diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ 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 +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..2ab98ef068d62829d17c5ade1827b9f013fa2bbf --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,86 @@ +[gMASK] +{%- if tools -%} +<|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 %} +{{ tool | tojson(ensure_ascii=False) }} +{% 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 }} + {%- 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 reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%} +{{ '' + reasoning_content.strip() + ''}} +{%- 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 m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '' }} +{{- m.content }} +{{- '' }} +{%- else -%} +<|observation|>{% for tr in m.content %} +{{ tr.output if tr.output is defined else tr }}{% endfor -%} +{% 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 -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5228d5805664fd337a31fbba683dc963049149ee --- /dev/null +++ b/config.json @@ -0,0 +1,268 @@ +{ + "vocab_size": 154880, + "max_position_embeddings": 202752, + "hidden_size": 6144, + "intermediate_size": 12288, + "num_hidden_layers": 78, + "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" + ], + "moe_intermediate_size": 2048, + "num_attention_heads": 64, + "n_shared_experts": 1, + "n_routed_experts": 256, + "routed_scaling_factor": 2.5, + "kv_lora_rank": 512, + "q_lora_rank": 2048, + "qk_rope_head_dim": 64, + "v_head_dim": 256, + "qk_nope_head_dim": 192, + "qk_head_dim": 256, + "head_dim": 64, + "n_group": 1, + "topk_group": 1, + "num_experts_per_tok": 8, + "norm_topk_prob": true, + "rope_interleave": true, + "num_key_value_heads": 64, + "hidden_act": "silu", + "initializer_range": 0.02, + "index_topk": 2048, + "rms_norm_eps": 1e-05, + "use_cache": true, + "attention_bias": false, + "attention_dropout": 0.0, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "pad_token_id": 154820, + "bos_token_id": 0, + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "tie_word_embeddings": false, + "return_dict": true, + "output_hidden_states": false, + "dtype": "bfloat16", + "chunk_size_feed_forward": 0, + "is_encoder_decoder": false, + "architectures": [ + "GlmMoeDsaForCausalLM" + ], + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "problem_type": null, + "_name_or_path": "zai-org/GLM-5", + "transformers_version": "5.2.0.dev0", + "ep_size": 1, + "first_k_dense_replace": 3, + "index_head_dim": 128, + "index_n_heads": 32, + "indexer_rope_interleave": true, + "moe_layer_freq": 1, + "model_type": "glm_moe_dsa", + "num_nextn_predict_layers": 1, + "pretraining_tp": 1, + "scoring_func": "sigmoid", + "topk_method": "noaux_tc", + "output_attentions": false, + "quantization_config": { + "config_groups": { + "group_0": { + "input_activations": { + "dynamic": false, + "num_bits": 4, + "type": "float", + "group_size": 16 + }, + "weights": { + "dynamic": false, + "num_bits": 4, + "type": "float", + "group_size": 16 + }, + "targets": [ + "Linear" + ] + } + }, + "ignore": [ + "lm_head", + "model.layers.0.self_attn*", + "model.layers.1.self_attn*", + "model.layers.10.self_attn*", + "model.layers.11.self_attn*", + "model.layers.12.self_attn*", + "model.layers.13.self_attn*", + "model.layers.14.self_attn*", + "model.layers.15.self_attn*", + "model.layers.16.self_attn*", + "model.layers.17.self_attn*", + "model.layers.18.self_attn*", + "model.layers.19.self_attn*", + "model.layers.2.self_attn*", + "model.layers.20.self_attn*", + "model.layers.21.self_attn*", + "model.layers.22.self_attn*", + "model.layers.23.self_attn*", + "model.layers.24.self_attn*", + "model.layers.25.self_attn*", + "model.layers.26.self_attn*", + "model.layers.27.self_attn*", + "model.layers.28.self_attn*", + "model.layers.29.self_attn*", + "model.layers.3.self_attn*", + "model.layers.30.self_attn*", + "model.layers.31.self_attn*", + "model.layers.32.self_attn*", + "model.layers.33.self_attn*", + "model.layers.34.self_attn*", + "model.layers.35.self_attn*", + "model.layers.36.self_attn*", + "model.layers.37.self_attn*", + "model.layers.38.self_attn*", + "model.layers.39.self_attn*", + "model.layers.4.self_attn*", + "model.layers.40.self_attn*", + "model.layers.41.self_attn*", + "model.layers.42.self_attn*", + "model.layers.43.self_attn*", + "model.layers.44.self_attn*", + "model.layers.45.self_attn*", + "model.layers.46.self_attn*", + "model.layers.47.self_attn*", + "model.layers.48.self_attn*", + "model.layers.49.self_attn*", + "model.layers.5.self_attn*", + "model.layers.50.self_attn*", + "model.layers.51.self_attn*", + "model.layers.52.self_attn*", + "model.layers.53.self_attn*", + "model.layers.54.self_attn*", + "model.layers.55.self_attn*", + "model.layers.56.self_attn*", + "model.layers.57.self_attn*", + "model.layers.58.self_attn*", + "model.layers.59.self_attn*", + "model.layers.6.self_attn*", + "model.layers.60.self_attn*", + "model.layers.61.self_attn*", + "model.layers.62.self_attn*", + "model.layers.63.self_attn*", + "model.layers.64.self_attn*", + "model.layers.65.self_attn*", + "model.layers.66.self_attn*", + "model.layers.67.self_attn*", + "model.layers.68.self_attn*", + "model.layers.69.self_attn*", + "model.layers.7.self_attn*", + "model.layers.70.self_attn*", + "model.layers.71.self_attn*", + "model.layers.72.self_attn*", + "model.layers.73.self_attn*", + "model.layers.74.self_attn*", + "model.layers.75.self_attn*", + "model.layers.76.self_attn*", + "model.layers.77.self_attn*", + "model.layers.8.self_attn*", + "model.layers.9.self_attn*" + ], + "quant_algo": "NVFP4", + "kv_cache_scheme": { + "dynamic": false, + "num_bits": 8, + "type": "float" + }, + "producer": { + "name": "modelopt", + "version": "0.39.0.dev290+gf9d9a71de.d20260214" + }, + "quant_method": "modelopt" + } +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ea7c83eafc45ce62fe0c934f5ca913022b6c9a8d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,74 @@ +{ + "max_length": null, + "max_new_tokens": null, + "min_length": null, + "min_new_tokens": null, + "early_stopping": null, + "max_time": null, + "stop_strings": null, + "do_sample": null, + "num_beams": null, + "use_cache": true, + "cache_implementation": null, + "cache_config": null, + "temperature": null, + "top_k": null, + "top_p": null, + "min_p": null, + "top_h": null, + "typical_p": null, + "epsilon_cutoff": null, + "eta_cutoff": null, + "repetition_penalty": null, + "encoder_repetition_penalty": null, + "length_penalty": null, + "no_repeat_ngram_size": null, + "bad_words_ids": null, + "renormalize_logits": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "remove_invalid_values": null, + "exponential_decay_length_penalty": null, + "suppress_tokens": null, + "begin_suppress_tokens": null, + "sequence_bias": null, + "token_healing": null, + "guidance_scale": null, + "watermarking_config": null, + "num_return_sequences": null, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": null, + "output_logits": null, + "return_dict_in_generate": null, + "pad_token_id": 154820, + "bos_token_id": 0, + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "encoder_no_repeat_ngram_size": null, + "decoder_start_token_id": null, + "is_assistant": null, + "num_assistant_tokens": null, + "num_assistant_tokens_schedule": null, + "assistant_confidence_threshold": null, + "prompt_lookup_num_tokens": null, + "max_matching_ngram_size": null, + "assistant_early_exit": null, + "assistant_lookbehind": null, + "target_lookbehind": null, + "compile_config": null, + "disable_compile": null, + "low_memory": null, + "penalty_alpha": null, + "dola_layers": null, + "diversity_penalty": null, + "num_beam_groups": null, + "constraints": null, + "force_words_ids": null, + "prefill_chunk_size": null, + "_from_model_config": true, + "transformers_version": "5.2.0.dev0" +} \ No newline at end of file diff --git a/hf_quant_config.json b/hf_quant_config.json new file mode 100644 index 0000000000000000000000000000000000000000..269e0194c9aa43f31bc7784f5d63b32362a4e298 --- /dev/null +++ b/hf_quant_config.json @@ -0,0 +1,113 @@ +{ + "config_groups": { + "group_0": { + "input_activations": { + "dynamic": false, + "num_bits": 4, + "type": "float", + "group_size": 16 + }, + "weights": { + "dynamic": false, + "num_bits": 4, + "type": "float", + "group_size": 16 + }, + "targets": [ + "Linear" + ] + } + }, + "ignore": [ + "lm_head", + "model.layers.0.self_attn*", + "model.layers.1.self_attn*", + "model.layers.10.self_attn*", + "model.layers.11.self_attn*", + "model.layers.12.self_attn*", + "model.layers.13.self_attn*", + "model.layers.14.self_attn*", + "model.layers.15.self_attn*", + "model.layers.16.self_attn*", + "model.layers.17.self_attn*", + "model.layers.18.self_attn*", + "model.layers.19.self_attn*", + "model.layers.2.self_attn*", + "model.layers.20.self_attn*", + "model.layers.21.self_attn*", + "model.layers.22.self_attn*", + "model.layers.23.self_attn*", + "model.layers.24.self_attn*", + "model.layers.25.self_attn*", + "model.layers.26.self_attn*", + "model.layers.27.self_attn*", + "model.layers.28.self_attn*", + "model.layers.29.self_attn*", + "model.layers.3.self_attn*", + "model.layers.30.self_attn*", + "model.layers.31.self_attn*", + "model.layers.32.self_attn*", + "model.layers.33.self_attn*", + "model.layers.34.self_attn*", + "model.layers.35.self_attn*", + "model.layers.36.self_attn*", + "model.layers.37.self_attn*", + "model.layers.38.self_attn*", + "model.layers.39.self_attn*", + "model.layers.4.self_attn*", + "model.layers.40.self_attn*", + "model.layers.41.self_attn*", + "model.layers.42.self_attn*", + "model.layers.43.self_attn*", + "model.layers.44.self_attn*", + "model.layers.45.self_attn*", + "model.layers.46.self_attn*", + "model.layers.47.self_attn*", + "model.layers.48.self_attn*", + "model.layers.49.self_attn*", + "model.layers.5.self_attn*", + "model.layers.50.self_attn*", + "model.layers.51.self_attn*", + "model.layers.52.self_attn*", + "model.layers.53.self_attn*", + "model.layers.54.self_attn*", + "model.layers.55.self_attn*", + "model.layers.56.self_attn*", + "model.layers.57.self_attn*", + "model.layers.58.self_attn*", + "model.layers.59.self_attn*", + "model.layers.6.self_attn*", + "model.layers.60.self_attn*", + "model.layers.61.self_attn*", + "model.layers.62.self_attn*", + "model.layers.63.self_attn*", + "model.layers.64.self_attn*", + "model.layers.65.self_attn*", + "model.layers.66.self_attn*", + "model.layers.67.self_attn*", + "model.layers.68.self_attn*", + "model.layers.69.self_attn*", + "model.layers.7.self_attn*", + "model.layers.70.self_attn*", + "model.layers.71.self_attn*", + "model.layers.72.self_attn*", + "model.layers.73.self_attn*", + "model.layers.74.self_attn*", + "model.layers.75.self_attn*", + "model.layers.76.self_attn*", + "model.layers.77.self_attn*", + "model.layers.8.self_attn*", + "model.layers.9.self_attn*" + ], + "quant_algo": "NVFP4", + "kv_cache_scheme": { + "dynamic": false, + "num_bits": 8, + "type": "float" + }, + "producer": { + "name": "modelopt", + "version": "0.39.0.dev290+gf9d9a71de.d20260214" + }, + "quant_method": "modelopt" +} \ No newline at end of file diff --git a/model-00006-of-00082.safetensors b/model-00006-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..308681ed043d62638b206b4cb41217b478ee6fed --- /dev/null +++ b/model-00006-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cf0d4bcd9dbfce7ec8c3e5d66555e14af08b22c0db838b4c7390eb65a8082d0 +size 5370444876 diff --git a/model-00008-of-00082.safetensors b/model-00008-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4b7d643e60e9257d0f61563ed4b88e4ca6e33d53 --- /dev/null +++ b/model-00008-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1ae9966ce076bc7df12bda8e0eb7e55b6fa00534b5c5867967463c6f9bf476 +size 5370445148 diff --git a/model-00011-of-00082.safetensors b/model-00011-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d770e4f834672a51837021a4886fc4ff0d256e5 --- /dev/null +++ b/model-00011-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cca2a6f13e5a665fb02300f4642c86bd80aa78a6af36a6f92637ecc4ab9677a +size 5373591688 diff --git a/model-00014-of-00082.safetensors b/model-00014-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b97ec78fb243ddc8a3c85bd499e5edc65bb20157 --- /dev/null +++ b/model-00014-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:813570148a55a9d8ca3ec73b750a8af570324baa4f1edf37515a530da35c812a +size 5370447300 diff --git a/model-00016-of-00082.safetensors b/model-00016-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ea56eff38f7949174129574e0d01dfb716d9010 --- /dev/null +++ b/model-00016-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e67135f17a9856cc541d9f72f829a794ed4d37f81d51ae64886bda80702eccd9 +size 5370447356 diff --git a/model-00019-of-00082.safetensors b/model-00019-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b3b28d95f2c0a26b8adef2216c8dbf538db89d4 --- /dev/null +++ b/model-00019-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a399d0b87c4f5c7ff8cf3de93816cb0c09c58451390d0cda8a39f3d1f93063 +size 5370447172 diff --git a/model-00021-of-00082.safetensors b/model-00021-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39a4407af3fad979d56db60c51635a3039956367 --- /dev/null +++ b/model-00021-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35dd921d300af6d06d2294f6a00e38846180b45d62042569a91e324cd8c8cec6 +size 5370447012 diff --git a/model-00022-of-00082.safetensors b/model-00022-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc2d74bf69a7b87b0e741a5a5054edfa629fa8ce --- /dev/null +++ b/model-00022-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a45c0c9edc6a6703b03a7292a441fefeb7b89d36bc3c00500df96a161d41353f +size 5370447164 diff --git a/model-00023-of-00082.safetensors b/model-00023-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5b302fd90c450aafab0e4e5cc9f439cd5c75022 --- /dev/null +++ b/model-00023-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70abd450ad1bdd6f8ed13dbb34916a89d20992f06f1ab5c80e156a2d59a70223 +size 5369540220 diff --git a/model-00025-of-00082.safetensors b/model-00025-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01b76900e19abe1bf328aa93371eecee698687b7 --- /dev/null +++ b/model-00025-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a5b0fac18528bc126ba02183140e7ccf212182b60de754cabad1a397adc3893 +size 5370447388 diff --git a/model-00026-of-00082.safetensors b/model-00026-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee80e2ba2eb5da4a24dc9b25cf93cf34067f6a82 --- /dev/null +++ b/model-00026-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80a0e0f3258aad710f03477858d6b4453c90dce2205b8786a4dbe007ee18de3a +size 5370447300 diff --git a/model-00027-of-00082.safetensors b/model-00027-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..48a2895c0a21b07605174884f5deb2fe7b48f4f3 --- /dev/null +++ b/model-00027-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff6cdb0c15b83ecd70dfbfecd4766d5abb210bc7cb1699d8baf697c4fc2adef +size 5370447324 diff --git a/model-00030-of-00082.safetensors b/model-00030-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2dd2a59e988aa5834414352525dbdb738b48b975 --- /dev/null +++ b/model-00030-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d144ff87884f1e07872cf64e484a238d450880a0d62ca34e8cc7195b2c7d0e0 +size 5370447364 diff --git a/model-00031-of-00082.safetensors b/model-00031-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..760cae0366cbbe632211b4423c195a214979db08 --- /dev/null +++ b/model-00031-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93747f976cd0025158de3d433d721e15e6189b8200b9df2c9dbf3d5815e0b84b +size 5370447540 diff --git a/model-00034-of-00082.safetensors b/model-00034-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21c6e8696737980f5f6eda09a8267a2000cbf6bf --- /dev/null +++ b/model-00034-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb4aa2bbd6b4db60f868a0c539d39625326aff603fb89cb149ac2675188fe7a +size 5370446980 diff --git a/model-00035-of-00082.safetensors b/model-00035-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..79b41514717b532a826dca8f83ff7c8cf853ceec --- /dev/null +++ b/model-00035-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee382e72a8d58c718a97415aa1d4aa77c058f4d053e632f0c9b7e4ed0866b30 +size 5370447156 diff --git a/model-00036-of-00082.safetensors b/model-00036-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1dc6f62a48b5dd345c0f3a730164fe86d0114c0e --- /dev/null +++ b/model-00036-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:446bb068a54ad9559690b5e0e518e86e879c15451fd90b9ac5142ab7e55ceb91 +size 5494054480 diff --git a/model-00037-of-00082.safetensors b/model-00037-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91f74c755cf6b1fdd2c6da62fa449dd225df0cc5 --- /dev/null +++ b/model-00037-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5c10072e987ac18e15dffd3a490cca0257d4a7f86b6fa902d6c0a66eb38019 +size 5369121324 diff --git a/model-00038-of-00082.safetensors b/model-00038-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e5d791c8426b24effdbbb53068067022c86e0f5 --- /dev/null +++ b/model-00038-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf6641f3ad26229e26f7bd58a944ba28c15d5fb960cb9a4bb694ee1a3e44c90b +size 5370447476 diff --git a/model-00039-of-00082.safetensors b/model-00039-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3cf7d7b5c667bdf69370a6027a11475d0c6f0bfd --- /dev/null +++ b/model-00039-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d734199f744ebb997b829dbe98a13ab2794738459cbb984ff8f9d4c9f7cb90b1 +size 5370447332 diff --git a/model-00042-of-00082.safetensors b/model-00042-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78c3f712b7be41b78d01eb0450faf9b720790e6a --- /dev/null +++ b/model-00042-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60015ca9b3179ef34f33a9082149e2ebe523557622ded864a81f6bb829ed8aac +size 5370447356 diff --git a/model-00044-of-00082.safetensors b/model-00044-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8d1d6507ff562169ba70c45607a979daa000e941 --- /dev/null +++ b/model-00044-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f2ffc115d7c9a4765efcd80291187d1cfa240335be662d14b725c79573b83ef +size 5370447460 diff --git a/model-00046-of-00082.safetensors b/model-00046-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a7ec73455ef64493eb15178521fa416b9d142641 --- /dev/null +++ b/model-00046-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9024a5d81487f80da262b837956c7122330645a11b86d185e8be56245ac5e6b +size 5370447020 diff --git a/model-00048-of-00082.safetensors b/model-00048-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c42ff35be3122d5fa5e593cc84d1e97e8d680c40 --- /dev/null +++ b/model-00048-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5ded23696367b82e9a674fab7824d72306da787f98645af00aa6b17811354b1 +size 5370447060 diff --git a/model-00049-of-00082.safetensors b/model-00049-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ffe976e3e774115229f8a144d45f600e83fadff --- /dev/null +++ b/model-00049-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ac7f19901d6663f5b8c2484286d4a988dae15be92c5a625a7b445e862c3a5ff +size 5370447164 diff --git a/model-00050-of-00082.safetensors b/model-00050-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8add75258c6244a5fd3ec17b7c6a3ce3fb533b66 --- /dev/null +++ b/model-00050-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b908325b29e44afcab5f8cf228108da0457d8901a96eec89e0947157c9ce61c +size 5369253496 diff --git a/model-00051-of-00082.safetensors b/model-00051-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5d9e78f6194aa0de9326aec481973dcbc2ce65af --- /dev/null +++ b/model-00051-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad40fada34a84990e74430c02d54eed57934419aeedc2421bf848dcf0e755a85 +size 5373591688 diff --git a/model-00052-of-00082.safetensors b/model-00052-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7a072e2dfb6e2ba23c6deada916f83a4eabf60d --- /dev/null +++ b/model-00052-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c38718568ebb086e98351234d050b5974557496b035f0150fae7080dc1229ae8 +size 5370447356 diff --git a/model-00053-of-00082.safetensors b/model-00053-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4522ee810d85b6412b9b15ea2a4948edaf75bf73 --- /dev/null +++ b/model-00053-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df5ca7217f0879dfb56770dbb9bdf9c11733fe3214928320c03ec4a1be369eb +size 5370447316 diff --git a/model-00054-of-00082.safetensors b/model-00054-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a6c3f8ce243f0fd649bdc617fb16df29eff8e01 --- /dev/null +++ b/model-00054-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f16bcc75e5ddfde30b64bec3a98e17f322a5b2fcf6a6ff6c5e60c2a2971b25 +size 5370447300 diff --git a/model-00056-of-00082.safetensors b/model-00056-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..57cc9ed03c10306be1bfc5b046f465e765a110c6 --- /dev/null +++ b/model-00056-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01c2c139ad7da33b9532d1560ffd5446158bc02032d56c26531e7722bc655576 +size 5370447356 diff --git a/model-00057-of-00082.safetensors b/model-00057-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b21fbfe4ee4bd3af2e90aebdb4fb99d242f4a939 --- /dev/null +++ b/model-00057-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8defeb5f87ad1d08c1cf10640169ca5ee05e5e05f8567b53264d679938843824 +size 5370447412 diff --git a/model-00058-of-00082.safetensors b/model-00058-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..15f68ebac23b95363b2bb296ade5cac744b5a294 --- /dev/null +++ b/model-00058-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bcd9e6b06be11a6b38f809ac54093145418286859389c1f1589cf6abbec19b9 +size 5370447540 diff --git a/model-00059-of-00082.safetensors b/model-00059-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63e6f6e7f1af2ce8e67872040409d94a551222da --- /dev/null +++ b/model-00059-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8386711a9f257018c0b0cacf06172563709123781641811f466ff72795c7df34 +size 5370447172 diff --git a/model-00060-of-00082.safetensors b/model-00060-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a74d741b3bd16b365460b90b1c88aa716a66eaa8 --- /dev/null +++ b/model-00060-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da7dddc1577a70a0b52b1d2729ea84ccd468efc5bd739dc2611fd553fce4cb2c +size 5370446980 diff --git a/model-00062-of-00082.safetensors b/model-00062-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f2b38c44c61c88cdafea957caedc8b0625c1cd54 --- /dev/null +++ b/model-00062-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b38a81ebf36df5726c64d16b57e9af92357271feabc64f28bfdcd81fc128926f +size 5370447164 diff --git a/model-00064-of-00082.safetensors b/model-00064-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..205eaf9448be0e34fb92a95d4458e2c5490f8462 --- /dev/null +++ b/model-00064-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a76dd5a6d6236474e4900118d2426376dc37428c02a996c77de216f2771e5ae4 +size 5373305276 diff --git a/model-00065-of-00082.safetensors b/model-00065-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5905c19f7814dcec185b363ae057ab263bf25a1 --- /dev/null +++ b/model-00065-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17c4e89b00b8144532cb4505ff86ed04f7756a41f2960a113a753a473cc2b0e7 +size 5370447388 diff --git a/model-00066-of-00082.safetensors b/model-00066-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dcc83686b2e7bfa882befba8d04092aba5ea8248 --- /dev/null +++ b/model-00066-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a3893ed239fded2810effe741c3744f8eafd44513018cb580cb2c55f908878 +size 5370447300 diff --git a/model-00070-of-00082.safetensors b/model-00070-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eec61e409e5581d8e5d94990493a82096fd4bfb9 --- /dev/null +++ b/model-00070-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f21e143a3cd6004fc1164fac0430b5011445a7fe1da9496cfa29efd3deddb53d +size 5370447364 diff --git a/model-00071-of-00082.safetensors b/model-00071-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f93bf0d160e7aeb8759e9a9df55afc55a085197 --- /dev/null +++ b/model-00071-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09eb81430c07121a40bb7361a8f4ed0c940179b51f2d59f63d13e90296656bdd +size 5370447540 diff --git a/model-00073-of-00082.safetensors b/model-00073-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f769da3f6301415e19f68ac4d559d37573e13f1a --- /dev/null +++ b/model-00073-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0234a6d4c9c0ad9b45a33e8a365f8ef4ff98039fb62efb94cc73705e82e03f3 +size 5370446980 diff --git a/model-00076-of-00082.safetensors b/model-00076-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf2aae5d87b73cd3c609279c8f4b057c3b8be686 --- /dev/null +++ b/model-00076-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e51da96c5b0f3f75cab1a9d4d99699880bbcf76f0b469fdc327f08d74716658 +size 5494054480 diff --git a/model-00078-of-00082.safetensors b/model-00078-of-00082.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a432dd66aa8e13ee7a19a2f0e1299ea22f573ed --- /dev/null +++ b/model-00078-of-00082.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:679fa7e23699e7c2b13db531668f9af89fef5a8c738b1566a38d55e0123f05d9 +size 5370447476 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..aba40197a4cdb5607f4ab7a05fb0a4ee8054fd6d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d +size 20217442 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1723f7d90e3fb497303ec7b18f88cf5d05928f37 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,33 @@ +{ + "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, + "model_max_length": 202752, + "model_specific_special_tokens": {}, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "TokenizersBackend" +}