初始化项目，由ModelHub XC社区提供模型

Model: Sao10K/Llama-3.1-8B-Stheno-v3.4
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+meneno.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+license: cc-by-nc-4.0
+datasets:
+- Setiaku/Stheno-v3.4-Instruct
+- Setiaku/Stheno-3.4-Creative-2
+language:
+- en
+---
+
+![img](https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4/resolve/main/meneno.jpg)
+
+---
+
+Thanks to Backyard.ai for the compute to train this. :)
+
+---
+
+Llama-3.1-8B-Stheno-v3.4
+
+This model has went through a multi-stage finetuning process.
+```
+- 1st, over a multi-turn Conversational-Instruct
+- 2nd, over a Creative Writing / Roleplay along with some Creative-based Instruct Datasets.
+- - Dataset consists of a mixture of Human and Claude Data.
+```
+
+Prompting Format:
+```
+- Use the L3 Instruct Formatting - Euryale 2.1 Preset Works Well
+- Temperature + min_p as per usual, I recommend 1.4 Temp + 0.2 min_p.
+- Has a different vibe to previous versions. Tinker around.
+```
+
+Changes since previous Stheno Datasets:
+```
+- Included Multi-turn Conversation-based Instruct Datasets to boost multi-turn coherency. # This is a seperate set, not the ones made by Kalomaze and Nopm, that are used in Magnum. They're completely different data.
+- Replaced Single-Turn Instruct with Better Prompts and Answers by Claude 3.5 Sonnet and Claude 3 Opus.
+- Removed c2 Samples -> Underway of re-filtering and masking to use with custom prefills. TBD
+- Included 55% more Roleplaying Examples based of [Gryphe's](https://huggingface.co/datasets/Gryphe/Sonnet3.5-Charcard-Roleplay) Charcard RP Sets. Further filtered and cleaned on.
+- Included 40% More Creative Writing Examples.
+- Included Datasets Targeting System Prompt Adherence.
+- Included Datasets targeting Reasoning / Spatial Awareness.
+- Filtered for the usual errors, slop and stuff at the end. Some may have slipped through, but I removed nearly all of it.
+```
+
+Personal Opinions:
+```
+- Llama3.1 was more disappointing, in the Instruct Tune? It felt overbaked, atleast. Likely due to the DPO being done after their SFT Stage.
+- Tuning on L3.1 base did not give good results, unlike when I tested with Nemo base. unfortunate.
+- Still though, I think I did an okay job. It does feel a bit more distinctive.
+- It took a lot of tinkering, like a LOT to wrangle this.
+```
+
+Below are some graphs and all for you to observe.
+
+---
+
+`Turn Distribution # 1 Turn is considered as 1 combined Human/GPT pair in a ShareGPT format. 4 Turns means 1 System Row + 8 Human/GPT rows in total.`
+
+![Turn](https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4/resolve/main/turns_distribution_bar_graph.png)
+
+`Token Count Histogram # Based on the Llama 3 Tokenizer`
+
+![Turn](https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4/resolve/main/token_count_histogram.png)
+
+---
+
+Have a good one.
+
+```
+Source Image: https://www.pixiv.net/en/artworks/91689070
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "Sao10K/Llama-3.1-8B-Stheno-v3.4",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.4"
+}

meneno.jpg

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9ac0aabacc4348e3befa9015ea2a491adb34c0e165e1007415fea5592ac11e
+size 1689246

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baac7aef02592bcdb5f4e5bcf84cf2ef024b80663ba4c376342e8f30a1697da0
+size 1973455376

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e420c391c1ce606ebef3cdcea19211a9c9b6b53d9489fcc03b56089df21625
+size 1895895336

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f23b247a095c3306d3efdd196dd0dbd35dffe60834b34c733162f72c5b813d22
+size 1979798040

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe0097bf8c9ceeba55f26d56c3ad5be0a00062b12912bcf112d87cc141e7eff
+size 1946227368

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b03c56f26b5e97f1bd43934325f5ef35965a28a49bda84dc0fb10ea485df9688
+size 1979798064

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f80fd6c0b997d79c50097affe0f2f2d3fe99810729924f973b65326de7c16f
+size 1946227368

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1312786280a1a3a55e5b74add9e111c3364255ccfdbb4ee7784ac418a5427f58
+size 1979798064

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea349f01a9f70028309dc41f584e6ef0a2675c47fd8f5262fd8ec5125e2e9706
+size 1308683424

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5321ca97dd0968a3e2b676b3a42728e9f5327d516bcf0addd4e9cd61c068a1ad
+size 1050673280

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.norm.weight": "model-00008-of-00009.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}