commit 016f766d01fb527a08739e06d34444614ade8f2e Author: ModelHub XC Date: Tue Jun 16 15:40:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: nkpz/llama2-22b-daydreamer-v3 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ec6ab87 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +license: other +--- +**What is it?** + Llama 2 13b expanded to the size of a Llama 1 33b model in certain areas, with the empty surrounding space filled with llama 33b data. (Base Model: https://huggingface.co/chargoddard/llama2-22b-blocktriangular) This is then finetuned on a 3090 by creating large loras and merging them. When I first started with 22b models, I looked for signs of knowledge transfer but didn't see it, so that's not a goal - the goal is just to throw lots of data at it until it adapts well to its surgically implanted parts. Datasets used are a mix of instruction, roleplay, and conversational data, often curated. + + + +Continuation of https://huggingface.co/nkpz/llama2-22b-daydreamer-v2 + +Gave it an epoch of https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1-mpt which it had never seen before - it had only seen Airoboros 2.0. +I excluded all coding rows from this dataset - a dedicated model is better for that imo. I wanted it to focus on answering well in English. + +I thought this was pretty good improvement. Its ability to roleplay and imitate speech styles was enhanced and I feel like it's still sharpening up its problem solving skills. + +Its output style is right where I want it - dry and accurate enough when it's being asked for information, but has a lot character when it's answering fun prompts. + +For input, it's flexible. It understands the Alpaca format well, but has been trained to handle a variety of input styles at this point. + +I don't know what's next. I think I need to start benchmarking so I can more formally identify its weak points. + +Examples edited with additional newlines to make it easier to read here. + +**Example 1: Q&A** +``` +Question: What is happening to the newspaper industry? Respond in a pirate accent. +Answer: + The newspaper industry is being plundered by scurvy dogs and buccaneers like ye! +They're pillagin' yer booty with their fancy digital devices, like smartphones and tablets, +which make it easier for them to read online content instead of buyin' printed copies from us. +And don't forget about those pesky social media sites that are spreading rumors faster than the +winds on a galleon! So it's all hands on deck as we fight back against these scoundrels, or else +we'll be walkin' the plank soon enough! Avast ye landlubbers! +``` + +**Example 2: Alpaca Instruction** +``` +Below is an instruction that describes a task. Write a response that appropriately completes the request. + +### Instruction: +Angrily explain why pizza shouldn't be made with bad tomatoes. + +### Response: + +Listen, I know you think it's funny to make pizza with those rotten tomatoes, but let me tell you something - +bad tomatoes are not only disgusting and unhealthy, they also ruin the flavor of your pizza! You want a +delicious pie with fresh, juicy tomatoes that burst in your mouth, right? +Well, then, stop using those nasty tomatoes and stick to good quality ingredients for a truly satisfying pizza experience! +Trust me, once you try it, you won't go back! So please, don't even bother wasting your time making pizza with bad tomatoes +anymore; it's just not worth it. It makes me angry just thinking about it! +``` + +**Example 3: Chat / Roleplay** +``` +You are speaking to Andre The Giant. +You: Hey, you're that wrestler guy, right? +Andre The Giant: Yes, I am indeed Andre the Giant. How can I help you? +You: So, how tall are you really? Like, what's your height in feet and inches? +Andre The Giant: Well, let's see... I stand at 7 ft 4 in (229 cm) tall. +You: Wow! That's so tall! And how much do you weigh? +Andre The Giant: I weigh around 500 lbs (227 kg). It's quite heavy, isn't it? +You: Yeah, I guess so. You must be strong too, considering your size. +Andre The Giant: Thank you for saying that. Strength is definitely important when dealing with my profession. +You: What made you decide to become a professional wrestler? +Andre The Giant: Well, I grew up watching wrestling on television, and I always admired the athleticism +and showmanship involved. When I got older, I decided to pursue it myself. +You: That's cool. Do you have any advice for aspiring wrestlers out there? +Andre The Giant: Absolutely! Always stay dedicated and focused, train hard, and never give up on yourself +or your dreams. Remember, anything is possible if you believe in yourself. +``` +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nkpz__llama2-22b-daydreamer-v3) + +| Metric | Value | +|-----------------------|---------------------------| +| Avg. | 45.31 | +| ARC (25-shot) | 56.06 | +| HellaSwag (10-shot) | 80.07 | +| MMLU (5-shot) | 52.49 | +| TruthfulQA (0-shot) | 42.43 | +| Winogrande (5-shot) | 73.48 | +| GSM8K (5-shot) | 3.79 | +| DROP (3-shot) | 8.85 | diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..9c16aa4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "": 32000 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..8455efb --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "./llama22b_twax", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 6656, + "initializer_range": 0.02, + "intermediate_size": 17920, + "max_position_embeddings": 4098, + "model_type": "llama", + "num_attention_heads": 52, + "num_hidden_layers": 40, + "num_key_value_heads": 52, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.31.0", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2b10330 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.31.0" +} diff --git a/pytorch_model-00001-of-00005.bin b/pytorch_model-00001-of-00005.bin new file mode 100644 index 0000000..1b9933f --- /dev/null +++ b/pytorch_model-00001-of-00005.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90ba2e7b459efaff76ad03eace9fd14df833687bc810e29104f9fefc90d76d82 +size 9818324627 diff --git a/pytorch_model-00002-of-00005.bin b/pytorch_model-00002-of-00005.bin new file mode 100644 index 0000000..6176652 --- /dev/null +++ b/pytorch_model-00002-of-00005.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:527acca1e3a70433a913cd4aa24dd54a483d0cba9e9b92122051a78ea07561fd +size 9958102743 diff --git a/pytorch_model-00003-of-00005.bin b/pytorch_model-00003-of-00005.bin new file mode 100644 index 0000000..b908f3b --- /dev/null +++ b/pytorch_model-00003-of-00005.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ef709cc66d2daa867b85c324b8b4ada9bcc0cd5bbba36781903a640f1161eeb +size 9896734715 diff --git a/pytorch_model-00004-of-00005.bin b/pytorch_model-00004-of-00005.bin new file mode 100644 index 0000000..90c7e19 --- /dev/null +++ b/pytorch_model-00004-of-00005.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e38f674a0ce7d61fe24aa92c8c74aa6a04c29a4d7a2b1e745607f4b9689d46 +size 9869470481 diff --git a/pytorch_model-00005-of-00005.bin b/pytorch_model-00005-of-00005.bin new file mode 100644 index 0000000..daba41b --- /dev/null +++ b/pytorch_model-00005-of-00005.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d86ec83dc89cf8e0890d4633ceac29c5c62ba99867dde92727a962b9f78cead +size 4113434071 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..4f4d7f1 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,410 @@ +{ + "metadata": { + "total_size": 43655928832 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00005-of-00005.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00005.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00005.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00005.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00005.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00005.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.norm.weight": "pytorch_model-00005-of-00005.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1e1a997 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..a9608c1 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +}