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/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..8f691443fa56e0aba0f42f63df89f94d2242647b --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: zai-org/GLM-5.2 +base_model_relation: quantized +license: mit +library_name: transformers +pipeline_tag: text-generation +tags: + - nvfp4 + - fp4 + - quantization + - modelopt + - tensorrt + - moe + - glm + - sglang +--- + +# GLM-5.2-NVFP4 + +**NVFP4 (4-bit) quantization of [zai-org/GLM-5.2](https://huggingface.co/zai-org/GLM-5.2)**, produced with +[NVIDIA TensorRT Model Optimizer](https://github.com/NVIDIA/Model-Optimizer) 0.44.0. The MoE expert FFNs +(routed + shared) are quantized to NVFP4; attention (MLA + the DeepSeek-style DSA lightning indexer), +the router, and the LM head are kept in BF16. This shrinks the checkpoint from **1.5 TB → 410 GB (~3.7×)** +while retaining GSM8K accuracy within ~2 points of BF16. + +GLM-5.2 is a `glm_moe_dsa` model: DeepSeek-V3.2-style **MLA attention + DSA sparse-attention indexer**, +with a **256-routed-expert + 1-shared-expert** MoE (8 experts/token), 78 layers, hidden 6144, vocab 154880. + +## Evaluation + +GSM8K, 5-shot, served via SGLang, scored with lm-evaluation-harness (`local-chat-completions`, +`--apply_chat_template`, `max_gen_toks=2048` — the default 256 truncates this reasoning model's chains). + +| GSM8K (1319 q) | flexible-extract | strict-match | checkpoint size | +|---|---|---|---| +| **GLM-5.2-NVFP4 (this model)** | **92.72%** | **92.12%** | 410 GB | +| GLM-5.2 BF16 (reference) | 94.92% | 94.31% | 1507 GB | +| Δ vs BF16 | −2.20 | −2.19 | 3.7× smaller | + +Both rows were measured on the same hardware and harness for an apples-to-apples comparison. + +## Quantization recipe + +- **Format:** NVFP4 (FP4 weights + FP8 block scales), block/group size 16, `modelopt` producer. +- **Quantized:** `mlp.experts.*` (256 routed experts) and `mlp.shared_experts.*`. +- **Kept in BF16 (excluded):** all of `self_attn.*` — MLA projections (q/kv) **and** the DSA indexer — + plus the MoE router (`mlp.gate`) and `lm_head`. The indexer and MLA attention **must** stay BF16: + SGLang's `deepseek_v2` MLA path (used for `glm_moe_dsa`) cannot consume NVFP4 attention weights. +- **KV cache:** not quantized. +- **Calibration:** 512 samples × 2048 tokens from cnn_dailymail + nvidia/OpenCodeReasoning + + nvidia/OpenMathReasoning. + +## Serving (SGLang) + +Requires **SGLang ≥ v0.5.13.post1** (the version that registers `GlmMoeDsaForCausalLM`). + +```bash +docker run --runtime=nvidia --gpus '"device=0,1,2,3"' --ipc=host --shm-size=32g \ + -v /path/to/GLM-5.2-NVFP4:/model -p 30000:30000 \ + lmsysorg/sglang:v0.5.13.post1-cu130 \ + sglang serve --model-path /model --tp 4 \ + --quantization modelopt_fp4 --moe-runner-backend flashinfer_cutlass \ + --context-length 32768 --mem-fraction-static 0.85 \ + --tool-call-parser auto --trust-remote-code --host 0.0.0.0 --port 30000 +``` + +Fits on 4× ≥80 GB GPUs at TP=4 (~110 GB/GPU). Use a generous `max_tokens` at inference — GLM-5.2 is a +reasoning model and its `` chains can be long. + +## Notes + +- Quantized with `nvfp4` + a small `build_quant_cfg` exclusion that keeps `self_attn.*` in BF16 (required + for SGLang's MLA path). Same overall pipeline as our [MiniMax-M3-NVFP4](https://huggingface.co/Mapika/MiniMax-M3-NVFP4). +- License inherited from the base model (MIT, Zhipu AI). 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..f9ae4638d93d61c4dd6d2fa829e8345d700049ce --- /dev/null +++ b/config.json @@ -0,0 +1,331 @@ +{ + "architectures": [ + "GlmMoeDsaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "ep_size": 1, + "first_k_dense_replace": 3, + "head_dim": 192, + "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, + "max_position_embeddings": 1048576, + "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": 256, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 64, + "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, + "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": "5.12.0", + "use_cache": true, + "v_head_dim": 256, + "vocab_size": 154880, + "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", + "producer": { + "name": "modelopt", + "version": "0.44.0" + }, + "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..1bb68282272b21b64e760856d56040d2a4829f8b --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "_from_model_config": true, + "do_sample": true, + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "pad_token_id": 154820, + "temperature": 1.0, + "top_p": 0.95, + "transformers_version": "5.10.0.dev0" +} diff --git a/hf_quant_config.json b/hf_quant_config.json new file mode 100644 index 0000000000000000000000000000000000000000..733ff523e00202b492733b7aa6dc10fd80caf8b5 --- /dev/null +++ b/hf_quant_config.json @@ -0,0 +1,92 @@ +{ + "producer": { + "name": "modelopt", + "version": "0.44.0" + }, + "quantization": { + "quant_algo": "NVFP4", + "kv_cache_quant_algo": null, + "group_size": 16, + "exclude_modules": [ + "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*" + ] + } +} \ No newline at end of file diff --git a/model-00001-of-00045.safetensors b/model-00001-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07f2f13e90ee23b0caf67b1639c30823765905a3 --- /dev/null +++ b/model-00001-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4670a28802c1730862e8c84519c493557687498fedc39fa5d8281f7d7be83b4 +size 9997538680 diff --git a/model-00002-of-00045.safetensors b/model-00002-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c9ac3609ea32cbadf8f5d16d3dc4a72e57aa733a --- /dev/null +++ b/model-00002-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c1e884e0dfe73758f1cbd13d298468ab9881b30a1ff5eb9fa21cf5d60b7515 +size 9995191816 diff --git a/model-00003-of-00045.safetensors b/model-00003-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..438e66772aa75be9c77271c349eb8b54e20b0022 --- /dev/null +++ b/model-00003-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9078d0c0407babbd6dd540e063d816595281274cbf393eebe29056015303f86b +size 10000313896 diff --git a/model-00004-of-00045.safetensors b/model-00004-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0126ad9fcdd272e932d127c105112ca121dc3d2a --- /dev/null +++ b/model-00004-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:733046a21633727dbbabb40614c687159c5c063bad6b613e0a24b4bc2caaf196 +size 9995726000 diff --git a/model-00005-of-00045.safetensors b/model-00005-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ae476d331287064a642df162e4cd874380737a95 --- /dev/null +++ b/model-00005-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbd07a3b820b9a0c28f98d0297c264d25d165443a2634961e7fdb35687712924 +size 9834382056 diff --git a/model-00006-of-00045.safetensors b/model-00006-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a394e105e29f542e3bace480c345a874c8a9f439 --- /dev/null +++ b/model-00006-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ebe95c8cb155f66e899409f86ba60769181827e78d2c9d9f2dd944a0117efc +size 9998329432 diff --git a/model-00007-of-00045.safetensors b/model-00007-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..27a48e62fffdb0589cf14553ed5658051f058c41 --- /dev/null +++ b/model-00007-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e93f1800eb3c9256b8654f6f95870956ea669f16b2ff661bcbee042a850d5cf8 +size 10000319088 diff --git a/model-00008-of-00045.safetensors b/model-00008-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64f30a1a7cbbf395be0bbb7a191a9b81c393025a --- /dev/null +++ b/model-00008-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:234774a5103e3e8e292f6cdc37ba9fd43a6a79b5ba4619e0c611757dd8b010b7 +size 9995731608 diff --git a/model-00009-of-00045.safetensors b/model-00009-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..998e5a56a01f89cd19773da23a2ed44d88987611 --- /dev/null +++ b/model-00009-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be87442a1a0164e7170e5326c76fbc843e1cda2b6d98ffef45eeaa0492364784 +size 9995197440 diff --git a/model-00010-of-00045.safetensors b/model-00010-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..489608a7546f5fd2a35d05d2e1b1a7eb48927d6f --- /dev/null +++ b/model-00010-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a6bf03cc29339b1e502f75035e9612d5bc4389326ed3b66e06500a8a653509 +size 10000319336 diff --git a/model-00011-of-00045.safetensors b/model-00011-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7fbee4b48417cf07e0443b08ceb1b28701730f6f --- /dev/null +++ b/model-00011-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:099f521ee7143c5bf77d3fe3e862f2dc39aa63a7ebf68e958a7815033e4495da +size 9995731296 diff --git a/model-00012-of-00045.safetensors b/model-00012-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ef86e56e7e8a4f801e51a28b2cbfa8623f8c3ad --- /dev/null +++ b/model-00012-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5095c01b0ebf91c3721a59ee74a76decaf526b7463c9bbadc62333fc8dc21231 +size 10000319464 diff --git a/model-00013-of-00045.safetensors b/model-00013-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c0575dfe7d9196d5997349c57615dc13d913ed34 --- /dev/null +++ b/model-00013-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc68c8d27865fd7d61bd7df2439751451c90295634fd91597ec1bdbf5903b4b5 +size 9995197112 diff --git a/model-00014-of-00045.safetensors b/model-00014-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de7d2ee7cd89df1de5256735c80d83231d3add10 --- /dev/null +++ b/model-00014-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75081c59ef0f4ce555f46737a05b6954f0cc6b3565ba58f94ab76d515e83ae26 +size 10000319080 diff --git a/model-00015-of-00045.safetensors b/model-00015-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef0549cc3eddc5bfaa874a078038a7b0f29d4b24 --- /dev/null +++ b/model-00015-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:846b1f4c34eb31e9e117c14827b226b1d1111166eeddaa806ca4a104d59b5718 +size 9995731368 diff --git a/model-00016-of-00045.safetensors b/model-00016-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c4887b686f21f46c565267c19d00ef945837f7ec --- /dev/null +++ b/model-00016-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d076dfc32d359817b7204f60fc4e8621c8af21caf41f5a4ee4294bd53c7c8857 +size 9991291112 diff --git a/model-00017-of-00045.safetensors b/model-00017-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b642cabff56cb3a535df44f79848c84932114282 --- /dev/null +++ b/model-00017-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc7608df6151362e4b9e5d4e3cd66971b1a5c0b9ed0e130b06bd5e99351691a +size 9997146752 diff --git a/model-00020-of-00045.safetensors b/model-00020-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56714791d3f11b33e441c45461ee2a64a32750b9 --- /dev/null +++ b/model-00020-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ecd156e63e00b3cd95647d93ae03a35b7ec211fa1ed3bf784a90a055b0f19d +size 9995197352 diff --git a/model-00021-of-00045.safetensors b/model-00021-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7dd82bd842ec309c51aab30d4e216fbcdbe3150 --- /dev/null +++ b/model-00021-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3aacb01cb4e691c37337a36321e9cc27f6cd2bb30be7c352f1eab96806a4af +size 10000319272 diff --git a/model-00022-of-00045.safetensors b/model-00022-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..002b098be2d92d32321a1ccaaa565f7199df9743 --- /dev/null +++ b/model-00022-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:851591d634eb3ca252565b2717ad4be0f485192a2abc744352cb248dda5ee240 +size 9995731296 diff --git a/model-00023-of-00045.safetensors b/model-00023-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ea5f01a8cfae1ee8bbbf8a30b1d5b75e63c31c0 --- /dev/null +++ b/model-00023-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:167eaeb1bd2eb647cfaa8d6103f0816b6200acbd2eba8914c34d60f692989187 +size 10000319552 diff --git a/model-00024-of-00045.safetensors b/model-00024-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ae32ea9964046799a7a4b9da1be6ec94b2bcb48b --- /dev/null +++ b/model-00024-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe08608dd041c4baaa84223e2b5d61fc2adb513f87b4c04a58f569fd2b652808 +size 9995196960 diff --git a/model-00025-of-00045.safetensors b/model-00025-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..22ef28eb2ea11ccf41e95063551279dd0adf9e0f --- /dev/null +++ b/model-00025-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c973a31e3188faf3cf2e3c356b78f348f2fe990c23784b1a0b082466f4c1f9b +size 9995731384 diff --git a/model-00027-of-00045.safetensors b/model-00027-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e246546c65ac06a79dcc93afd79a0c99cfee7e0d --- /dev/null +++ b/model-00027-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94334b82a784888201d83bbfb5ed7f1fcd9d33fc76408cce7831174f1d7ba06e +size 9995197600 diff --git a/model-00028-of-00045.safetensors b/model-00028-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c529814805ccfe7ca32d0a1ea44e128f662f6ddf --- /dev/null +++ b/model-00028-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81253aa28890aaefd7639909bbb6d94f3c14a2791b342af226e971a2a0626b0a +size 10000319512 diff --git a/model-00029-of-00045.safetensors b/model-00029-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..987ebf3ddf7d8d095318e371c418149715a5ace3 --- /dev/null +++ b/model-00029-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad54fe4396c70dc84153d28b56b60a2c3b21e7aa5f46ce1df859ac89b695d30c +size 9995731312 diff --git a/model-00030-of-00045.safetensors b/model-00030-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf95331c4a9972da8f6f579ff741810d4c55f70e --- /dev/null +++ b/model-00030-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e55d2350cd5a7a51fba98214cce1636e24e43ddbe1348c435dc9499e10e9b94 +size 10000319472 diff --git a/model-00031-of-00045.safetensors b/model-00031-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..846d0fc24720134d7790926996dad31bd3a229ba --- /dev/null +++ b/model-00031-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68e8d152c11a0163e9ab8105e53961ad8a1fb980af6a97e0c553f4218b42b78d +size 9995197272 diff --git a/model-00032-of-00045.safetensors b/model-00032-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5eb569ade4775338372de11acc8f4ecdd2c3c28b --- /dev/null +++ b/model-00032-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1081343006c2b5b85b7b26d0f432f9e1ff12a6c26ca7616bb26a8beb3446b3cb +size 9995731488 diff --git a/model-00033-of-00045.safetensors b/model-00033-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fecaec74b2cf8b4af6afbd33d9809e635f2bccda --- /dev/null +++ b/model-00033-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2363797c71cf1d00e6bc48278934884589daf65f56df1f8ef808c17a672111fa +size 10000318992 diff --git a/model-00034-of-00045.safetensors b/model-00034-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..22c4926471e94dd8b8d628e9fa276827f9c35745 --- /dev/null +++ b/model-00034-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc224e0b881b87d51381bee58a1017c2f66489e77ddbbb68ab83b0df63636565 +size 9829796552 diff --git a/model-00035-of-00045.safetensors b/model-00035-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cac69adc9d48c5585aa7943651f8d1872175b679 --- /dev/null +++ b/model-00035-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c23451e927415ff61d5e741b4070ad10fe0d7fda230f162ecdc7ff593c37bafa +size 9995838752 diff --git a/model-00036-of-00045.safetensors b/model-00036-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef15cb21a52ed8287cea59fa39922aa4f2e4e07b --- /dev/null +++ b/model-00036-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36a2a6c09dd1a387d07e8c866b0414384455333dc9ef467b88291f755837cd52 +size 9995731392 diff --git a/model-00037-of-00045.safetensors b/model-00037-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a04234f356b89adee0c0bf5d7325656c86105bbb --- /dev/null +++ b/model-00037-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0c22ee0ce5801f91330411ed4a44fc5835a048959356f4ec9213a67e91e81c0 +size 10000319320 diff --git a/model-00038-of-00045.safetensors b/model-00038-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b07b79aa48c17d794bb38f6a18c98a034f2cb92a --- /dev/null +++ b/model-00038-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80643af29e8c7b60acabdf6103823a98cce7eb18ef86b2b9e751286d64f19538 +size 9995197424 diff --git a/model-00039-of-00045.safetensors b/model-00039-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9adb198ff38193b3b932db23f6e0bfe992810dea --- /dev/null +++ b/model-00039-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:425282631a855611577e6c3c389d3801411615cbfd65305791f94dee3d93c595 +size 9995731640 diff --git a/model-00040-of-00045.safetensors b/model-00040-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd90f9496c15423838219e0a3515d39de2410a82 --- /dev/null +++ b/model-00040-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86e8f76e41eb7abf52d75d22662bc0c78fd50affe4fb4f0fa4cb65e21d51009 +size 10000318992 diff --git a/model-00041-of-00045.safetensors b/model-00041-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53a6da997e86eca508f88f70bf3be79e0d8fafc9 --- /dev/null +++ b/model-00041-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36653b2bc562d89c6f26911559c409a65e89c0e5153c25ac043124f02d9dc7ce +size 9995731776 diff --git a/model-00042-of-00045.safetensors b/model-00042-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..74e22795ce8952adb96010ca42f53f3dd7601550 --- /dev/null +++ b/model-00042-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e12271030ae2d83c4e4c0e773efc549d61fb68c8c29375d9877b47ab763243 +size 9999784792 diff --git a/model-00043-of-00045.safetensors b/model-00043-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fbfab1ffef4b445823ec04f040ad392e95fee4a5 --- /dev/null +++ b/model-00043-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd5b0b527522be88fde5d3362c530aa31fa5e2074cef9de827342dad64affbb6 +size 9995731384 diff --git a/model-00044-of-00045.safetensors b/model-00044-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea0b4ccdb8dcc66bac2a87ee000091ab4e8275fb --- /dev/null +++ b/model-00044-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5377147c9bf6983940cc98e60b9b7e56981aedef2b6fb85e2086c1b376436b8a +size 8412825168 diff --git a/model-00045-of-00045.safetensors b/model-00045-of-00045.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c740df24bb46398fbe622fec0b4cff399c8ce36 --- /dev/null +++ b/model-00045-of-00045.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd26ce41a46adc0d601ad37961fd7ef5aa2c7028a5f590931e0fdd1b7dbb6ac7 +size 1903165568 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..c7bbacdd3a3255e57e2d8e8830dc4ac9303201fa --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf530ea04c965a476b0110088f73a2b5df248e9ba12ee5d91b494ce9f663ccf +size 22192859 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..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" +}