commit 5b76f9a9b1f2e7fd8d34940c1b4e24ed6ef594ea Author: ModelHub XC Date: Sun Sep 20 06:34:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: CohereLabs/tiny-aya-en-thinker Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a8e0d12 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm 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 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..8d78e9e --- /dev/null +++ b/README.md @@ -0,0 +1,258 @@ +--- +language: +- multilingual +- am +- ar +- eu +- bn +- bg +- ca +- zh +- cs +- en +- fil +- fi +- fr +- de +- el +- ha +- he +- hi +- hu +- ig +- id +- ga +- it +- ja +- jv +- km +- ko +- lt +- ms +- mt +- no +- fa +- pl +- pa +- ru +- sk +- sw +- ta +- te +- th +- tr +- uk +- ur +- vi +- yo +- zu +license: cc-by-nc-4.0 +library_name: transformers +pipeline_tag: text-generation +tags: +- aya +- multilingual +- reasoning +- tiny-aya +extra_gated_heading: "Acknowledge license to accept the repository" +extra_gated_button_content: "Accept license" +extra_gated_prompt: > + By submitting this form, you agree to the License Agreement and acknowledge + that the information you provide will be collected, used, and shared in + accordance with Cohere's Privacy Policy. You'll receive email updates about + Cohere Labs and Cohere research, events, products and services. You can + unsubscribe at any time. +extra_gated_fields: + Name: text + Email: text + Affiliation: text + Country: country + I agree to use this model for non-commercial use ONLY: checkbox +--- + +# Model Card for Tiny Aya En-Thinker + +## Model Summary + +Cohere Labs Tiny Aya En-Thinker is an open-weights research release of a 3.35 billion parameter multilingual reasoning model. It is trained on multilingual reasoning data with English reasoning traces for 44 languages plus English, with coverage extending to 20+ more through additional non-reasoning instruction data. The model is designed to support mathematics, science, and general reasoning tasks, as well as instruction following and multilingual open-ended generation. + +This is a different model from [Tiny Aya L2-Thinker](https://huggingface.co/CohereLabs/tiny-aya-l2-thinker), which thinks in the same language as the prompt. + +Developed by: [Cohere](https://cohere.com/) and [Cohere Labs](https://cohere.com/research) + +- Point of Contact: [Cohere Labs](https://cohere.com/research) +- License: [CC-BY-NC](https://cohere.com/cohere-labs-cc-by-nc-license), requires also adhering to [Cohere Lab's Acceptable Use Policy](https://docs.cohere.com/docs/cohere-labs-acceptable-use-policy) +- Model: tiny-aya-en-thinker +- Model Size: 3.35B +- Context Length: 32K (input + output) + +For the broader Tiny Aya family, see [tiny-aya-global](https://huggingface.co/CohereLabs/tiny-aya-global), [tiny-aya-base](https://huggingface.co/CohereLabs/tiny-aya-base), [tiny-aya-l2-thinker](https://huggingface.co/CohereLabs/tiny-aya-l2-thinker), and the [Tiny Aya collection](https://huggingface.co/collections/CohereLabs/tiny-aya). + +## Usage + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM + +model_id = "CohereLabs/tiny-aya-en-thinker" +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype="auto") + +messages = [ + {"role": "user", "content": "Plus on m'enlève, plus je deviens grand. Qui suis-je?"}, +] + +inputs = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_tensors="pt", + return_dict=True, +).to(model.device) + +outputs = model.generate( + **inputs, + max_new_tokens=32768, + do_sample=True, + temperature=0.6, + top_p=0.95, +) + +print(tokenizer.decode(outputs[0], skip_special_tokens=False)) +``` + +The model supports **dual-mode reasoning**. In thinking mode (default behavior), `apply_chat_template(..., add_generation_prompt=True, enable_thinking=True)` produces a prompt of this shape: + +``` +<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble ++ developer preamble... +<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>[USER MESSAGE] /think<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|> +``` + +The model then writes its thinking trace between `<|START_THINKING|>` and `<|END_THINKING|>`, followed by the user-facing answer between `<|START_RESPONSE|>` and `<|END_RESPONSE|>`. The answer is typically in the same language as the prompt. + +To skip reasoning and get an answer directly, pass `enable_thinking=False`. The user turn is suffixed with ` /no_think` and the generation prompt closes with an empty thinking block so the model starts at the response: + +```python +inputs = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + enable_thinking=False, + return_tensors="pt", + return_dict=True, +).to(model.device) +``` + +``` +<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble ++ developer preamble... +<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>[USER MESSAGE] /no_think<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|><|END_THINKING|> +``` + +You can also pass prior thinking back into the conversation: + +```python +messages = [ + {"role": "user", "content": "¿Cuántas r hay en strawberry?"}, + { + "role": "assistant", + "thinking": "Count the letters: S-T-R-A-W-B-E-R-R-Y. Three r's.", + "content": "Hay 3 r en strawberry.", + }, + {"role": "user", "content": "Ahora haz lo mismo con blueberry."}, +] +``` + +The model can also be used directly using transformers `pipeline` abstraction: + +```python +from transformers import pipeline + +pipe = pipeline( + "text-generation", + model="CohereLabs/tiny-aya-en-thinker", + torch_dtype="auto", + device_map="auto", +) + +print(pipe( + [{"role": "user", "content": "Describe a home made recipe that you like most."}], + max_new_tokens=512, +)[0]["generated_text"][-1]) +``` + +## Chat template behavior + +The tokenizer chat template: + +1. Inserts the Tiny Aya system prompt: + +``` +# System Preamble +You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes. + +Your information cutoff date is June 2024. + +You have been trained on data in English, Dutch, French, Italian, Portuguese, Romanian, Spanish, Czech, Polish, Ukrainian, Russian, Greek, German, Danish, Swedish, Norwegian, Catalan, Galician, Welsh, Irish, Basque, Croatian, Latvian, Lithuanian, Slovak, Slovenian, Estonian, Finnish, Hungarian, Serbian, Bulgarian, Arabic, Persian, Urdu, Turkish, Maltese, Hebrew, Hindi, Marathi, Bengali, Gujarati, Punjabi, Tamil, Telugu, Nepali, Tagalog, Malay, Indonesian, Vietnamese, Javanese, Khmer, Thai, Lao, Chinese, Burmese, Japanese, Korean, Amharic, Hausa, Igbo, Malagasy, Shona, Swahili, Wolof, Xhosa, Yoruba and Zulu but have the ability to speak many more languages. + +# Default Preamble +The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt. +- Your name is Aya. +- You are a large language model built by Cohere. +- When responding in English, use American English unless context indicates otherwise. +- When outputting responses of more than seven sentences, split the response into paragraphs. +- Prefer the active voice. +- Use gender-neutral pronouns for unspecified persons. +- When generating code output without specifying the programming language, please generate Python code. +``` + +2. Appends ` /think` to every user turn by default (`enable_thinking=True`). Pass `enable_thinking=False` to append ` /no_think` instead. +3. With `add_generation_prompt=True`, appends `<|START_THINKING|>` to start a thinking trace, or `<|START_THINKING|><|END_THINKING|>` when `enable_thinking=False` so the model writes the answer without thinking. If an assistant message includes a `thinking` field, that history is also wrapped in `<|START_THINKING|>` / `<|END_THINKING|>`. + +## Model Details + +**Input:** Text only. + +**Output:** Model generates text, including an explicit English thinking trace if thinking is enabled, and a multilingual final answer. + +**Model Architecture:** Auto-regressive transformer in the Tiny Aya / Cohere family. After pretraining, this checkpoint is supervised-fine-tuned on a mix of English reasoning traces and multilingual translated reasoning where the **prompt and response are in the target language** and the **thinking stays in English**. + +**Languages covered:** Amharic, Arabic, Basque, Bengali, Bulgarian, Catalan, Chinese, Czech, English, Filipino, Finnish, French, German, Greek, Hausa, Hebrew, Hindi, Hungarian, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Khmer, Korean, Lithuanian, Malay, Maltese, Norwegian, Persian, Polish, Punjabi, Russian, Slovak, Swahili, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Yoruba, and Zulu. + +**Context Length:** Tiny Aya En-Thinker supports a context length of 32K. + +## Usage and Limitations + +### Intended Usage + +Tiny Aya En-Thinker is meant for multilingual conversational use when you want an English chain-of-thought and a final answer in the user's language. Intended applications include multilingual math and reasoning, open-ended generation, and research that compares English thinking to target-language reasoning. + +Use [Tiny Aya L2-Thinker](https://huggingface.co/CohereLabs/tiny-aya-l2-thinker) instead if the thinking trace should stay in the prompt language. + +### Limitations + +As with any language model, outputs may contain incorrect or outdated statements. Thinking traces can be long; cap `max_new_tokens` appropriately. Lowest-resource languages may show more variability than high-resource ones. + +## Citation + +If you use this model, please cite: + +```bibtex +@misc{mofakhami2026buildingmultilingualbridgesdata, + title={Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning}, + author={Mehrnaz Mofakhami and Ananya Sahu and Alejandro R. Salamanca and Daniel D'souza and Alexandre Berard and Thomas Euyang and Marzieh Fadaee and Julia Kreutzer}, + year={2026}, + eprint={2609.10445}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2609.10445}, +} +``` + +## Model Card Contact + +For errors or additional questions about details in this model card, contact [labs@cohere.com](mailto:labs@cohere.com). + +## Terms of Use + +This model is governed by a [CC-BY-NC License](https://cohere.com/cohere-labs-cc-by-nc-license) (Non-Commercial) and also requires adhering to [Cohere Lab's Acceptable Use Policy](https://docs.cohere.com/docs/cohere-labs-acceptable-use-policy). If you are interested in commercial use, please contact Cohere’s Sales team. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..903df44 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,32 @@ +{{ bos_token }}{%- set developer_preamble = messages[0]['content'] if messages and messages[0]['role']|lower == 'system' else none -%} +{%- set thinking = false if enable_thinking is defined and enable_thinking is false else true -%} +{%- set mode_suffix = " /think" if thinking else " /no_think" -%} +<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble +You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes. + +Your information cutoff date is June 2024. + +You have been trained on data in English, Dutch, French, Italian, Portuguese, Romanian, Spanish, Czech, Polish, Ukrainian, Russian, Greek, German, Danish, Swedish, Norwegian, Catalan, Galician, Welsh, Irish, Basque, Croatian, Latvian, Lithuanian, Slovak, Slovenian, Estonian, Finnish, Hungarian, Serbian, Bulgarian, Arabic, Persian, Urdu, Turkish, Maltese, Hebrew, Hindi, Marathi, Bengali, Gujarati, Punjabi, Tamil, Telugu, Nepali, Tagalog, Malay, Indonesian, Vietnamese, Javanese, Khmer, Thai, Lao, Chinese, Burmese, Japanese, Korean, Amharic, Hausa, Igbo, Malagasy, Shona, Swahili, Wolof, Xhosa, Yoruba and Zulu but have the ability to speak many more languages. + +# Default Preamble +The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt. +- Your name is Aya. +- You are a large language model built by Cohere. +- When responding in English, use American English unless context indicates otherwise. +- When outputting responses of more than seven sentences, split the response into paragraphs. +- Prefer the active voice. +- Use gender-neutral pronouns for unspecified persons. +- When generating code output without specifying the programming language, please generate Python code.{%- if developer_preamble %} + + +# Developer Preamble +The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions. +{{ developer_preamble }}{%- endif -%}<|END_OF_TURN_TOKEN|>{%- for message in messages -%} + {%- if message['role']|lower == 'system' and not (loop.first and developer_preamble) -%} +<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message['content'] }}<|END_OF_TURN_TOKEN|> + {%- elif message['role']|lower == 'user' -%} +<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message['content'] }}{{ mode_suffix }}<|END_OF_TURN_TOKEN|> + {%- elif message['role']|lower == 'assistant' or message['role']|lower == 'chatbot' -%} +<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{%- if message.thinking is defined and message.thinking -%}<|START_THINKING|>{{ message.thinking }}<|END_THINKING|>{%- endif -%}{%- if message.content is defined and message.content -%}<|START_RESPONSE|>{{ message.content }}<|END_RESPONSE|>{%- endif -%}<|END_OF_TURN_TOKEN|> + {%- endif -%} +{%- endfor -%}{%- if add_generation_prompt -%}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>{%- if not thinking -%}<|END_THINKING|>{%- endif -%}{%- endif -%} diff --git a/config.json b/config.json new file mode 100644 index 0000000..99630ca --- /dev/null +++ b/config.json @@ -0,0 +1,80 @@ +{ + "_sliding_window_pattern": 4, + "architectures": [ + "Cohere2ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 2, + "dtype": "bfloat16", + "eos_token_id": 3, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_norm_eps": 1e-05, + "layer_switch": 4, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "logit_scale": 1.0, + "max_position_embeddings": 5000000, + "model_type": "cohere2", + "norm_type": "layer_norm", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "order_of_interleaved_layers": "local_attn_first", + "pad_token_id": 0, + "position_embedding_type": "rope_gptj", + "rms_norm_eps": null, + "rope_scaling": null, + "rope_style": "interleave", + "rope_theta": 50000, + "rotary_pct": 1.0, + "sliding_window": 4096, + "transformer_block_type": "parallel", + "transformers_version": "4.56.2.4", + "use_cache": true, + "use_embedding_sharing": true, + "use_gated_activation": true, + "use_parallel_embedding": false, + "use_qk_norm": false, + "vocab_size": 262144 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..f9ac001 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "eos_token_id": 3, + "pad_token_id": 0, + "transformers_version": "4.56.2.4" +} diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..f8aac70 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,478 @@ +{ + "weight_map": { + "model.embed_tokens.weight": "worker-000-000.safetensors", + "model.layers.0.mlp.up_proj.weight": "worker-000-000.safetensors", + "model.layers.0.mlp.gate_proj.weight": "worker-000-000.safetensors", + "model.layers.1.mlp.up_proj.weight": "worker-000-000.safetensors", + "model.layers.1.mlp.gate_proj.weight": "worker-000-000.safetensors", + "model.layers.2.mlp.up_proj.weight": "worker-000-000.safetensors", + "model.layers.2.mlp.gate_proj.weight": "worker-000-000.safetensors", + "model.layers.3.mlp.up_proj.weight": "worker-000-000.safetensors", + "model.layers.3.mlp.gate_proj.weight": "worker-000-000.safetensors", + "model.layers.4.mlp.up_proj.weight": "worker-000-000.safetensors", + "model.layers.4.mlp.gate_proj.weight": "worker-000-000.safetensors", + "model.layers.5.mlp.up_proj.weight": "worker-000-000.safetensors", + "model.layers.5.mlp.gate_proj.weight": "worker-000-000.safetensors", + "model.layers.6.mlp.up_proj.weight": "worker-000-000.safetensors", + "model.layers.6.mlp.gate_proj.weight": "worker-000-000.safetensors", + "model.layers.7.mlp.up_proj.weight": "worker-000-000.safetensors", + "model.layers.7.mlp.gate_proj.weight": "worker-000-000.safetensors", + "model.layers.8.mlp.up_proj.weight": "worker-000-000.safetensors", + "model.layers.8.mlp.gate_proj.weight": "worker-000-000.safetensors", + "model.layers.9.mlp.up_proj.weight": "worker-000-000.safetensors", + "model.layers.9.mlp.gate_proj.weight": "worker-000-000.safetensors", + "model.layers.0.self_attn.q_proj.weight": "worker-000-000.safetensors", + "model.layers.0.self_attn.o_proj.weight": "worker-000-000.safetensors", + "model.layers.0.self_attn.k_proj.weight": "worker-000-000.safetensors", + "model.layers.0.self_attn.v_proj.weight": "worker-000-000.safetensors", + "model.layers.0.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.0.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.1.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.1.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.2.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.2.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.3.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.3.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.4.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.4.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.5.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.5.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.6.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.6.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.7.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.7.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.8.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.8.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.9.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.9.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.10.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.10.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.11.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.11.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.12.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.12.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.13.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.13.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.14.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.14.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.15.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.15.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.16.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.16.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.17.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.17.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.18.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.18.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.19.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.19.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.20.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.20.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.21.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.21.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.22.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.22.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.23.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.23.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.24.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.24.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.25.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.25.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.26.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.26.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.27.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.27.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.28.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.28.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.29.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.29.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.30.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.30.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.31.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.31.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.32.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.32.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.33.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.33.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.34.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.34.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.layers.35.mlp.up_proj.bias": "worker-000-000.safetensors", + "model.layers.35.mlp.gate_proj.bias": "worker-000-000.safetensors", + "model.norm.weight": "worker-000-000.safetensors", + "model.norm.bias": "worker-000-000.safetensors", + "model.layers.0.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.0.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.0.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.0.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.1.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.1.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.1.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.1.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.2.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.2.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.2.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.2.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.3.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.3.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.3.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.3.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.4.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.4.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.4.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.4.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.5.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.5.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.5.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.5.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.6.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.6.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.6.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.6.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.7.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.7.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.7.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.7.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.8.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.8.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.8.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.8.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.9.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.9.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.9.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.9.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.10.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.10.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.10.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.10.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.11.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.11.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.11.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.11.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.12.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.12.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.12.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.12.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.13.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.13.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.13.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.13.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.14.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.14.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.14.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.14.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.15.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.15.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.15.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.15.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.16.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.16.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.16.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.16.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.17.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.17.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.17.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.17.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.18.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.18.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.18.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.18.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.19.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.19.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.19.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.19.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.20.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.20.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.20.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.20.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.21.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.21.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.21.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.21.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.22.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.22.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.22.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.22.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.23.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.23.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.23.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.23.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.24.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.24.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.24.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.24.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.25.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.25.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.25.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.25.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.26.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.26.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.26.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.26.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.27.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.27.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.27.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.27.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.28.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.28.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.28.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.28.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.29.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.29.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.29.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.29.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.30.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.30.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.30.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.30.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.31.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.31.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.31.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.31.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.32.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.32.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.32.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.32.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.33.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.33.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.33.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.33.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.34.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.34.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.34.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.34.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.35.input_layernorm.weight": "worker-000-000.safetensors", + "model.layers.35.input_layernorm.bias": "worker-000-000.safetensors", + "model.layers.35.self_attn.o_proj.bias": "worker-000-000.safetensors", + "model.layers.35.mlp.down_proj.bias": "worker-000-000.safetensors", + "model.layers.10.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.10.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.11.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.11.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.12.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.12.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.13.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.13.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.14.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.14.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.15.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.15.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.16.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.16.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.17.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.17.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.18.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.18.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.19.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.19.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.20.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.20.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.21.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.21.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.22.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.22.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.23.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.23.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.24.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.24.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.25.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.25.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.26.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.26.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.27.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.27.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.28.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.28.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.29.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.29.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.30.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.30.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.31.mlp.up_proj.weight": "worker-000-001.safetensors", + "model.layers.31.mlp.gate_proj.weight": "worker-000-001.safetensors", + "model.layers.1.self_attn.q_proj.weight": "worker-000-001.safetensors", + "model.layers.1.self_attn.k_proj.weight": "worker-000-001.safetensors", + "model.layers.1.self_attn.v_proj.weight": "worker-000-001.safetensors", + "model.layers.32.mlp.up_proj.weight": "worker-000-002.safetensors", + "model.layers.32.mlp.gate_proj.weight": "worker-000-002.safetensors", + "model.layers.33.mlp.up_proj.weight": "worker-000-002.safetensors", + "model.layers.33.mlp.gate_proj.weight": "worker-000-002.safetensors", + "model.layers.34.mlp.up_proj.weight": "worker-000-002.safetensors", + "model.layers.34.mlp.gate_proj.weight": "worker-000-002.safetensors", + "model.layers.35.mlp.up_proj.weight": "worker-000-002.safetensors", + "model.layers.35.mlp.gate_proj.weight": "worker-000-002.safetensors", + "model.layers.0.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.1.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.2.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.3.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.4.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.5.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.6.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.7.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.8.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.9.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.10.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.11.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.12.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.13.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.14.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.15.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.16.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.17.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.18.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.19.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.20.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.21.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.22.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.23.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.24.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.25.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.26.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.27.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.28.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.29.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.30.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.31.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.32.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.33.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.34.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.35.mlp.down_proj.weight": "worker-000-002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "worker-000-002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "worker-000-002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "worker-000-002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.32.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.32.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.33.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.33.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.34.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.34.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.35.self_attn.q_proj.weight": "worker-000-003.safetensors", + "model.layers.35.self_attn.o_proj.weight": "worker-000-003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.32.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.32.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.33.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.33.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.34.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.34.self_attn.v_proj.weight": "worker-000-003.safetensors", + "model.layers.35.self_attn.k_proj.weight": "worker-000-003.safetensors", + "model.layers.35.self_attn.v_proj.weight": "worker-000-003.safetensors" + }, + "metadata": { + "total_size": 6700486656 + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..553cc1f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,40 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "additional_special_tokens": [ + "<|START_RESPONSE|>", + "<|END_RESPONSE|>", + "<|START_ACTION|>", + "<|END_ACTION|>", + "<|START_TOOL_RESULT|>", + "<|END_TOOL_RESULT|>", + "<|START_THINKING|>", + "<|END_THINKING|>" + ] +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..9505840 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55388a861271fb6b9eb631670e5eee0562bcddf204dc63494d98ee67f5551839 +size 30245131 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5cf6f5b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,202 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": false, + "clean_up_tokenization_spaces": false, + "legacy": true, + "spaces_between_special_tokens": false, + "use_default_system_prompt": false, + "bos_token": "", + "eos_token": "", + "pad_token": "", + "unk_token": "", + "tokenizer_class": "CohereTokenizerFast", + "model_max_length": 1000000000000000019884624838656, + "sp_model_kwargs": {}, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "5": { + "content": "<|START_OF_TURN_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "6": { + "content": "<|END_OF_TURN_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "7": { + "content": "<|USER_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "8": { + "content": "<|CHATBOT_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "9": { + "content": "<|SYSTEM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "10": { + "content": "<|NEW_FILE|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "11": { + "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "12": { + "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "13": { + "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "14": { + "content": "<|END_OF_MIDDLE_FIM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "261000": { + "content": "<|START_RESPONSE|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "261001": { + "content": "<|END_RESPONSE|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "261002": { + "content": "<|START_ACTION|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "261003": { + "content": "<|END_ACTION|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "261004": { + "content": "<|START_TOOL_RESULT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "261005": { + "content": "<|END_TOOL_RESULT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "261006": { + "content": "<|START_THINKING|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "261007": { + "content": "<|END_THINKING|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + } +} diff --git a/worker-000-000.safetensors b/worker-000-000.safetensors new file mode 100644 index 0000000..f0cff18 --- /dev/null +++ b/worker-000-000.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bacbd00cf67e9ae1d8be136533340d72c11a53cb83c5e7854f99e0addffc372 +size 1998698496 diff --git a/worker-000-001.safetensors b/worker-000-001.safetensors new file mode 100644 index 0000000..17ca8dd --- /dev/null +++ b/worker-000-001.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d6363e6adac69ac36b370c98f60344f641653e868696fbfa258bd6e391fd5d0 +size 1996494056 diff --git a/worker-000-002.safetensors b/worker-000-002.safetensors new file mode 100644 index 0000000..287ff15 --- /dev/null +++ b/worker-000-002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79f4e79c3207aaa385202e1999529d29c3c0206445e56c0796beb1fdac14443c +size 1996494088 diff --git a/worker-000-003.safetensors b/worker-000-003.safetensors new file mode 100644 index 0000000..9f85d2e --- /dev/null +++ b/worker-000-003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd127b837f39674e3a427d6c6561b0948ba9871437690cdfe8274c27c0d030c5 +size 708852792