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/.mdl b/.mdl new file mode 100644 index 0000000000000000000000000000000000000000..125146bfac0da312f83f9931dea571541f595354 Binary files /dev/null and b/.mdl differ diff --git a/.msc b/.msc new file mode 100644 index 0000000000000000000000000000000000000000..1cda92927e6ad2cc5ab5c52505921d9b157b6f7e Binary files /dev/null and b/.msc differ diff --git a/.mv b/.mv new file mode 100644 index 0000000000000000000000000000000000000000..113aa401e56fdfa1b40464f5595cdbd4a9adc495 --- /dev/null +++ b/.mv @@ -0,0 +1 @@ +Revision:master,CreatedAt:1772131132 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..cf9ef1fae1721ba1cf49793d97c7345d415ad3c8 --- /dev/null +++ b/README.md @@ -0,0 +1,225 @@ +--- +library_name: transformers +license: mit +pipeline_tag: text-to-text +tags: +- vLLM +- AWQ +base_model: + - ZhipuAI/GLM-5 +base_model_relation: quantized + +--- +# GLM-5-AWQ +Base model: [ZhipuAI/GLM-5](https://www.modelscope.cn/models/ZhipuAI/GLM-5) + +This repo quantizes the model using data-free quantization (no calibration dataset required). + +### 【Dependencies / Installation】 + +```python +# NOTE: +# vllm==0.16.0rc2 absolutely would NOT work! +# Must upgrade to >=0.16.1rc1 +vllm>=0.16.1rc1.dev7 +transformers>=5.3.0.dev0 +``` + +As of **2026-02-26**, make sure your system has cuda12.8 installed. + +Then, create a fresh Python environment (e.g. python3.12 venv) and run: +```bash +pip install -U vllm --pre --index-url https://pypi.org/simple --extra-index-url https://wheels.vllm.ai/nightly +pip install git+https://github.com/huggingface/transformers.git +pip install git+https://github.com/deepseek-ai/DeepGEMM.git@v2.1.1.post3 --no-build-isolation +``` +[vLLM Official Guide](https://docs.vllm.ai/projects/recipes/en/latest/Qwen/Qwen3.5.html) + + +### 【vLLM Startup Command】 +Note: When launching with TP=8, include `--enable-expert-parallel`; +otherwise the expert tensors wouldn’t be evenly sharded across GPU devices. + +``` +export VLLM_USE_DEEP_GEMM=0 +export VLLM_USE_FLASHINFER_MOE_FP16=1 +export VLLM_USE_FLASHINFER_SAMPLER=0 +export OMP_NUM_THREADS=4 + +vllm serve \ + __YOUR_PATH__/tclf90/GLM-5-AWQ \ + --served-model-name MY_MODEL \ + --swap-space 16 \ + --max-num-seqs 32 \ + --max-model-len 32768 \ + --gpu-memory-utilization 0.9 \ + --tensor-parallel-size 8 \ + --enable-expert-parallel \ + --enable-auto-tool-choice \ + --tool-call-parser glm47 \ + --reasoning-parser glm45 \ + --speculative-config '{"method":"mtp","num_speculative_tokens":1}' \ + --trust-remote-code \ + --host 0.0.0.0 \ + --port 8000 +``` + +### 【Logs】 +``` +2026-02-26 +1. Initial commit +``` + +### 【Model Files】 +| File Size | Last Updated | +|-----------|--------------| +| `392 GiB` | `2026-02-26` | + +### 【Model Download】 +```python +from modelscope import snapshot_download +snapshot_download('tclf90/GLM-5-AWQ', cache_dir="your_local_path") +``` + +### 【Overview】 + +# GLM-5 + +
+ +
+

+ 👋 Join our WeChat or Discord community. +
+ 📖 Check out the GLM-5 technical blog. +
+ 📍 Use GLM-5 API services on Z.ai API Platform. +
+ 👉 One click to GLM-5. +

+ +## Introduction + +We are launching GLM-5, targeting complex systems engineering and long-horizon agentic tasks. Scaling is still one of the most important ways to improve the intelligence efficiency of Artificial General Intelligence (AGI). Compared to GLM-4.5, GLM-5 scales from 355B parameters (32B active) to 744B parameters (40B active), and increases pre-training data from 23T to 28.5T tokens. GLM-5 also integrates DeepSeek Sparse Attention (DSA), largely reducing deployment cost while preserving long-context capacity. + +Reinforcement learning aims to bridge the gap between competence and excellence in pre-trained models. However, deploying it at scale for LLMs is a challenge due to the RL training inefficiency. To this end, we developed [slime](https://github.com/THUDM/slime), a novel **asynchronous RL infrastructure** that substantially improves training throughput and efficiency, enabling more fine-grained post-training iterations. With advances in both pre-training and post-training, GLM-5 delivers significant improvement compared to GLM-4.7 across a wide range of academic benchmarks and achieves best-in-class performance among all open-source models in the world on reasoning, coding, and agentic tasks, closing the gap with frontier models. + +## Benchmark + +| | GLM-5 | GLM-4.7 | DeepSeek-V3.2 | Kimi K2.5 | Claude Opus 4.5 | Gemini 3 Pro | GPT-5.2 (xhigh) | +| -------------------------------- | ---------------------- | --------- | ------------- |-----------| --------------- | ------------ | --------------- | +| HLE | 30.5 | 24.8 | 25.1 | 31.5 | 28.4 | 37.2 | 35.4 | +| HLE (w/ Tools) | 50.4 | 42.8 | 40.8 | 51.8 | 43.4* | 45.8* | 45.5* | +| AIME 2026 I | 92.7 | 92.9 | 92.7 | 92.5 | 93.3 | 90.6 | - | +| HMMT Nov. 2025 | 96.9 | 93.5 | 90.2 | 91.1 | 91.7 | 93.0 | 97.1 | +| IMOAnswerBench | 82.5 | 82.0 | 78.3 | 81.8 | 78.5 | 83.3 | 86.3 | +| GPQA-Diamond | 86.0 | 85.7 | 82.4 | 87.6 | 87.0 | 91.9 | 92.4 | +| SWE-bench Verified | 77.8 | 73.8 | 73.1 | 76.8 | 80.9 | 76.2 | 80.0 | +| SWE-bench Multilingual | 73.3 | 66.7 | 70.2 | 73.0 | 77.5 | 65.0 | 72.0 | +| Terminal-Bench 2.0 (Terminus 2) | 56.2 / 60.7 † | 41.0 | 39.3 | 50.8 | 59.3 | 54.2 | 54.0 | +| Terminal-Bench 2.0 (Claude Code) | 56.2 / 61.1 † | 32.8 | 46.4 | - | 57.9 | - | - | +| CyberGym | 43.2 | 23.5 | 17.3 | 41.3 | 50.6 | 39.9 | - | +| BrowseComp | 62.0 | 52.0 | 51.4 | 60.6 | 37.0 | 37.8 | - | +| BrowseComp (w/ Context Manage) | 75.9 | 67.5 | 67.6 | 74.9 | 67.8 | 59.2 | 65.8 | +| BrowseComp-Zh | 72.7 | 66.6 | 65.0 | 62.3 | 62.4 | 66.8 | 76.1 | +| τ²-Bench | 89.7 | 87.4 | 85.3 | 80.2 | 91.6 | 90.7 | 85.5 | +| MCP-Atlas (Public Set) | 67.8 | 52.0 | 62.2 | 63.8 | 65.2 | 66.6 | 68.0 | +| Tool-Decathlon | 38.0 | 23.8 | 35.2 | 27.8 | 43.5 | 36.4 | 46.3 | +| Vending Bench 2 | $4,432.12 | $2,376.82 | $1,034.00 | $1,198.46 | $4,967.06 | $5,478.16 | $3,591.33 | + +> *: refers to their scores of full set. +> +> †: A verified version of Terminal-Bench 2.0 that fixes some ambiguous instructions. +See footnote for more evaluation details. + +### Footnote + +* **Humanity’s Last Exam (HLE) & other reasoning tasks**: We evaluate with a maximum generation length of 131,072 tokens (`temperature=1.0, top_p=0.95, max_new_tokens=131072`). By default, we report the text-only subset; results marked with * are from the full set. We use GPT-5.2 (medium) as the judge model. For HLE-with-tools, we use a maximum context length of 202,752 tokens. +* **SWE-bench & SWE-bench Multilingual**: We run the SWE-bench suite with OpenHands using a tailored instruction prompt. Settings: `temperature=0.7, top_p=0.95, max_new_tokens=16384`, with a 200K context window. +* **BrowserComp**: Without context management, we retain details from the most recent 5 turns. With context management, we use the same discard-all strategy as DeepSeek-v3.2 and Kimi K2.5. +* **Terminal-Bench 2.0 (Terminus 2)**: We evaluate with the Terminus framework using `timeout=2h, temperature=0.7, top_p=1.0, max_new_tokens=8192`, with a 128K context window. Resource limits are capped at 16 CPUs and 32 GB RAM. +* **Terminal-Bench 2.0 (Claude Code)**: We evaluate in Claude Code 2.1.14 (think mode, default effort) with `temperature=1.0, top_p=0.95, max_new_tokens=65536`. We remove wall-clock time limits due to generation speed, while preserving per-task CPU and memory constraints. Scores are averaged over 5 runs. We fix environment issues introduced by Claude Code and also report results on a verified Terminal-Bench 2.0 dataset that resolves ambiguous instructions (see: [https://huggingface.co/datasets/zai-org/terminal-bench-2-verified](https://huggingface.co/datasets/zai-org/terminal-bench-2-verified)). +* **CyberGym**: We evaluate in Claude Code 2.1.18 (think mode, no web tools) with (`temperature=1.0, top_p=1.0, max_new_tokens=32000`) and a 250-minute timeout per task. Results are single-run Pass@1 over 1,507 tasks. +* **MCP-Atlas**: All models are evaluated in think mode on the 500-task public subset with a 10-minute timeout per task. We use Gemini 3 Pro as the judge model. +* **τ²-bench**: We add a small prompt adjustment in Retail and Telecom to avoid failures caused by premature user termination. For Airline, we apply the domain fixes proposed in the Claude Opus 4.5 system card. +* **Vending Bench 2**: Runs are conducted independently by [Andon Labs](https://andonlabs.com/evals/vending-bench-2). + + +## Serve GLM-5 Locally + +### Prepare environment + +vLLM, SGLang, and xLLM all support local deployment of GLM-5. A simple deployment guide is provided here. + ++ vLLM + + Using Docker as: + + ```shell + docker pull vllm/vllm-openai:nightly + ``` + + or using pip: + + ```shell + pip install -U vllm --pre --index-url https://pypi.org/simple --extra-index-url https://wheels.vllm.ai/nightly + ``` + + then upgrade transformers: + + ``` + pip install git+https://github.com/huggingface/transformers.git + ``` + ++ SGLang + + Using Docker as: + ```bash + docker pull lmsysorg/sglang:glm5-hopper # For Hopper GPU + docker pull lmsysorg/sglang:glm5-blackwell # For Blackwell GPU + ``` + +### Deploy + ++ vLLM + + ```shell + vllm serve zai-org/GLM-5-FP8 \ + --tensor-parallel-size 8 \ + --gpu-memory-utilization 0.85 \ + --speculative-config.method mtp \ + --speculative-config.num_speculative_tokens 1 \ + --tool-call-parser glm47 \ + --reasoning-parser glm45 \ + --enable-auto-tool-choice \ + --served-model-name glm-5-fp8 + ``` + + Check the [recipes](https://github.com/vllm-project/recipes/blob/main/GLM/GLM5.md) for more details. + ++ SGLang + + ```shell + python3 -m sglang.launch_server \ + --model-path zai-org/GLM-5-FP8 \ + --tp-size 8 \ + --tool-call-parser glm47 \ + --reasoning-parser glm45 \ + --speculative-algorithm EAGLE \ + --speculative-num-steps 3 \ + --speculative-eagle-topk 1 \ + --speculative-num-draft-tokens 4 \ + --mem-fraction-static 0.85 \ + --served-model-name glm-5-fp8 + ``` + + Check the [sglang cookbook](https://cookbook.sglang.io/autoregressive/GLM/GLM-5) for more details. + ++ xLLM and other Ascend NPU + + Please check the deployment guide [here](https://github.com/zai-org/GLM-5/blob/main/example/ascend.md). + + +## Citation + +Our technical report is coming soon. 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..5ec4c1031a9b2c2c025b2f8fe2985ccb54441cb3 --- /dev/null +++ b/config.json @@ -0,0 +1,75 @@ +{ + "name_or_path": "tclf90/GLM-5-AWQ", + "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, + "hidden_act": "silu", + "head_dim": 64, + "hidden_size": 6144, + "index_head_dim": 128, + "index_n_heads": 32, + "index_topk": 2048, + "indexer_rope_interleave": true, + "initializer_range": 0.02, + "intermediate_size": 12288, + "kv_lora_rank": 512, + "max_position_embeddings": 202752, + "moe_intermediate_size": 2048, + "moe_layer_freq": 1, + "model_type": "glm_moe_dsa", + "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": 1000000, + "rope_type": "default" + }, + "routed_scaling_factor": 2.5, + "scoring_func": "sigmoid", + "tie_word_embeddings": false, + "topk_group": 1, + "topk_method": "noaux_tc", + "transformers_version": "5.0.2.dev0", + "use_cache": true, + "v_head_dim": 256, + "vocab_size": 154880, + "quantization_config": { + "quant_method": "awq", + "bits": 4, + "group_size": 128, + "version": "gemm", + "zero_point": true, + "modules_to_not_convert": [ + "self_attn", + "shared_expert", + "mlp.gate", + "model.layers.0.", + "model.layers.1.", + "model.layers.2." + ] + } +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..640e99c64d2f17d76e2f1f13af219fb369e1004e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 154820, + 154827, + 154829 + ], + "pad_token_id": 154820, + "temperature": 1.0, + "top_p": 0.95, + "transformers_version": "5.0.2.dev0" +} diff --git a/model-00082-of-00141.safetensors b/model-00082-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce0d52f86d85d63afba372a463eb5549089d2437 --- /dev/null +++ b/model-00082-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ea5c2c328515811836d05f2524b7b8f0e85e09577db536eb2e2a08a5dfc146 +size 2994214048 diff --git a/model-00084-of-00141.safetensors b/model-00084-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6fc061f0fd52509b2a86eb4d30e3959b4cb45add --- /dev/null +++ b/model-00084-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee21677b046e8c42f2b2690ffcb64fa4eb22cf0ab095333719ffb5341527aae +size 2994213912 diff --git a/model-00085-of-00141.safetensors b/model-00085-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1092323225c95957870c9f1c18e50925e9a3d67c --- /dev/null +++ b/model-00085-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3e4d8c454ffa0bf5cf26874d45e9936fd0b85ab26d600f203bbf26227fc7af +size 2999875360 diff --git a/model-00087-of-00141.safetensors b/model-00087-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eeab36faf7e1d7621596fac059ed1c1a2ed7efb9 --- /dev/null +++ b/model-00087-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf734e2a5d20180cc07d1f8aab0f67679e2186fda641a4b7ac2b886496f1683 +size 2999875608 diff --git a/model-00089-of-00141.safetensors b/model-00089-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e6469b71fb41a8cb016eedcecf15be1cd9d650d --- /dev/null +++ b/model-00089-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15513bec5e3894f6a14753639fa38fbe7ffdb3f969cc57b403716953dba5b39b +size 2999875840 diff --git a/model-00090-of-00141.safetensors b/model-00090-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3fdf5b41fd2edeeec2e6400b087fe2764215e889 --- /dev/null +++ b/model-00090-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88cd200b518043691e1b03298474ac2db757f3daa27baea0c3c16bcefd48cd4 +size 2992576552 diff --git a/model-00091-of-00141.safetensors b/model-00091-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4dcb68822eb0aefb9bdd21c7ee5e877ae5ea3776 --- /dev/null +++ b/model-00091-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52367e137f82654b72fbf56e8b49da66038fe4ec074efc5a9c7a33ccf9d610e5 +size 2994975120 diff --git a/model-00092-of-00141.safetensors b/model-00092-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a702749d504dd5a2ce124c1bafb6a73230d6bc4b --- /dev/null +++ b/model-00092-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f53c4832f6ca555fb0dee23e0dfa1807cc990de64d37c9bf49a4489b5f2e6c3d +size 2999875224 diff --git a/model-00093-of-00141.safetensors b/model-00093-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac8491d6b37927e97dad2098ed576e7ff35cae96 --- /dev/null +++ b/model-00093-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b36a5a3547a3d45e6c54360c116458a5448cf8d6d1c0e356a0d970c7df48ac4 +size 2994214040 diff --git a/model-00094-of-00141.safetensors b/model-00094-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c2f8e9d211d7089f636d747e0204e75caa9ecd4 --- /dev/null +++ b/model-00094-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca572f2a22e4e494793c062f826fd0a267fe5ad3c84ff0d7b12c1cd7b55b2403 +size 2999875224 diff --git a/model-00095-of-00141.safetensors b/model-00095-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd7c70e1607462e5fc1cb1cb350ab81921904c3d --- /dev/null +++ b/model-00095-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4b5110054e1c34c3e1d2b88c96d98265b2c488e4121ef7db5e254806b06eb34 +size 2994213784 diff --git a/model-00097-of-00141.safetensors b/model-00097-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85584a0387a386bd26a561f995ad192bd29fbead --- /dev/null +++ b/model-00097-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d864701fc5d1bf0e27c69e585c571bf3f26ac132627a704fd94a7a60c3ab7ee +size 2994213536 diff --git a/model-00099-of-00141.safetensors b/model-00099-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..44b072a7d52c599c1f1c118e75b78383ed246177 --- /dev/null +++ b/model-00099-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c901ab44ebe3a8493d51f1a6bedd4c9167700c1793cdb4c7511a975e95437aa +size 2998537240 diff --git a/model-00100-of-00141.safetensors b/model-00100-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc81387ded66966625faf66fe18ccc6704eb16ee --- /dev/null +++ b/model-00100-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a948430ab086b1bdfbaec32c3742902b41b82583e293b6ea9813a7bfd609f34 +size 2995552016 diff --git a/model-00101-of-00141.safetensors b/model-00101-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e611318547f1b3ad5884e0469a1f4210b580cb33 --- /dev/null +++ b/model-00101-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:498b1a46e1c452d12311246d1c1ea79769cd548e31be2e2a0ece44a7624f9bd3 +size 2999875216 diff --git a/model-00102-of-00141.safetensors b/model-00102-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a27382031bb69863d95ccbaba411f20a2a0219a8 --- /dev/null +++ b/model-00102-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c9927fd89559146117d11582388c3f7691f05520103cfa7a1791a2f1d69332 +size 2994214040 diff --git a/model-00104-of-00141.safetensors b/model-00104-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f784c1a953ddd24fa0953f7fea0ffccbbce1e4a2 --- /dev/null +++ b/model-00104-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e77c9c59d25c05feb00490e87f166b4176958be273a3a26d71a244c3d1b1deed +size 2994213928 diff --git a/model-00105-of-00141.safetensors b/model-00105-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f01b85017eb4bfe966560861c858ad9acbea4bf --- /dev/null +++ b/model-00105-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffbf45bc5cf4cca0de28f56d00dbdabe2102f3ece747b0a7cc5e98a22ac71b02 +size 2999875344 diff --git a/model-00107-of-00141.safetensors b/model-00107-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1d6f80db58e9c6b8bb3f8993f4345761e116374e --- /dev/null +++ b/model-00107-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d22e0acdbe80f00ffe9e578e4d93a8886b98353f52ad7b8111121066944073f +size 2999875592 diff --git a/model-00108-of-00141.safetensors b/model-00108-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e29aa206c66825f314e9694a57d3a0d6bb42e0d --- /dev/null +++ b/model-00108-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d158752d0c23d921b80b558959a9c2910ac29c35389a2ad1becef70f068c6cd3 +size 2994213424 diff --git a/model-00109-of-00141.safetensors b/model-00109-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5c9c7a22930eea0eaba743149892a1dbae08a76 --- /dev/null +++ b/model-00109-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3e944715639b341e0c6ebf68de9993f551677488eb2bff1bf157deea8d20f86 +size 2999875824 diff --git a/model-00112-of-00141.safetensors b/model-00112-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f5515631632c9a544ed2867ad5f38983023e402 --- /dev/null +++ b/model-00112-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1fbb90a6fb222a416726ef9b0fe0eafcd5f30802e7f1e44ac174ab35c6b0813 +size 3000071960 diff --git a/model-00114-of-00141.safetensors b/model-00114-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0d8a0f9d9127a78a020a07be34d6e255dbb0816b --- /dev/null +++ b/model-00114-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0273e507b3508affbf235a930bcc83a5a3d10f06d804e463a6cfb611446552fe +size 2999875216 diff --git a/model-00115-of-00141.safetensors b/model-00115-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b11873ce38073fccc1ecda0fd5acd87ae59d60c --- /dev/null +++ b/model-00115-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7918c048056a14fefdff45da8704be02fa90fc26bbf3dff43bb897be522638ee +size 2994213880 diff --git a/model-00116-of-00141.safetensors b/model-00116-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a39412df89d0601d91d66b7419f960d7402a158f --- /dev/null +++ b/model-00116-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3b81392cb747c98efa304ab472cbd1837d53eece256335b31ca118483970d7 +size 2999875392 diff --git a/model-00117-of-00141.safetensors b/model-00117-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e02a4cd0c0b7bceda0d1c5eb07c888042c1ff64c --- /dev/null +++ b/model-00117-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe32ad3844e322646646d8186688775a27f53a01ac19df7ac8ee89c19cd518c +size 2994213632 diff --git a/model-00118-of-00141.safetensors b/model-00118-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c33d267fc24efbec639c04b6125f266af468bb35 --- /dev/null +++ b/model-00118-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8ada5ea3d11290182ba5056a8cca1cce1483eedacebd583dd9bb8f88c5a6c99 +size 2999875632 diff --git a/model-00119-of-00141.safetensors b/model-00119-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0a5bb0898303cbb30ad981787b065db00fdb2c3b --- /dev/null +++ b/model-00119-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f42052b3b899901dbee4787feb8798cea18f4c639ec4d8ea830f1c0bfee44380 +size 2994213384 diff --git a/model-00123-of-00141.safetensors b/model-00123-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0d1ea7b0ab99cf2c8b29e67520ae68fb8f337def --- /dev/null +++ b/model-00123-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:955a63f081dd7b56738b34f84aedc035a8e0544d46886a3890a96e9b3135495f +size 2999875224 diff --git a/model-00124-of-00141.safetensors b/model-00124-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fd7f7b3c0436a3d27a7d668f50d5e7ad3029dc5c --- /dev/null +++ b/model-00124-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbc3e9591eb95fd53928f95d54a3af613b984536b2efbf05bd3ddd85a149abb2 +size 2994214024 diff --git a/model-00128-of-00141.safetensors b/model-00128-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e11630692eaace0a0ecf76e23521d8623f4a23a1 --- /dev/null +++ b/model-00128-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ed3f8cbafaeb665035c4ad01427852eab7a8bf8a33807d4d280b4799be18d0 +size 2994213536 diff --git a/model-00129-of-00141.safetensors b/model-00129-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91b5939fcf86cab9f95b1123ca7d8549e39359b5 --- /dev/null +++ b/model-00129-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:230a896720f5b8fe22973431080a2ad26927eb2e67c63989dd444151e5a8d57a +size 2999875736 diff --git a/model-00130-of-00141.safetensors b/model-00130-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..211c7c6a0e9b1a5d8617d3eeebfea306a0359638 --- /dev/null +++ b/model-00130-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2173c8d9e91dcff2a64dd5b277c933b5393007637aaa93ad9c31fb164d9c8989 +size 2999532328 diff --git a/model-00131-of-00141.safetensors b/model-00131-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0f88e64a3e3c6558686afadbe623736789e2256 --- /dev/null +++ b/model-00131-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67fb5585c3832df24d54d468d61113589b40d94bc146758f566519abf4f71e3e +size 2994556920 diff --git a/model-00132-of-00141.safetensors b/model-00132-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1362b5b2070273d70d56c44d231c9adc8ab32a9 --- /dev/null +++ b/model-00132-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d2cfc12c0ae16995b18064ed23ced1c34a7596a7c283b39da0c76ba33df97e +size 2999875216 diff --git a/model-00133-of-00141.safetensors b/model-00133-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f67f2fc106482a37bce083c3ba5c77a68a879eaa --- /dev/null +++ b/model-00133-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b0d6ab754aa92f9764649856a06c3fefc09450da6d9a346e1f194f49090b71 +size 2994214048 diff --git a/model-00135-of-00141.safetensors b/model-00135-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3eb7fafa3394c49a584b264b4d487570142418ac --- /dev/null +++ b/model-00135-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac988353923bbe074747530ccb2ec0cb536f5e2925e1f98e95c9f26b1bbdf695 +size 2994213912 diff --git a/model-00138-of-00141.safetensors b/model-00138-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8920c708b3a965ee4bf6f61d900b43bf148f5a9 --- /dev/null +++ b/model-00138-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c3ecf3e08fa09f4ef9b850db2b85b505245d241b88a9b37e2f1f48fb225a80 +size 2999875608 diff --git a/model-00139-of-00141.safetensors b/model-00139-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f53cce14502d0921201c99009169319c0e7c95f7 --- /dev/null +++ b/model-00139-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5128360abce7b1276c47d47ffe56170f23625bf5c6f5b48fffb006577ea3ef59 +size 2994213416 diff --git a/model-00141-of-00141.safetensors b/model-00141-of-00141.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..45a20a25abe82e5d528bf46adbab4b1b1c352598 --- /dev/null +++ b/model-00141-of-00141.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abf9afc9bd62201a4d0fbe0e8a393269d5e8e2658be83b1c4e5c8eb84d4127b +size 2054210192 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b9782a4a066ed5e25e911f7df0e9dd4a5dce6d52 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b154ef2838068217de8fa81b2f8d5242f2c33bfe7f6d057f0f72d46f53a458c +size 16093166 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" +}