diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..aa7aacd0134a92c3c1943fdecc75cd8b7420cce6 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,5 @@ saved_model/**/* 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 +model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..672034e3a1196d8b9fc0116ddc037cb554227f89 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,119 @@ +[gMASK] +{%- set effective_reasoning_effort = 'high' if reasoning_effort is defined and reasoning_effort == 'high' else 'max' -%} +{%- if (enable_thinking is not defined or enable_thinking) and effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%} +{%- if tools -%} +{%- macro tool_to_json(tool) -%} + {%- set ns_tool = namespace(first=true) -%} + {{ '{' -}} + {%- for k, v in tool.items() -%} + {%- if k != 'defer_loading' and k != 'strict' -%} + {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%} + {%- set ns_tool.first = false -%} + "{{ k }}": {{ v | tojson(ensure_ascii=False) }} + {%- endif -%} + {%- endfor -%} + {{- '}' -}} +{%- endmacro -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{%- if 'function' in tool -%} + {%- set tool = tool['function'] -%} +{%- endif -%} +{% if tool.defer_loading is not defined or not tool.defer_loading %} +{{ tool_to_json(tool) }} +{% endif %} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name}{arg-key-1}{arg-value-1}{arg-key-2}{arg-value-2}...{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is string -%} + {{- item }} + {%- elif item is mapping and item.type in ['image', 'image_url', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%} + {%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%} + {{- "You are unable to process this " ~ media_type ~ " because you don't have multi-modal input ability. Try different methods." }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) -%} +{%- for m in messages %} + {%- if m.role == 'user' %} + {%- set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{%- for m in messages -%} +{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- elif '' in content %} + {%- set reasoning_content = content.split('')[0].split('')[-1] %} + {%- set content = content.split('')[-1] %} +{%- endif %} +{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%} +{{ '' + reasoning_content + ''}} +{%- else -%} +{{ '' }} +{%- endif -%} +{%- if content.strip() -%} +{{ content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{- '' + tc.name -}} +{% set _args = tc.arguments %}{% for k, v in _args.items() %}{{ k }}{{ v | tojson(ensure_ascii=False) if v is not string else v }}{% endfor %}{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' -}} +{%- endif %} +{%- if m.content is string -%} + {{- '' + m.content + '' -}} +{%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0.type == "tool_reference" -%} + {{- '\n' -}} + {% for tr in m.content %} + {%- for tool in tools -%} + {%- if 'function' in tool -%} + {%- set tool = tool['function'] -%} + {%- endif -%} + {%- if tool.name == tr.name -%} + {{- tool_to_json(tool) + '\n' -}} + {%- endif -%} + {%- endfor -%} + {%- endfor -%} + {{- '' -}} +{%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0 is mapping and m.content.0.output is defined -%} + {%- for tr in m.content -%} + {{- '' + tr.output + '' -}} + {%- endfor -%} +{%- else -%} + {{- '' + visible_text(m.content) + '' -}} +{% endif -%} +{%- elif m.role == 'system' -%} +<|system|>{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + <|assistant|>{{- '' if (enable_thinking is defined and not enable_thinking) else '' -}} +{%- endif -%} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4a4a4cc5a12f6b8aa1a1633ee36f9f70090c0bd7 --- /dev/null +++ b/config.json @@ -0,0 +1,449 @@ +{ + "architectures": [ + "GlmMoeDsaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 0, + "dtype": "bfloat16", + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "ep_size": 1, + "first_k_dense_replace": 3, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 6144, + "index_head_dim": 128, + "index_n_heads": 32, + "index_share_for_mtp_iteration": true, + "index_skip_topk_offset": 3, + "index_topk": 2048, + "index_topk_freq": 4, + "index_topk_pattern": null, + "indexer_rope_interleave": true, + "indexer_types": [ + "full", + "full", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared", + "full", + "shared", + "shared", + "shared" + ], + "initializer_range": 0.02, + "intermediate_size": 12288, + "kv_lora_rank": 512, + "layer_types": [ + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention", + "deepseek_sparse_attention" + ], + "max_position_embeddings": 1048576, + "mlp_bias": false, + "mlp_layer_types": [ + "dense", + "dense", + "dense", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse", + "sparse" + ], + "model_type": "glm_moe_dsa", + "moe_intermediate_size": 2048, + "moe_layer_freq": 1, + "n_group": 1, + "n_routed_experts": 168, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 64, + "num_experts": 256, + "num_experts_per_tok": 8, + "num_hidden_layers": 78, + "num_key_value_heads": 64, + "num_nextn_predict_layers": 1, + "pad_token_id": 154820, + "pretraining_tp": 1, + "q_lora_rank": 2048, + "qk_head_dim": 256, + "qk_nope_head_dim": 192, + "qk_rope_head_dim": 64, + "quantization_config": { + "autoround_version": "0.13.1", + "batch_size": 4, + "bits": 4, + "block_name_to_quantize": "model.layers", + "data_type": "int", + "extra_config": { + ".*layers\\.[0-2]\\.mlp.*": { + "bits": 16, + "data_type": "float" + }, + ".*weights_proj.*": { + "bits": 16, + "data_type": "float" + }, + "model.layers.0.mlp.down_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.0.mlp.gate_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.0.mlp.up_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.0.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.1.mlp.down_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.1.mlp.gate_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.1.mlp.up_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.1.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.10.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.14.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.18.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.2.mlp.down_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.2.mlp.gate_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.2.mlp.up_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.2.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.22.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.26.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.30.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.34.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.38.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.42.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.46.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.50.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.54.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.58.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.6.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.62.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.66.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.70.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + }, + "model.layers.74.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "float" + } + }, + "group_size": 128, + "low_gpu_mem_usage": true, + "nsamples": 512, + "packing_format": "auto_round:auto_gptq", + "quant_method": "auto-round", + "sym": true + }, + "rms_norm_eps": 1e-05, + "rope_interleave": true, + "rope_parameters": { + "rope_theta": 8000000, + "rope_type": "default" + }, + "routed_scaling_factor": 2.5, + "scoring_func": "sigmoid", + "tie_word_embeddings": false, + "topk_group": 1, + "topk_method": "noaux_tc", + "transformers_version": "5.12.1", + "use_cache": true, + "v_head_dim": 256, + "vocab_size": 154880 +} diff --git a/model-00001-of-00049.safetensors b/model-00001-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f38ca1999740047750cf0f2b4971ef9de42ab84 --- /dev/null +++ b/model-00001-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5904d65fb344992656b602eda5fb3272013e7e8c079b88c56a8b277c67872d4 +size 5368286104 diff --git a/model-00002-of-00049.safetensors b/model-00002-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59c319f5e35a43f72318cbb6fc18ecb025604b71 --- /dev/null +++ b/model-00002-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c753cd73aa7eda87191018732f131d8c0cfdc4266acc1ed3eb224dff1b6ea2d +size 5363657920 diff --git a/model-00003-of-00049.safetensors b/model-00003-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..feadbcd7b2bf55d9052faad80f2281697517d64c --- /dev/null +++ b/model-00003-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d93f65fd745250e2399bf87ba43f3ed05b3cc30ea7db4a0bc78f6ccaaf30d6f5 +size 5365123720 diff --git a/model-00004-of-00049.safetensors b/model-00004-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8687b05ca00132621448b6109e904f8c7a8cce13 --- /dev/null +++ b/model-00004-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ab319c9a68f3da4822aabb835bcf30819faed8c1bc39e11814b36e0aa83a618 +size 5363658160 diff --git a/model-00005-of-00049.safetensors b/model-00005-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..950b67ff5b56d87cc51e122a75ffae42eb120f53 --- /dev/null +++ b/model-00005-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d6b332be8627c981fb4d3bd7baecd64d729d3c5bb685d7cf1ce8badbe124c25 +size 5365124096 diff --git a/model-00006-of-00049.safetensors b/model-00006-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5711a25ac478d7afc79040a48db7a4083c2771c --- /dev/null +++ b/model-00006-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28470e0a3ee03b162f9b3929bc4cc65a5c07492dd8dadd17d8790014b376addf +size 5363660840 diff --git a/model-00007-of-00049.safetensors b/model-00007-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1531d9d92024dd456253fc032c7fb75366a1f63 --- /dev/null +++ b/model-00007-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69b75402f2b95b75dbf2aa5b2e4aec187bdede08dcee6e8368e9ec3bbfdcb026 +size 5366501720 diff --git a/model-00008-of-00049.safetensors b/model-00008-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5be1e39bd9396d228d0e2e11b5e1540b13977c4 --- /dev/null +++ b/model-00008-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd0d3a873281f9e382898599e80a84658b3b236a73dfe43a6df841f7c462c6a +size 5365126264 diff --git a/model-00009-of-00049.safetensors b/model-00009-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ad5e7646f38848afe424bcf4b622536cf750cba --- /dev/null +++ b/model-00009-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def468e7a4660d94f9f808918c6805e537cdca53a678920565eebcd8915650eb +size 5363660416 diff --git a/model-00010-of-00049.safetensors b/model-00010-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a2d02649bda49fc365c3b0e45d64296d9e326fac --- /dev/null +++ b/model-00010-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36237cdc22dd4aade4ef618cfa5a755dc6779ef269a0b66dc9b323150f90d087 +size 5365126104 diff --git a/model-00011-of-00049.safetensors b/model-00011-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b9774f4f7ff0cec154f49daa1d779258aa3d89a --- /dev/null +++ b/model-00011-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7001cf5fdcd522d783aa26ab6bc0bc8ad8b2284edc299a8ec851b777420bd401 +size 5363660656 diff --git a/model-00012-of-00049.safetensors b/model-00012-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..54faad2af61f6dfafd8abefd3c9c1c6f29965c50 --- /dev/null +++ b/model-00012-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4e94b9b8460c067fbba2c10dc6a9f08bb19b10e3ecdb0e4ab69a39f0707a80 +size 5366501912 diff --git a/model-00013-of-00049.safetensors b/model-00013-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..34bb6e18e34edc68982cc409f366a20df2cc70af --- /dev/null +++ b/model-00013-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3839ac40254b43d52d26d046db55d9746baedc839690976639ed0fc01e332825 +size 5358591360 diff --git a/model-00014-of-00049.safetensors b/model-00014-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..448d7343dc0e0e0c4a194e54bf9eb8445fc0e3f6 --- /dev/null +++ b/model-00014-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65bd541f086e77b4ef3f06051172a01efd52745e6b7412fb462747fff80a75fd +size 5363657568 diff --git a/model-00015-of-00049.safetensors b/model-00015-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1c82bc8a972e1f105dc6b40b51a50074de26029 --- /dev/null +++ b/model-00015-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eedc17b816ce04efec40fc2879f9e74c95ff81dabb229e7e29d5331f10f900a +size 5365126264 diff --git a/model-00016-of-00049.safetensors b/model-00016-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c0010a35db3bdf307ad557f801b7c449be01d464 --- /dev/null +++ b/model-00016-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59410b26b95f55b7c4a00ffa23cfcea7524063d3f4ab8e8b2f5b5babdf43e933 +size 5363660464 diff --git a/model-00017-of-00049.safetensors b/model-00017-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e48cd4bf5559eb670d2b3a2cc5bb48ba80c8edc --- /dev/null +++ b/model-00017-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a8f36faf15d9f56179642fa2f465d7623e632423888f7115da9f59fc18bd0d7 +size 5366502096 diff --git a/model-00018-of-00049.safetensors b/model-00018-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce4179392bd8fc598956b515c3aa870eef0975b3 --- /dev/null +++ b/model-00018-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0dd2b8d8f37487654ede600b86816341a6044ca22774646e77bd793d5a06b80 +size 5368822240 diff --git a/model-00019-of-00049.safetensors b/model-00019-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ad39be90ee16b69196d7ab9d80efabc697b8a24 --- /dev/null +++ b/model-00019-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8858c2c4c200cf94ad3dc5caf3d0ea15ec60f1e3d1eb5da1182c037797795868 +size 5366501856 diff --git a/model-00020-of-00049.safetensors b/model-00020-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d91190b45446010fa02ccb9eb9123a7b7c168d3a --- /dev/null +++ b/model-00020-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874f3bdcaa6c0ce5cdf25637794cc0fcaa4b64d028d2f9a8b8812cbc38314270 +size 5365126328 diff --git a/model-00021-of-00049.safetensors b/model-00021-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f99150b31ad37d8e7470391bf8cde195dc05ae26 --- /dev/null +++ b/model-00021-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94155143f17369414bc51ae2465387f66d18c92ec4756b4820b2541f02afd7e3 +size 5363660224 diff --git a/model-00022-of-00049.safetensors b/model-00022-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f60e20700d51c0e14a70928d8265e0799661e5f6 --- /dev/null +++ b/model-00022-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dd37f7bad35c9ff5e67438ae4d04247865ecafe673d7d5b8a4803b54e78ac25 +size 5366502280 diff --git a/model-00023-of-00049.safetensors b/model-00023-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3f9d61cfe43a10e2a1ec7c0c5401432a515af27b --- /dev/null +++ b/model-00023-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e865442f2000f0355e9ecd79e2ad6a32b58a04e809cb0fb166841fd382ac019 +size 5368822056 diff --git a/model-00024-of-00049.safetensors b/model-00024-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..72d637f5fc841c8e18ff8c501f507aefcbbd9b46 --- /dev/null +++ b/model-00024-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0e3358e4e85bca53fee33307dcbefa3431c08ebac41c2cdd457070c81ce902 +size 5366502048 diff --git a/model-00025-of-00049.safetensors b/model-00025-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dd5fa6d28ff416e41933cf2c0fc95e1a04e2061d --- /dev/null +++ b/model-00025-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f239c8e133bbb7edfaa9e1371850dc4656f452e9cbe394546c40ea3cd776c10c +size 5363660760 diff --git a/model-00026-of-00049.safetensors b/model-00026-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ff5e8b69a1ef9434dd9f0c579703f9e20a9f953 --- /dev/null +++ b/model-00026-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e3362616fd4cf0d60857992e0de3f466a6a2ac3f77c8e4526087a31eb4f8e88 +size 5365125752 diff --git a/model-00027-of-00049.safetensors b/model-00027-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f616fb09c3b603c2395eaff63afee779c017dd72 --- /dev/null +++ b/model-00027-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e441f8cd63a66d5fc8480b6f995d9d3a36c2a05202ede3bce1d797dbc91ebf9 +size 5366502320 diff --git a/model-00028-of-00049.safetensors b/model-00028-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..272b912db5b76363d50567b82125d0ddade90552 --- /dev/null +++ b/model-00028-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d1f8acaf385d98669064411908b8fd77e1c7f4e41dd4bb9432b031ee903d1e5 +size 5368821872 diff --git a/model-00029-of-00049.safetensors b/model-00029-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c6b1f48b5132c3996594b0131457ed2e0a849f2 --- /dev/null +++ b/model-00029-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f9903e12daf98957260e1bb4fcdf6bc49530b224231fb53266db877c6e3c99 +size 5366502224 diff --git a/model-00030-of-00049.safetensors b/model-00030-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8180c47b1b3b60c168d8bc904f6b5bf0e8bd338d --- /dev/null +++ b/model-00030-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ec7c8403ed2b87b440f3c4217514f467d29a237bfecf072f602f04a47af771 +size 5363660576 diff --git a/model-00031-of-00049.safetensors b/model-00031-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0d05d019e8511f73e465839f1627d338b373ebae --- /dev/null +++ b/model-00031-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8a3627ed197c2d8fecc2c7ccea89aa70e0e8cbc17d348581848afea63c5ce05 +size 5365125936 diff --git a/model-00032-of-00049.safetensors b/model-00032-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b9ed8ba01d843e06175a8be5789db8085dec2db --- /dev/null +++ b/model-00032-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9767093dcfce75ae070e9c53fb86e26c26081572b545592d83ddb513df8d120a +size 5363660816 diff --git a/model-00033-of-00049.safetensors b/model-00033-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..142e6574d1778878df3b24e1762675c0b9d5cb4b --- /dev/null +++ b/model-00033-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e40ce53df9f62a5b10ad88eea88e9ca0a1065219122c46bfd4766f26b056b94b +size 5365125696 diff --git a/model-00034-of-00049.safetensors b/model-00034-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb408fa03eed96e573672436891760a5712ba4d9 --- /dev/null +++ b/model-00034-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:113cf9cb316f5f19a1547b4ea432f2a565970594daa91f01e8743405a2db4bb4 +size 5366502320 diff --git a/model-00035-of-00049.safetensors b/model-00035-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06d0f716a386bd396d36f6f2f2c3426c17fed4f1 --- /dev/null +++ b/model-00035-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8186dad1ce71be457babe70d2fe5e9b272502524ba09052c212e43c05fc67f32 +size 5363660392 diff --git a/model-00036-of-00049.safetensors b/model-00036-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b549f2c4c5a71f9fce6a661806884f83862ffedc --- /dev/null +++ b/model-00036-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:173ca0ddaca515146fda7e731ff3c4c801c6b04ff6dfedd4428cdce2eec1cbac +size 5365126120 diff --git a/model-00037-of-00049.safetensors b/model-00037-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8aadc4634526f70d5d9ec89595531ea2c35a761c --- /dev/null +++ b/model-00037-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e71276d6b90ba26bb28b7aa5dc25a471a209e9e2e4cd80a4069ef60417257273 +size 5363660632 diff --git a/model-00038-of-00049.safetensors b/model-00038-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c60fbbfbd1d48735ba71c2806e1a3b7b481f1872 --- /dev/null +++ b/model-00038-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:413cab7177c6a3b0c4631a35982d2e36a844559395d9b9aa1eb5cd9397c38828 +size 5365125888 diff --git a/model-00039-of-00049.safetensors b/model-00039-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a04f13f46ae13300c320bea3d2ee584cb0d71d6c --- /dev/null +++ b/model-00039-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09794ac38b513bd48b4e853c307245f8de4a5aa0bfee6784738e58d6df302d8 +size 5365726152 diff --git a/model-00040-of-00049.safetensors b/model-00040-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..41a70d9f5a45772c8d5690010422ce0ca70e36b1 --- /dev/null +++ b/model-00040-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55128ff66a498b94f5850e4a0b112cfc9ac60c976e3053e4f66e1ba268a66393 +size 5364436416 diff --git a/model-00041-of-00049.safetensors b/model-00041-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b941b94fcda41bd33760f1f54d5e7bb3357441c --- /dev/null +++ b/model-00041-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbfddc7d46c3ca9f5f67eda220cf0a05bd9d9d0349bb1dd77c6e20ae247a5ac6 +size 5365126264 diff --git a/model-00042-of-00049.safetensors b/model-00042-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..36622d3578b958e00f33f9aa8fb18e45aaa510ea --- /dev/null +++ b/model-00042-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96616a1badcefdede0289e27ca28ca6aa81e831cf35f980bdb0a165d7deac1be +size 5363660440 diff --git a/model-00043-of-00049.safetensors b/model-00043-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90409b327c274530ef1544db2fe5f1aa49766fed --- /dev/null +++ b/model-00043-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d26a2907ef1b4e604b9cbccececf3ea5ef8fb93058e8b65dbf0937576351605d +size 5365126072 diff --git a/model-00044-of-00049.safetensors b/model-00044-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d1b3dcf3d842717c7314ca62c03215ab11fa2b53 --- /dev/null +++ b/model-00044-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddbd9479642831e4e35ee8a92dbbeb4de68b9a7fde31e182a6afa70d1a55c5f9 +size 5363660680 diff --git a/model-00045-of-00049.safetensors b/model-00045-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..73e5448748e9068c070b5ade2b25df9df0ffb23b --- /dev/null +++ b/model-00045-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07eeec9eaa95d00289a62f1b20e3f5108f5e97fcc99ab6de6130c50e6f3f4fe0 +size 5366501880 diff --git a/model-00046-of-00049.safetensors b/model-00046-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64e54149dcf65b08924dbf0233a3a594fe9f26a7 --- /dev/null +++ b/model-00046-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3fb7eac31d5c87d3818138a78217d60bd3043a446788681c950b96fa9b4058 +size 5365126352 diff --git a/model-00047-of-00049.safetensors b/model-00047-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a48f764d8cb5b499158f433aa77853abd757b148 --- /dev/null +++ b/model-00047-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a87ff34f73f943ff9e579bb3068b3cd28fbc9ed03bf2143e5ff6e8f393fb42 +size 5363660176 diff --git a/model-00048-of-00049.safetensors b/model-00048-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8972ee57784158ce9d51fcbe7f38d51a190e34c8 --- /dev/null +++ b/model-00048-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f038ebada43dc34672e6b730089c3e927b223db7e31393a404db62a153684e53 +size 4744680488 diff --git a/model-00049-of-00049.safetensors b/model-00049-of-00049.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..703d5e333d0082abb4f047a8435ab69d5da6fadc --- /dev/null +++ b/model-00049-of-00049.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:374da1491bc7584a0f01981fdbb239c7d356f1f10be9205e961a00aaa36d8641 +size 3806343464 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..bbda9d9998c3007204a4554994116f8d12975082 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32bdb6f8ab1e043feb146a99abd83d2f1259010d95bba7b51166fde644300da8 +size 10533852 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..c7edb3c9544185418004c88e219aae5cf34eedfa --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cfe2c099a7702a0921abc315ee039deb51e4a34b4818fc509bd27fa3dc4acc1 +size 20217541 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0891a18eef6fc3d26dd2e87796ed39c7f91e3a77 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "backend": "tokenizers", + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>" + ], + "is_local": true, + "local_files_only": false, + "model_max_length": 1048576, + "model_specific_special_tokens": {}, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "TokenizersBackend" +}