初始化项目，由ModelHub XC社区提供模型
Model: hakim78/DeepSeek-R1-Distill-Qwen-8B-Abliterated 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
|
||||
9
README.md
Normal file
9
README.md
Normal file
@@ -0,0 +1,9 @@
|
||||
---
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
# DeepSeek-R1-Distill-Qwen-8B-Abliterated
|
||||
|
||||
Abliterated build of DeepSeek-R1-Distill-Qwen-8B (Qwen2 architecture, 8B params).
|
||||
Servable via Text Generation Inference / vLLM (OpenAI-compatible chat completions).
|
||||
1
chat_template.jinja
Normal file
1
chat_template.jinja
Normal file
@@ -0,0 +1 @@
|
||||
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\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": "float16",
|
||||
"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": 10000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.0.0",
|
||||
"use_cache": true,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 151646,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.0.0"
|
||||
}
|
||||
3
model-00001-of-00010.safetensors
Normal file
3
model-00001-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cb5bfd8d83c32acc68b6291e53f9af6d846c2faeb0d2b36310e6fa69cc9d6d43
|
||||
size 1089994880
|
||||
3
model-00002-of-00010.safetensors
Normal file
3
model-00002-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a75139e5b06c9b489a738eb4d0d26e1125ee848bd24d15b94f85705fb65e276e
|
||||
size 1691909816
|
||||
3
model-00003-of-00010.safetensors
Normal file
3
model-00003-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:528073c3b5b7375eeca338bb29a4a5f8ee4b142f8b57a599fe1ec395c93645c1
|
||||
size 1728677040
|
||||
3
model-00004-of-00010.safetensors
Normal file
3
model-00004-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:12bb0f7477828604f21b614c90d18bd9ccf3d95704751401dcb7f0377d06fdbf
|
||||
size 1669932216
|
||||
3
model-00005-of-00010.safetensors
Normal file
3
model-00005-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:760d4381f3296d79e993654350439b50ba0b6c2cf77985824f63088c67611bff
|
||||
size 1728677056
|
||||
3
model-00006-of-00010.safetensors
Normal file
3
model-00006-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c05a2b5ba10485f756b4fc2665e65e19f84d687947b6162432e91ce289516a06
|
||||
size 1728677088
|
||||
3
model-00007-of-00010.safetensors
Normal file
3
model-00007-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:10ad57542601b206aec626c7cd2b0d863346017d99c3bd91c3e0517f6dee37bb
|
||||
size 1669932256
|
||||
3
model-00008-of-00010.safetensors
Normal file
3
model-00008-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d3323f94cc430609e90297727db5f0fdc8949020af05d86e10ccf80b119b2a57
|
||||
size 1728677088
|
||||
3
model-00009-of-00010.safetensors
Normal file
3
model-00009-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e7dc889d50db96e44db03634edd71bd336134cdb72e47f9972952c486bfd08cd
|
||||
size 1728677088
|
||||
3
model-00010-of-00010.safetensors
Normal file
3
model-00010-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b03038c257cfff5c1769b69acbee94f840b52dc4211be56ba0109b5c98e7b86e
|
||||
size 466116944
|
||||
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-00010.safetensors",
|
||||
"model.embed_tokens.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00006-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00007-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00008-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00009-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00010-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00010-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00010-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00003-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00004-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00005-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.norm.weight": "model-00010-of-00010.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:322664cdc3082b6eba003af5228a77ca1d7936d402e584ecde8f15d3d98bdb72
|
||||
size 11421911
|
||||
35
tokenizer_config.json
Normal file
35
tokenizer_config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<｜begin▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": true,
|
||||
"model_max_length": 16384,
|
||||
"pad_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<｜end▁of▁sentence｜>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"sp_model_kwargs": {},
|
||||
"unk_token": null,
|
||||
"tokenizer_class": "LlamaTokenizerFast",
|
||||
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}"
|
||||
}
|
||||
Reference in New Issue
Block a user