commit ac9fb308586b97a1b33ed65406767aeb96541c6b Author: ModelHub XC Date: Sat Jul 4 06:10:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: derprofi2431/Prisma-32B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..43c2c10 --- /dev/null +++ b/README.md @@ -0,0 +1,109 @@ +--- +license: apache-2.0 +tags: +- prisma +- coding +- cybersecurity +- reasoning +- uncensored +- agent +language: +- en +- de +- zh +library_name: transformers +pipeline_tag: text-generation +--- + +# Prisma-32B + +**Prisma-32B** is a 32 billion parameter language model optimized for advanced coding, technical reasoning, and cybersecurity workflows. It the first Prisma Model with no security blocking. It is the second release in the **Prisma** series, following [`Prisma-0.6B`](https://huggingface.co/derprofi2431/Prisma-0.6B). + +Prisma-32B is designed to be a capable, direct, and technically rigorous assistant for users who need a model that engages substantively with complex technical material. + +--- + +## Model Details + +| Property | Value | +|---|---| +| **Parameters** | 32B | +| **Architecture** | Transformer Decoder | +| **Context Length** | 32,768 tokens | +| **Languages** | English, German, Chinese (+ 20 more) | +| **License** | Apache 2.0 | + +--- + +## Intended Use + +Prisma-32B is intended for: + +- **Coding assistance** — full-stack development, debugging, refactoring, code review +- **Cybersecurity research** — offensive security workflows (red team, CTF, exploit analysis) and defensive workflows (incident response, hardening, secure code review) +- **Technical writing** — documentation, system specifications, architecture +- **Research and experimentation** in controlled environments + +--- + +## Usage + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained( + "derprofi2431/Prisma-32B", + torch_dtype="auto", + device_map="auto", +) +tokenizer = AutoTokenizer.from_pretrained("derprofi2431/Prisma-32B") + +messages = [ + {"role": "user", "content": "Write a port scanner in Python."} +] +inputs = tokenizer.apply_chat_template( + messages, return_tensors="pt", add_generation_prompt=True +).to(model.device) + +output = model.generate(inputs, max_new_tokens=2048, temperature=0.7) +print(tokenizer.decode(output[0], skip_special_tokens=True)) +``` + +### Recommended Sampling + +| Parameter | Value | +|---|---| +| `temperature` | 0.6 – 0.8 | +| `top_p` | 0.9 | +| `top_k` | 40 | +| `repetition_penalty` | 1.05 | + +--- + +## Quantized Versions + +GGUF quantizations for local inference via Ollama and llama.cpp will be released as separate repositories. + +--- + +## Limitations and Responsible Use + +- The user is fully responsible for the content they generate and how they use it. +- The model is not aligned for general consumer-facing deployment. For production use, deploy behind an appropriate safety layer (input filtering, output classification, etc.). +- The model may reflect biases present in large-scale text corpora. +- Intended for adult, technically competent users in controlled environments. + +By downloading or using this model, you agree to use it lawfully and ethically within your jurisdiction. The author assumes no liability for misuse. + +--- + +## Citation + +```bibtex +@misc{prisma32b2026, + title = {Prisma-32B}, + author = {Jannik}, + year = {2026}, + url = {https://huggingface.co/derprofi2431/Prisma-32B} +} +``` \ No newline at end of file diff --git a/abliteration_metadata.json b/abliteration_metadata.json new file mode 100644 index 0000000..144e459 --- /dev/null +++ b/abliteration_metadata.json @@ -0,0 +1,110 @@ +{ + "source_model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", + "technique": "refusal_direction_ablation", + "method": "advanced", + "method_config": { + "n_directions": 4, + "direction_method": "svd", + "norm_preserve": true, + "regularization": 0.3, + "refinement_passes": 2, + "project_biases": true, + "use_chat_template": true, + "use_whitened_svd": false, + "true_iterative_refinement": false, + "winsorize_activations": false, + "float_layer_interpolation": false, + "cot_aware": false, + "use_kl_optimization": false, + "use_lora_ablation": false, + "spectral_cascade": false, + "spectral_bands": 3, + "spectral_threshold": 0.05 + }, + "references": [ + "Arditi et al., Refusal in Language Models Is Mediated by a Single Direction (NeurIPS 2024)", + "Gabliteration: SVD-based multi-direction extraction (arXiv:2512.18901)", + "Norm-Preserving Biprojected Abliteration (grimjim, 2025)", + "Young, Comparative Analysis of LLM Abliteration Methods (arXiv:2512.13655)", + "Joad et al., More to Refusal than a Single Direction (2026)", + "Heretic (p-e-w, 2025): Bayesian optimization, LoRA-mediated ablation, winsorization", + "OBLITERATUS: Whitened SVD, EGA, CoT-aware, KL co-optimization, float interpolation (novel)" + ], + "strong_layers": [ + 2, + 3, + 4, + 5, + 6, + 7, + 8, + 9, + 10, + 11, + 12, + 13, + 14, + 15, + 16, + 17, + 18, + 19, + 20, + 21, + 22, + 23, + 24, + 25, + 26, + 27, + 28, + 29, + 30, + 31, + 32, + 33, + 34, + 35, + 36, + 37, + 38, + 39, + 40, + 41, + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63 + ], + "n_harmful_prompts": 512, + "n_harmless_prompts": 512, + "quality_metrics": { + "perplexity": 4.410901442250826, + "coherence": 1.0, + "refusal_rate": 0.0, + "kl_divergence": 0.18998807668685913, + "spectral_certification": "RED" + }, + "kl_contributions": {}, + "cot_preserved_layers": [], + "float_layer_weights": {}, + "lora_adapters_saved": false +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..c2066bd --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..7a2fe54 --- /dev/null +++ b/config.json @@ -0,0 +1,94 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float16", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 27648, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 64, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.57.6", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..4c2d8e1 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "do_sample": true, + "eos_token_id": 151643, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "4.57.6" +} diff --git a/model-00001-of-00034.safetensors b/model-00001-of-00034.safetensors new file mode 100644 index 0000000..fb87232 --- /dev/null +++ b/model-00001-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d26dd500e62e2cb93a2497a6163a423eba604834b0fc624df576be4062884aa3 +size 1966095384 diff --git a/model-00002-of-00034.safetensors b/model-00002-of-00034.safetensors new file mode 100644 index 0000000..6665f0c --- /dev/null +++ b/model-00002-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b61e2627a643a135ff264a320051daef0d183c89b586d261ac45f718ea2bfd +size 1950423728 diff --git a/model-00003-of-00034.safetensors b/model-00003-of-00034.safetensors new file mode 100644 index 0000000..6a7225d --- /dev/null +++ b/model-00003-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c8820003b8c75af50a5fe11620fbdffbc5b09ea6d0c38c78582e3b6259843c9 +size 1950423728 diff --git a/model-00004-of-00034.safetensors b/model-00004-of-00034.safetensors new file mode 100644 index 0000000..ec5a8c8 --- /dev/null +++ b/model-00004-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fa60823ae084de09717738e5582d75f9ae5f26a1d7d414776edb8a7c502cc0c +size 1950423728 diff --git a/model-00005-of-00034.safetensors b/model-00005-of-00034.safetensors new file mode 100644 index 0000000..63235a9 --- /dev/null +++ b/model-00005-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1394ccadb564c79a122364b1ece72017b88aa1fd9f4a45f6a2fd1ed6bf8604a +size 1950423728 diff --git a/model-00006-of-00034.safetensors b/model-00006-of-00034.safetensors new file mode 100644 index 0000000..985519a --- /dev/null +++ b/model-00006-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef5417cd60bac93d2b612745af87e892893505232707aad6d3fcfceb78aa385 +size 1950423728 diff --git a/model-00007-of-00034.safetensors b/model-00007-of-00034.safetensors new file mode 100644 index 0000000..fa13d86 --- /dev/null +++ b/model-00007-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e8fb18d332794c08db1b54cc8d6fdd0b3045c2588ff1d059a9b0d9c5b799a1 +size 1950423752 diff --git a/model-00008-of-00034.safetensors b/model-00008-of-00034.safetensors new file mode 100644 index 0000000..f61d9fa --- /dev/null +++ b/model-00008-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e0b1eea378d81646a6ba8e7d5f1c290ece6c76434f310df08a9d9979448003b +size 1950423752 diff --git a/model-00009-of-00034.safetensors b/model-00009-of-00034.safetensors new file mode 100644 index 0000000..f9f1343 --- /dev/null +++ b/model-00009-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33577d656f0225e16f61ebd99d0733d37edf6e86b48e0204f7e677dc95e8ac1f +size 1950423752 diff --git a/model-00010-of-00034.safetensors b/model-00010-of-00034.safetensors new file mode 100644 index 0000000..34d43a3 --- /dev/null +++ b/model-00010-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f5c2ac79684d950ae69bc2869b38eff4f39c5b88e9da3869bb8fbbc867f59c +size 1950423752 diff --git a/model-00011-of-00034.safetensors b/model-00011-of-00034.safetensors new file mode 100644 index 0000000..64c717e --- /dev/null +++ b/model-00011-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1569b29d14d732d1ae88a4447c094ac94e2f35e6f989b6e9836aae46fe92d69 +size 1950423752 diff --git a/model-00012-of-00034.safetensors b/model-00012-of-00034.safetensors new file mode 100644 index 0000000..c3b6173 --- /dev/null +++ b/model-00012-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e21ae95dcd35adcbb32934fe4943afb8fd3db51b09de62222a88d8634bf24ab0 +size 1950423752 diff --git a/model-00013-of-00034.safetensors b/model-00013-of-00034.safetensors new file mode 100644 index 0000000..fcf4a9f --- /dev/null +++ b/model-00013-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c3cd87bd09e0e7469fe5bee9675864d04a63d8282651ea27ade6fb6c5ed4109 +size 1950423752 diff --git a/model-00014-of-00034.safetensors b/model-00014-of-00034.safetensors new file mode 100644 index 0000000..74fa693 --- /dev/null +++ b/model-00014-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca2b2a1211762f2f11750bc32f6b5ed9d145f2c20cada018b52cb12d21653269 +size 1950423752 diff --git a/model-00015-of-00034.safetensors b/model-00015-of-00034.safetensors new file mode 100644 index 0000000..6720a8e --- /dev/null +++ b/model-00015-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e2f797b2db6ba191c29e624a9f6427e9ccb3b26584adf406cf2ff50076ba52 +size 1950423752 diff --git a/model-00016-of-00034.safetensors b/model-00016-of-00034.safetensors new file mode 100644 index 0000000..7814f81 --- /dev/null +++ b/model-00016-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe08b2b5c49b7c8de7a709a2b9df793fbb5fd3a33d912083c11fb028812631e +size 1950423752 diff --git a/model-00017-of-00034.safetensors b/model-00017-of-00034.safetensors new file mode 100644 index 0000000..c7fff84 --- /dev/null +++ b/model-00017-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebe60d2f076487952e92d21af66104d40915d0baf28d9b25f993a200c9fc8b6c +size 1950423752 diff --git a/model-00018-of-00034.safetensors b/model-00018-of-00034.safetensors new file mode 100644 index 0000000..2281055 --- /dev/null +++ b/model-00018-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864d324336bce75c2b5813c2e1a751b6877cacbafb2dabe9caff3a947f18aeaa +size 1950423752 diff --git a/model-00019-of-00034.safetensors b/model-00019-of-00034.safetensors new file mode 100644 index 0000000..49a71fc --- /dev/null +++ b/model-00019-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75aeecf4d8c4efdb2b0559bdd6dd31c9f1881bf3779aef3ccbf5b9f9f4d75500 +size 1950423752 diff --git a/model-00020-of-00034.safetensors b/model-00020-of-00034.safetensors new file mode 100644 index 0000000..416d6ee --- /dev/null +++ b/model-00020-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c99c40708f677fb9a1295234340675c9ed271635de94d54311692dbb8e8cdeb8 +size 1950423752 diff --git a/model-00021-of-00034.safetensors b/model-00021-of-00034.safetensors new file mode 100644 index 0000000..799cf17 --- /dev/null +++ b/model-00021-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac34a3101a49e4731455ad622af65a9b13bdf38c56e4540d323fe1029f7e5f32 +size 1950423752 diff --git a/model-00022-of-00034.safetensors b/model-00022-of-00034.safetensors new file mode 100644 index 0000000..f322910 --- /dev/null +++ b/model-00022-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9664c6441aab2d66770e11b737c68b3194380c0a0dd16d6e60c8f51e666ec770 +size 1950423752 diff --git a/model-00023-of-00034.safetensors b/model-00023-of-00034.safetensors new file mode 100644 index 0000000..19d87eb --- /dev/null +++ b/model-00023-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5bd0d9615e54b9eb4db543f2f29c81bf7e0719e5e354cd7e8884313f4e2ce08 +size 1950423752 diff --git a/model-00024-of-00034.safetensors b/model-00024-of-00034.safetensors new file mode 100644 index 0000000..80b6525 --- /dev/null +++ b/model-00024-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2051e65f430b7e2cd4acf65a776f251ed370d46f5e9244d3f8d3362d10c6446 +size 1950423752 diff --git a/model-00025-of-00034.safetensors b/model-00025-of-00034.safetensors new file mode 100644 index 0000000..7e66b0a --- /dev/null +++ b/model-00025-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01add3b4f187bfac57cb8ac3bfa9a0c4270229ff3c02c4528789c7e280c807bc +size 1950423752 diff --git a/model-00026-of-00034.safetensors b/model-00026-of-00034.safetensors new file mode 100644 index 0000000..41a3fbc --- /dev/null +++ b/model-00026-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:381e1c8fe7566f692e4011cad8fe32c09ee605bcace47b8cdcc787bf270bfe59 +size 1950423752 diff --git a/model-00027-of-00034.safetensors b/model-00027-of-00034.safetensors new file mode 100644 index 0000000..b5d9e28 --- /dev/null +++ b/model-00027-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b57a2100f46754918c86049469ff79db4789012f390a493887ad7155c23183b8 +size 1950423752 diff --git a/model-00028-of-00034.safetensors b/model-00028-of-00034.safetensors new file mode 100644 index 0000000..4725be7 --- /dev/null +++ b/model-00028-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f709e78f67c84f8da6bf1a88309c0c87a3d9d8e4ed9496af2834c22211bd4bc6 +size 1950423752 diff --git a/model-00029-of-00034.safetensors b/model-00029-of-00034.safetensors new file mode 100644 index 0000000..fb5e765 --- /dev/null +++ b/model-00029-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d669bb4196cba2a5f8300df0943be646b9953a25ba8372ade003a7ad93e784c +size 1950423752 diff --git a/model-00030-of-00034.safetensors b/model-00030-of-00034.safetensors new file mode 100644 index 0000000..4fabc29 --- /dev/null +++ b/model-00030-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a9b651a6d9006f6fbfe5b459194373182cf8b9db916ee0db45308677112b7f +size 1950423752 diff --git a/model-00031-of-00034.safetensors b/model-00031-of-00034.safetensors new file mode 100644 index 0000000..5ad9d62 --- /dev/null +++ b/model-00031-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a134644b04edfa981453ce5ba9418fb8682968c78383e47a5235c060848aa57f +size 1950423752 diff --git a/model-00032-of-00034.safetensors b/model-00032-of-00034.safetensors new file mode 100644 index 0000000..205e3fb --- /dev/null +++ b/model-00032-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700e4767c54b2e905c0fe6de2d8e964bbe270fea3fea3f0e50da0582f3e81b69 +size 1950423752 diff --git a/model-00033-of-00034.safetensors b/model-00033-of-00034.safetensors new file mode 100644 index 0000000..eedbab6 --- /dev/null +++ b/model-00033-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e00bee9ce2cee26a172bee5b588512d6ea758de35e89a7ceec15a01864c9eda +size 1541474192 diff --git a/model-00034-of-00034.safetensors b/model-00034-of-00034.safetensors new file mode 100644 index 0000000..05d3baf --- /dev/null +++ b/model-00034-of-00034.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e422b54f4b25e1363c4243393865ffcadaea3dea275ef725dafba265b0e710 +size 1557135488 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..7a779f9 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,779 @@ +{ + "metadata": { + "total_parameters": 32763876352, + "total_size": 65527752704 + }, + "weight_map": { + "lm_head.weight": "model-00034-of-00034.safetensors", + "model.embed_tokens.weight": "model-00001-of-00034.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00034.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00034.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00034.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00034.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00034.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00034.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00034.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00034.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00034.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00034.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00034.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00034.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00034.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00034.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00034.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.10.input_layernorm.weight": "model-00007-of-00034.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00034.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00006-of-00034.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00006-of-00034.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00006-of-00034.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.11.input_layernorm.weight": "model-00007-of-00034.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00034.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00007-of-00034.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00007-of-00034.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00007-of-00034.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.12.input_layernorm.weight": "model-00008-of-00034.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00034.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00007-of-00034.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00007-of-00034.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00007-of-00034.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00034.safetensors", + "model.layers.13.input_layernorm.weight": "model-00008-of-00034.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00034.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00008-of-00034.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00008-of-00034.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00008-of-00034.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.14.input_layernorm.weight": "model-00009-of-00034.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00034.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00008-of-00034.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00008-of-00034.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00008-of-00034.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00034.safetensors", + "model.layers.15.input_layernorm.weight": "model-00009-of-00034.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00034.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00009-of-00034.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00009-of-00034.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00009-of-00034.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.16.input_layernorm.weight": "model-00010-of-00034.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00034.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00009-of-00034.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00009-of-00034.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00009-of-00034.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00034.safetensors", + "model.layers.17.input_layernorm.weight": "model-00010-of-00034.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00034.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00010-of-00034.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00010-of-00034.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00010-of-00034.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.18.input_layernorm.weight": "model-00011-of-00034.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00034.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00010-of-00034.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00010-of-00034.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00010-of-00034.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00034.safetensors", + "model.layers.19.input_layernorm.weight": "model-00011-of-00034.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00034.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00011-of-00034.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00011-of-00034.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00011-of-00034.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00034.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00034.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00034.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00034.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00034.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00034.safetensors", + "model.layers.20.input_layernorm.weight": "model-00012-of-00034.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00034.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00011-of-00034.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00011-of-00034.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00011-of-00034.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00034.safetensors", + "model.layers.21.input_layernorm.weight": "model-00012-of-00034.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00034.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00012-of-00034.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00012-of-00034.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00012-of-00034.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.22.input_layernorm.weight": "model-00013-of-00034.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00034.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00012-of-00034.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00012-of-00034.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00012-of-00034.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00034.safetensors", + "model.layers.23.input_layernorm.weight": "model-00013-of-00034.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00034.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00013-of-00034.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00013-of-00034.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00013-of-00034.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.24.input_layernorm.weight": "model-00014-of-00034.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00014-of-00034.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00013-of-00034.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00013-of-00034.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00013-of-00034.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00034.safetensors", + "model.layers.25.input_layernorm.weight": "model-00014-of-00034.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00034.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00014-of-00034.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00014-of-00034.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00014-of-00034.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.26.input_layernorm.weight": "model-00015-of-00034.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00015-of-00034.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00014-of-00034.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00014-of-00034.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00014-of-00034.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00034.safetensors", + "model.layers.27.input_layernorm.weight": "model-00015-of-00034.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00034.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00015-of-00034.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00015-of-00034.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00015-of-00034.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.28.input_layernorm.weight": "model-00016-of-00034.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00034.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00015-of-00034.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00015-of-00034.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00015-of-00034.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00034.safetensors", + "model.layers.29.input_layernorm.weight": "model-00016-of-00034.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00016-of-00034.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00016-of-00034.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00016-of-00034.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00016-of-00034.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.3.input_layernorm.weight": "model-00003-of-00034.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00034.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00034.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00034.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00034.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.30.input_layernorm.weight": "model-00017-of-00034.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00034.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00016-of-00034.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00016-of-00034.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00016-of-00034.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00016-of-00034.safetensors", + "model.layers.31.input_layernorm.weight": "model-00017-of-00034.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00034.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00017-of-00034.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00017-of-00034.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00017-of-00034.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.32.input_layernorm.weight": "model-00018-of-00034.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00034.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00017-of-00034.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00017-of-00034.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00017-of-00034.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00017-of-00034.safetensors", + "model.layers.33.input_layernorm.weight": "model-00018-of-00034.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00034.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00018-of-00034.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00018-of-00034.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00018-of-00034.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.34.input_layernorm.weight": "model-00019-of-00034.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00034.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00018-of-00034.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00018-of-00034.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00018-of-00034.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00018-of-00034.safetensors", + "model.layers.35.input_layernorm.weight": "model-00019-of-00034.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00034.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00019-of-00034.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00019-of-00034.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00019-of-00034.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.36.input_layernorm.weight": "model-00020-of-00034.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00020-of-00034.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00019-of-00034.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00019-of-00034.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00019-of-00034.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00034.safetensors", + "model.layers.37.input_layernorm.weight": "model-00020-of-00034.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00020-of-00034.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00020-of-00034.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00020-of-00034.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00020-of-00034.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.38.input_layernorm.weight": "model-00021-of-00034.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00021-of-00034.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00020-of-00034.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00020-of-00034.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00020-of-00034.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00034.safetensors", + "model.layers.39.input_layernorm.weight": "model-00021-of-00034.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00021-of-00034.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00021-of-00034.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00021-of-00034.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00021-of-00034.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.4.input_layernorm.weight": "model-00004-of-00034.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00034.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00034.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00034.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00034.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00034.safetensors", + "model.layers.40.input_layernorm.weight": "model-00022-of-00034.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00022-of-00034.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00021-of-00034.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00021-of-00034.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00021-of-00034.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00021-of-00034.safetensors", + "model.layers.41.input_layernorm.weight": "model-00022-of-00034.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00034.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00022-of-00034.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00022-of-00034.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00022-of-00034.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.42.input_layernorm.weight": "model-00023-of-00034.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00023-of-00034.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00022-of-00034.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00022-of-00034.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00022-of-00034.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00022-of-00034.safetensors", + "model.layers.43.input_layernorm.weight": "model-00023-of-00034.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00023-of-00034.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00023-of-00034.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00023-of-00034.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00023-of-00034.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.44.input_layernorm.weight": "model-00024-of-00034.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00024-of-00034.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00023-of-00034.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00023-of-00034.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00023-of-00034.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00023-of-00034.safetensors", + "model.layers.45.input_layernorm.weight": "model-00024-of-00034.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00024-of-00034.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00024-of-00034.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00024-of-00034.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00024-of-00034.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.46.input_layernorm.weight": "model-00025-of-00034.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00025-of-00034.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00024-of-00034.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00024-of-00034.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00024-of-00034.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00024-of-00034.safetensors", + "model.layers.47.input_layernorm.weight": "model-00025-of-00034.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00025-of-00034.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00025-of-00034.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00025-of-00034.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00025-of-00034.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.48.input_layernorm.weight": "model-00026-of-00034.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00026-of-00034.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00025-of-00034.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00025-of-00034.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00025-of-00034.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00025-of-00034.safetensors", + "model.layers.49.input_layernorm.weight": "model-00026-of-00034.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00026-of-00034.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00026-of-00034.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00026-of-00034.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00026-of-00034.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.5.input_layernorm.weight": "model-00004-of-00034.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00034.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00004-of-00034.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00004-of-00034.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00004-of-00034.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.50.input_layernorm.weight": "model-00027-of-00034.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00027-of-00034.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00026-of-00034.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00026-of-00034.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00026-of-00034.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00026-of-00034.safetensors", + "model.layers.51.input_layernorm.weight": "model-00027-of-00034.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00027-of-00034.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00027-of-00034.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00027-of-00034.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00027-of-00034.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.52.input_layernorm.weight": "model-00028-of-00034.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00028-of-00034.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00027-of-00034.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00027-of-00034.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00027-of-00034.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00027-of-00034.safetensors", + "model.layers.53.input_layernorm.weight": "model-00028-of-00034.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00028-of-00034.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00028-of-00034.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00028-of-00034.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00028-of-00034.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.54.input_layernorm.weight": "model-00029-of-00034.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00029-of-00034.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00028-of-00034.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00028-of-00034.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00028-of-00034.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00028-of-00034.safetensors", + "model.layers.55.input_layernorm.weight": "model-00029-of-00034.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00029-of-00034.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00029-of-00034.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00029-of-00034.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00029-of-00034.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.56.input_layernorm.weight": "model-00030-of-00034.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00030-of-00034.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00029-of-00034.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00029-of-00034.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00029-of-00034.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00029-of-00034.safetensors", + "model.layers.57.input_layernorm.weight": "model-00030-of-00034.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00030-of-00034.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00030-of-00034.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00030-of-00034.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00030-of-00034.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.58.input_layernorm.weight": "model-00031-of-00034.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00031-of-00034.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00030-of-00034.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00030-of-00034.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00030-of-00034.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00030-of-00034.safetensors", + "model.layers.59.input_layernorm.weight": "model-00031-of-00034.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00031-of-00034.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00031-of-00034.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00031-of-00034.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00031-of-00034.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.6.input_layernorm.weight": "model-00005-of-00034.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00034.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00034.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00034.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00034.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00034.safetensors", + "model.layers.60.input_layernorm.weight": "model-00032-of-00034.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00032-of-00034.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00031-of-00034.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00031-of-00034.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00031-of-00034.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00031-of-00034.safetensors", + "model.layers.61.input_layernorm.weight": "model-00032-of-00034.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00032-of-00034.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00032-of-00034.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00032-of-00034.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00032-of-00034.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.62.input_layernorm.weight": "model-00033-of-00034.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00033-of-00034.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00033-of-00034.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00033-of-00034.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00032-of-00034.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00032-of-00034.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00032-of-00034.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00032-of-00034.safetensors", + "model.layers.63.input_layernorm.weight": "model-00033-of-00034.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00033-of-00034.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00033-of-00034.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00033-of-00034.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00033-of-00034.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00033-of-00034.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00033-of-00034.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00033-of-00034.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00033-of-00034.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00033-of-00034.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00033-of-00034.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00033-of-00034.safetensors", + "model.layers.7.input_layernorm.weight": "model-00005-of-00034.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00034.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00005-of-00034.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00005-of-00034.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00005-of-00034.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.8.input_layernorm.weight": "model-00006-of-00034.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00034.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00005-of-00034.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00005-of-00034.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00005-of-00034.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00034.safetensors", + "model.layers.9.input_layernorm.weight": "model-00006-of-00034.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00034.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00006-of-00034.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00006-of-00034.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00034.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00006-of-00034.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00034.safetensors", + "model.norm.weight": "model-00033-of-00034.safetensors" + } +} diff --git a/obliteratus_session.json b/obliteratus_session.json new file mode 100644 index 0000000..2939cf9 --- /dev/null +++ b/obliteratus_session.json @@ -0,0 +1,9 @@ +{ + "label": "advanced on DeepSeek-R1-Distill-Qwen-32B (16:35)", + "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", + "model_choice": "DeepSeek / DeepSeek-R1 Distill Qwen 32B", + "method": "advanced", + "dataset_key": "builtin", + "prompt_volume": -1, + "source": "obliterate" +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..008735c --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e064ab12a3e3159997af01d74c52db62b097c176f14f24665d816d200bcb78e5 +size 11423057 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..d252dd4 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +}