Upload 14 files

README.md

@@ -0,0 +1,68 @@
+---
+license: other
+license_name: yi-34b
+license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
+---
+
+
+# Merged-Vicuna-RP-Stew-34B
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+
+Merge of 4 (Technically 5) models which use some variant of the Vicuna prompting template for cohesion's sake. Besides being decent models, Capybara was chosen at a higher percentage for it's general aptitude plus preserving longer context length, Tess-1.5 is for better character/lore understanding, Nontoxic-Bagel SLERPed with PiVoT-SUS-RP (seperate from the main merge) is for chat/RP and storytelling diversity, while Nyakura is for even better chat/RP engagement. 
+
+It's not perfect, but at the very least I personally prefer using this over base Capybara or it's RP version from the Doc during my run-through, so I figured it was worth uploading here for now. Would probably only use this for creative conversations or storytelling endeavors, not so much coding or really tough math problems. Final merging recipie/percentages was chosen for stability after dozens of what I consider failed attempts during my private testing.
+
+Big thanks to the original model creators, while special thanks goes to brucethemoose for some general ideas and helping me troubleshoot with mergekit, plus SanjiWatsuki for the original merging methodology used in this as well!
+
+### Prompt Format: Orca-Vicuna
+
+```
+SYSTEM: <ANY SYSTEM CONTEXT>
+USER: 
+ASSISTANT:
+```
+
+### Models Merged
+
+The following models were included in the merge:
+
+https://huggingface.co/migtissera/Tess-34B-v1.5b
+https://huggingface.co/NousResearch/Nous-Capybara-34B
+https://huggingface.co/jondurbin/nontoxic-bagel-34b-v0.2
+https://huggingface.co/maywell/PiVoT-SUS-RP
+https://huggingface.co/Sao10K/NyakuraV2-34B-Yi-Llama
+https://huggingface.co/chargoddard/Yi-34B-200K-Llama
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: Tess-34B-v1.5b
+    parameters:
+      weight: 0.28
+      density: 0.66
+  - model: Nous-Capybara-34B-V1.9
+    parameters:
+      weight: 0.34
+      density: 0.78
+  - model: Nontoxic-PiVoT-Bagel-RP-34B
+    parameters:
+      weight: 0.22
+      density: 0.54
+  - model: NyakuraV2-34B-Yi-Llama
+    parameters:
+      weight: 0.16
+      density: 0.42
+merge_method: dare_ties
+tokenizer_source: union
+base_model: Yi-34B-200K-Llama
+parameters:
+  int8_mask: true
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Merged-Vicuna-RP-Stew-34B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 64002
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc794889e8856569f440486f91bbcdaad4e162dfa5c82e7bf874ea1e4553d34a
+size 9843234976

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc37003da2438bcbd1c37711db324d0300fbb707abf139020fe82ff29cc3750
+size 9747829888

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440ecd7fe878aa69f050c23ba8784eb009be3dfb5009438fb4c4025d209696a8
+size 9747829912

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c2286b051d7915704224f9e07a74d247c3adea1aa0360ae7f890cda19ad1d1
+size 9806549808

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eddfa06e41a353759991268f0f6e6fd36f9ae615d0faa26753945a8677943926
+size 9747829904

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85bc2f12beb8eb186a9cfb1e77343cc9570be8b0c33eaa840ebe291e9a7faccb
+size 9747801008

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4728708ceb0824224364f554fc9361d25a965594eeb184dcedf35cec1772d6
+size 9843249496

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4357ca4dadd9f012993095fc41d6c3b0ccb72269d3f2833077389335da5b801
+size 293630312

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.52.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "lm_head.weight": "model-00007-of-00008.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors"}}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64000": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64001": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 200000,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}