Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Snow_Lotus_Logo.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,42 @@
+---
+license: apache-2.0
+tags:
+- Roleplay
+- Solar
+- Mistral
+- Text Generation
+---
+![SnowLotus Logo](https://cdn-uploads.huggingface.co/production/uploads/64bb1109aaccfd28b023bcec/gTQtPK46laLIFg0RTAv73.png)
+
+### Premise
+
+So this is a basic slerp merge between a smart model and a good prose model. Prose and smarts. What we all want in an uncensored RP model right? I feel like Solar has untapped potential, in any case. 
+
+Sao10K's Frostwind finetune is a key component of the mixture, its smarts are impressive. NyxKrage's Frostmaid experiment, which merges Frostwind with a frankenmerge of Noromaid and a mystery medical model, delivers quite impressive prose. His model creatively incorporates long-range context and instructions too, despite being slightly incoherent due to the fraken merging. 
+
+So those are the main ingredients. Thanks to Nyx for sorting out the pytorch files btw. 
+
+### Recipe
+
+So, the recipe. I basically just gradient SLERP'd Frostwind into Frostmaid with these params:
+
+- filter: self_attn
+      value: [0.9, 0.6, 0.3, 0, 0]
+    - filter: mlp
+      value: [0.3, 0.6]
+    - value: 0.5 # fallback for rest of tensors
+
+
+### Tentative Dozen or So Test Conclusion
+
+This made a model that was actually pretty much everything I was looking for - NEARLY as smart as Frostwind but with MOST of Frostmaids punchy prose. I tried doing TIES merges and DARE ties merges, but they actually came out worse, because both models have major weaknesses - one is very dry and gpt-ish, the other is a little loose with what's going on. The ties merges tended to bring out those qualities, dare even worse. So I stuck with this. It's not AS smart as Frostwind, so you maybe have to regen a little, but it's pretty smart, and quite creative. A sweet spot hopefully. Maybe someone merge wiser than I can do more with this recipe, but I'm very pleased with it, it did what I was hoping for - a smaller model I can mobile dgpu and produces pretty outsized quality responses (it's fairly zealous tho, be warned). I've only played with it a TINY bit, so there may be qualities or flaws I've missed. 
+
+Cheers to all the finetuners, mergers and developers without which open source models wouldn't be half of what they are. 
+
+Resources used:
+
+https://huggingface.co/NyxKrage/FrostMaid-10.7B-TESTING-pt
+
+https://huggingface.co/Sao10K/Frostwind-10.7B-v1
+
+https://github.com/cg123/mergekit/tree/main

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "./FrostNymph",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,7 @@
+models:
+  - model: ./FrostNymph
+merge_method: passthrough
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "lm_head.weight": "model-00011-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe61891042b15a86ec772289d914c513527c01fbcdc4fe2424a246019a9d536
+size 6917616292

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}