensors
Normal file
3
model-00002-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ac6fd723552764c41a811bc5700a78a1ab05985636cfae471f66da9e01eb3df4
|
||||
size 1089994896
|
||||
3
model-00003-of-00016.safetensors
Normal file
3
model-00003-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bdc92378f817fdf01a964c792f4ba6702d23465d14b05aa951017fe6f064d506
|
||||
size 932241160
|
||||
3
model-00004-of-00016.safetensors
Normal file
3
model-00004-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:432a7b9d52603b93adf08db5fd5a70227d761ffe86fd5255e25de13bf0f38e6d
|
||||
size 932233888
|
||||
3
model-00005-of-00016.safetensors
Normal file
3
model-00005-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8fc395dd2d17a621220f707ecdcc25039ba412dc512762d88d39a92bdf8c627d
|
||||
size 932233888
|
||||
3
model-00006-of-00016.safetensors
Normal file
3
model-00006-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:51388d2192941d79c78ed0a66c849b83d3ff94e7c0ff1c6f9d78d70f7ae3812f
|
||||
size 932233888
|
||||
3
model-00007-of-00016.safetensors
Normal file
3
model-00007-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1a6fbbc6a97fcc2d8b01e7c4a2bdabff4e58ac81ae6ae9bbaf72884d57856767
|
||||
size 932233880
|
||||
3
model-00008-of-00016.safetensors
Normal file
3
model-00008-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8d01d452e67c85d88ffe7b5e235a9722d7b0f4eb0b7b34f110c81ea827d3aa80
|
||||
size 932233912
|
||||
3
model-00009-of-00016.safetensors
Normal file
3
model-00009-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:952002f3a81efe00f09f457a1f8b236fb8dbdb9257aea5b41219efd16970b912
|
||||
size 932233912
|
||||
3
model-00010-of-00016.safetensors
Normal file
3
model-00010-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ac25327bb45435cc0e89beca145df226b0fb7efcd1a3b32837ebd1a9d044d7a9
|
||||
size 932233912
|
||||
3
model-00011-of-00016.safetensors
Normal file
3
model-00011-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a94eaa5e1b8380ab6e5139ae7b36cb57f5adb5540ef2c58f68f09eb798e3db33
|
||||
size 932233912
|
||||
3
model-00012-of-00016.safetensors
Normal file
3
model-00012-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7f354b10100815af934aba63cda83f8090b99ff963e6be90f78d3e1d6ac5db6f
|
||||
size 932233912
|
||||
3
model-00013-of-00016.safetensors
Normal file
3
model-00013-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8cff1b536e7b522f0467491d98c7013886585c2b56837f577bae042c59c6f37f
|
||||
size 932233912
|
||||
3
model-00014-of-00016.safetensors
Normal file
3
model-00014-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e352a0ad943f29176561b62bf672dd5959738fd8065f2465f473e4836c6cdebe
|
||||
size 932233912
|
||||
3
model-00015-of-00016.safetensors
Normal file
3
model-00015-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:366923dc252ccb87d7b2f47f6790cd10d1973cd16d5f7ad23b9179206a6cf77f
|
||||
size 932233912
|
||||
3
model-00016-of-00016.safetensors
Normal file
3
model-00016-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:de161c0c8415e2d51981bd54ad77aae92c34acee53f96e0c44fd9c7dc48b5d7f
|
||||
size 932233896
|
||||
347
model.safetensors.index.json
Normal file
347
model.safetensors.index.json
Normal file
@@ -0,0 +1,347 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 7615616512,
|
||||
"total_size": 15231233024
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00016.safetensors",
|
||||
"model.embed_tokens.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00015-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00015-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00015-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00015-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00015-of-00016.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.norm.weight": "model-00016-of-00016.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
30
tokenizer_config.json
Normal file
30
tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_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|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user