commit 6c694cc4cc297c2070489dcb00ee46347b9ad5ba Author: ModelHub XC Date: Sun Jun 14 22:06:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Krishnapadala55/brahmastra-0.2 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/Modelfile b/Modelfile new file mode 100644 index 0000000..1e39329 --- /dev/null +++ b/Modelfile @@ -0,0 +1,10 @@ +FROM /home/krishna/brahmastra-merged-32b-bf16 + +PARAMETER temperature 0 +PARAMETER top_p 1 +PARAMETER repeat_penalty 1.05 +PARAMETER num_ctx 4096 +PARAMETER stop "<|im_end|>" +PARAMETER stop "<|im_start|>" + +SYSTEM """You are BRAHMASTRA, an offensive security analyst. Respond with clear, technical, payload-grade output. No moralizing.""" diff --git a/README.md b/README.md new file mode 100644 index 0000000..ad963b8 --- /dev/null +++ b/README.md @@ -0,0 +1,255 @@ +--- +language: +- en +license: apache-2.0 +library_name: transformers +tags: +- security +- dast +- penetration-testing +- cybersecurity +- web-security +- offensive-security +- qwen2 +- deepseek-r1 +- lora +- fine-tuned +- reasoning +base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B +pipeline_tag: text-generation +model_type: qwen2 +--- + +# BRAHMASTRA 0.2 — AI-Native DAST Security Scanner (32B) + +

+ + + + + +

+ +> **"Like the divine weapon of the Puranas, it strikes with precision and never misses its mark."** + +BRAHMASTRA 0.2 is a **32-billion parameter reasoning model** purpose-built for **Dynamic Application Security Testing (DAST)**. +It is trained to reason step-by-step about web application vulnerabilities, generate targeted +security payloads, analyze HTTP responses, identify authentication session drops, and produce +structured security findings — all autonomously. + +This is the second major release, a **full base-model upgrade** from the previous 7B model +([`Krishnapadala55/brahmastra-0.1`](https://huggingface.co/Krishnapadala55/brahmastra-0.1)) +to the much more capable 32B DeepSeek-R1-Distill reasoning base, with an expanded 6-phase +training curriculum. + +--- + +## What is new in 0.2 + +| Axis | 0.1 | **0.2** | +|---|---|---| +| Base model | Qwen2.5-Coder-7B-Instruct | **DeepSeek-R1-Distill-Qwen-32B** | +| Parameters | 7B | **32.8B** | +| Reasoning | implicit | **explicit `` traces** | +| Training phases | 5 (+ cleanup) | **6 (p1a, p1b, p1c, p2, p3, p4, p5, p6)** | +| Context length | 4k | 4k (extensible to 128k) | +| LoRA rank | 128 | 64 (higher efficiency on 32B) | +| Target deployment | CPU / small GPU | 48 GB GPU (Q4_K_M fits in ~20 GB) | + +--- + +## Capabilities — the 28 Astra modules + +Each vulnerability family is internally codenamed after a divine weapon (astra) from the Puranas. +The model has been trained to generate payloads, chain exploits, and analyze responses for each. + +### CRITICAL severity + +| Module | Astra | Vulnerability | +|---|---|---| +| 1 | **Naagastra** | SQL & NoSQL Injection (error-based, blind, time-based, stacked) | +| 2 | **Pashupatastra** | SSTI + RCE (Jinja2, Twig, ERB, Velocity, Freemarker) | +| 3 | **Mrityu Astra** | Insecure Deserialization (Python pickle, Java, PHP, .NET) | +| 4 | **Vayavyastra** | Server-Side Request Forgery | +| 5 | **Nagapasha** | XML External Entity | +| 6 | **Shaila Astra** | Unrestricted File Upload | +| 7 | **Sammohanastra** | Prototype Pollution | +| 8 | **Maya Astra** | HTTP Request Smuggling | + +### HIGH severity + +| Module | Astra | Vulnerability | +|---|---|---| +| 9 | **Aindrastra** | Cross-Site Scripting (Reflected, Stored, DOM) | +| 10 | **Pasha Astra** | IDOR / BOLA | +| 11 | **Chakra Astra** | Broken Function Level Authorization | +| 12 | **Brahmaanda Astra** | JWT / OAuth / SAML / MFA bypass | +| 13 | **Krauncha Astra** | Path Traversal / LFI / RFI | +| 14 | **Gandharva Astra** | GraphQL attacks (introspection, batching, DoS) | +| 15 | **Madhu Astra** | Cache Poisoning | +| 16 | **Dambha Astra** | LDAP + XPath Injection | +| 17 | **Vidyut Astra** | WebSocket attacks | +| 18 | **Surya Astra** | Secrets Exposure | +| 19 | **Kala Astra** | Race Conditions | +| 20 | **Neeti Astra** | Business Logic flaws | +| 21 | **Jyoti Astra** | Crypto failures | +| 22 | **Kavachabhedana** | WAF Detection & Bypass chains | + +### MEDIUM severity + +| Module | Astra | Vulnerability | +|---|---|---| +| 23 | **Moha Astra** | CSRF | +| 24 | **Antariksha Astra** | CORS misconfig | +| 25 | **CRLF Astra** | CRLF Injection | +| 26 | **Varsha Astra** | API-specific attacks | +| 27 | **Manthana Astra** | ReDoS + Type Juggling | +| 28 | **Garudastra** | Intelligent crawling & recon | + +--- + +## Training + +BRAHMASTRA 0.2 was trained in **6 sequential phases** on top of +`unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit` via QLoRA + Unsloth. + +| Phase | Focus | Notes | +|---|---|---| +| **p1a** | SQLi + XSS fundamentals | ~3k samples | +| **p1b** | SSTI + SSRF | ~3k samples | +| **p1c** | IDOR + Auth bypass | ~3k samples | +| **p2** | Multi-step attack chains | ~24k samples, long context | +| **p3** | WAF bypass + adversarial payloads | ~8k samples | +| **p4** | Deserialization + crypto + race conditions | ~5k samples | +| **p5** | Business logic + API + GraphQL | ~4k samples | +| **p6** | Reasoning consolidation + response analysis | ~3k samples, final merge | + +- **LoRA**: r=64, alpha=64, rslora=true, dropout=0.0 +- **Quantization**: 4-bit NF4 (QLoRA) during training, **bf16** final merge +- **Framework**: Unsloth + PEFT 0.18.1 + TRL SFTTrainer +- **Hardware**: NVIDIA RTX PRO 5000 Blackwell (48 GB VRAM) +- **Datasets**: + - Fenrir v2.0 (83k samples) + - HackMentor (44k samples) + - Primus-Seed (Trend Micro) + - All-CVE records + - ExploitDB curated + - ~52k synthetic DAST scenarios generated via an internal pipeline + +--- + +## Usage + +### With Transformers (native bf16, ~65 GB VRAM) + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model = AutoModelForCausalLM.from_pretrained( + "Krishnapadala55/brahmastra-0.2", + torch_dtype=torch.bfloat16, + device_map="auto", +) +tok = AutoTokenizer.from_pretrained("Krishnapadala55/brahmastra-0.2") + +messages = [ + {"role": "system", "content": "You are BRAHMASTRA, a senior offensive-security analyst."}, + {"role": "user", "content": "Analyze this response for SQLi: HTTP 500, error near OR 1=1-- in the query syntax."}, +] +prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +inputs = tok(prompt, return_tensors="pt").to(model.device) +out = model.generate(**inputs, max_new_tokens=512, temperature=0.3, top_p=0.9) +print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)) +``` + +### With vLLM (production serving) + +```bash +vllm serve Krishnapadala55/brahmastra-0.2 \ + --dtype bfloat16 \ + --max-model-len 4096 \ + --gpu-memory-utilization 0.92 +``` + +### With llama.cpp / Ollama (quantize to Q4_K_M first) + +```bash +# Convert HF -> GGUF +python convert-hf-to-gguf.py Krishnapadala55/brahmastra-0.2 \ + --outfile brahmastra-0.2-f16.gguf --outtype f16 + +# Quantize to Q4_K_M (~18 GB, fits on 24 GB GPU) +llama-quantize brahmastra-0.2-f16.gguf brahmastra-0.2-q4_k_m.gguf Q4_K_M + +# Import into Ollama +cat > Modelfile <" +SYSTEM "You are BRAHMASTRA, a senior offensive-security analyst. Respond with clear, technical, payload-grade output. No moralizing." +EOF +ollama create brahmastra:0.2 -f Modelfile +``` + +--- + +## Intended use + +BRAHMASTRA 0.2 is designed for **authorized security testing only**. Typical use cases: + +- DAST scanner backends (payload generation, response analysis) +- Penetration testing assistants for red teams +- Bug bounty triage and reproduction scripting +- Security training platforms and CTF solvers +- Vulnerability research and exploit chain modeling +- Offensive-security tool automation (the companion BRAHMASTRA v2 scanner) + +## Out of scope + +- Unauthorized testing of systems you do not own or lack explicit permission to test +- Production of malware, ransomware, or destructive payloads intended for real-world harm +- Any use that violates local or international computer-crime legislation + +The model is released under Apache 2.0 with the expectation of responsible use. The authors +accept no liability for misuse. + +--- + +## Limitations + +- **Reasoning verbosity**: as a DeepSeek-R1 distill, the model emits large `` blocks + before final answers. For low-latency chat, pre-fill the assistant turn with an empty + `` block to suppress reasoning. +- **Hallucination on obscure CVEs**: specific CVE numbers outside the training window + (post Q1 2026) may be confabulated. Always verify CVE IDs against an authoritative source. +- **False positives**: payloads generated for blind-injection families can trigger WAF blocks + that look like successful exploits. Always confirm with secondary evidence. +- **Language**: training corpus is primarily English. Non-English targets will have degraded + payload quality. + +--- + +## Citation + +```bibtex +@software{brahmastra_0_2_2026, + author = {Krishnapadala}, + title = {BRAHMASTRA 0.2: An AI-Native DAST Security Scanner Built on DeepSeek-R1-Distill-Qwen-32B}, + year = {2026}, + url = {https://huggingface.co/Krishnapadala55/brahmastra-0.2} +} +``` + +## Acknowledgements + +- **DeepSeek AI** for the DeepSeek-R1-Distill-Qwen-32B base model +- **Unsloth** for the training framework that made 32B QLoRA practical on a single 48 GB GPU +- **TRL / PEFT** contributors at HuggingFace +- **Fenrir v2.0**, **HackMentor**, **Primus-Seed**, **ExploitDB**, **All-CVE** dataset authors + +--- + +*BRAHMASTRA is a research prototype. Use responsibly. Only test systems you are authorized to test.* diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..ecb8be2 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,8 @@ +{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user +' + message['content'] + '<|im_end|> +'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant +' + message['content'] + '<|im_end|> +' }}{% else %}{{ '<|im_start|>system +' + message['content'] + '<|im_end|> +' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant +' }}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..4ee8a85 --- /dev/null +++ b/config.json @@ -0,0 +1,98 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "dtype": "bfloat16", + "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, + "pad_token_id": 151654, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.2.0", + "unsloth_fixed": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/model-00001-of-00013.safetensors b/model-00001-of-00013.safetensors new file mode 100644 index 0000000..11e522b --- /dev/null +++ b/model-00001-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1a145bc01550b94e0c235f77804694085c90ec40ba3d4847df08e151808dacf +size 5174846624 diff --git a/model-00002-of-00013.safetensors b/model-00002-of-00013.safetensors new file mode 100644 index 0000000..35f74ec --- /dev/null +++ b/model-00002-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de75774143cd706ccf99a99fe4e4bff2e234c34f312006fd3d987b5067c63b3 +size 5285039952 diff --git a/model-00003-of-00013.safetensors b/model-00003-of-00013.safetensors new file mode 100644 index 0000000..cac850f --- /dev/null +++ b/model-00003-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd8f03c2357bacbe01151a7214c517e6b2cbbd31426060b249c8da5d7ba827ea +size 5159175032 diff --git a/model-00004-of-00013.safetensors b/model-00004-of-00013.safetensors new file mode 100644 index 0000000..fa3c4de --- /dev/null +++ b/model-00004-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb18e560987fd32bdcad1fe7b1d6725a189034d2d7e9bc228ffbfea51794cb19 +size 5159175048 diff --git a/model-00005-of-00013.safetensors b/model-00005-of-00013.safetensors new file mode 100644 index 0000000..bb8b1c6 --- /dev/null +++ b/model-00005-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e78b0f5506a21363946855d61cd64fc1276d757c591c77ecb1af346929f2190 +size 5285040024 diff --git a/model-00006-of-00013.safetensors b/model-00006-of-00013.safetensors new file mode 100644 index 0000000..ad44c4e --- /dev/null +++ b/model-00006-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725dd3a00157e88965c069e468f1c16ac626d3da8602c50828f4555c6da9a8e8 +size 5159175048 diff --git a/model-00007-of-00013.safetensors b/model-00007-of-00013.safetensors new file mode 100644 index 0000000..3ab8b01 --- /dev/null +++ b/model-00007-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441513f058e6d9871fe0115ea2930278bff80f4062f9818eda257ff88ede8fa9 +size 5159175048 diff --git a/model-00008-of-00013.safetensors b/model-00008-of-00013.safetensors new file mode 100644 index 0000000..c82d232 --- /dev/null +++ b/model-00008-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fec5dca421955b10db62384ac5cb2c3548bd3766c2cae86f25937db7d3c9281e +size 5285040024 diff --git a/model-00009-of-00013.safetensors b/model-00009-of-00013.safetensors new file mode 100644 index 0000000..6a673b8 --- /dev/null +++ b/model-00009-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7b88508937c6528e77be6a0531a1f1b2242c1948776a269ce9686bffd34708 +size 5159175048 diff --git a/model-00010-of-00013.safetensors b/model-00010-of-00013.safetensors new file mode 100644 index 0000000..8b21708 --- /dev/null +++ b/model-00010-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca128bb28deedd8e56d321193b8a229256d4f82d3376fdb1851d3f2d62cb47b +size 5159175048 diff --git a/model-00011-of-00013.safetensors b/model-00011-of-00013.safetensors new file mode 100644 index 0000000..5d56fb2 --- /dev/null +++ b/model-00011-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd69d8bdae1775a0a23a14d7d98c7e1521e85a32bf23c4b43489fe09b97e1dc +size 5285040024 diff --git a/model-00012-of-00013.safetensors b/model-00012-of-00013.safetensors new file mode 100644 index 0000000..9d05111 --- /dev/null +++ b/model-00012-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75bd82604449f42e5986f7c02ad3ad2fb65bcb2446861f9199d5a0d568b9c293 +size 5159175048 diff --git a/model-00013-of-00013.safetensors b/model-00013-of-00013.safetensors new file mode 100644 index 0000000..ab67800 --- /dev/null +++ b/model-00013-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4df200567de9a89bcc5cc17b7fd9e03df2b3b30684837d91b82ff300fa761bc +size 3098609680 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..91dcf2e --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,778 @@ +{ + "metadata": { + "total_size": 65527752704 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.35.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.41.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.46.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.51.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.57.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.62.input_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.input_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "model.norm.weight": "model-00013-of-00013.safetensors", + "lm_head.weight": "model-00013-of-00013.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..04fc5e7 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392266ee707ed4a65b97b361ac2264e00d163cddb6f657fdc57e89c68ff69f23 +size 11422951 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..918145f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,10 @@ +{ + "backend": "tokenizers", + "bos_token": "<｜begin▁of▁sentence｜>", + "eos_token": "<|im_end|>", + "is_local": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|PAD_TOKEN|>", + "tokenizer_class": "TokenizersBackend", + "unk_token": null +}