初始化项目，由ModelHub XC社区提供模型

Model: Sao10K/L3-8B-Stheno-v3.2
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+170c547969d6d0c2522f3a91181008eb.png filter=lfs diff=lfs merge=lfs -text
+Stheno.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,88 @@
+---
+license: cc-by-nc-4.0
+language:
+- en
+datasets:
+- Gryphe/Opus-WritingPrompts
+- Sao10K/Claude-3-Opus-Instruct-15K
+- Sao10K/Short-Storygen-v2
+- Sao10K/c2-Logs-Filtered
+---
+
+*Just message me on discord if you want to host this privately for a service or something. We can talk.*
+
+*Train used 1x H100 SXM for like a total of 24 Hours over multiple runs.*
+
+Support me here if you're interested:
+<br>Ko-fi: https://ko-fi.com/sao10k
+<br> *wink* Euryale v2?
+
+If not, that's fine too. Feedback would be nice.
+
+Contact Me in Discord:
+<br>`sao10k` // `Just ping me in the KoboldAI discord, I'll respond faster.`
+
+`Art by navy_(navy.blue)` - [Danbooru](https://danbooru.donmai.us/posts/3214477)
+
+---
+
+![Stheno](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2/resolve/main/Stheno.png?)
+
+Stheno-v3.2-Zeta
+
+I have done a test run with multiple variations of the models, merged back to its base at various weights, different training runs too, and this Sixth iteration is the one I like most.
+
+
+Changes compared to v3.1
+<br>\- Included a mix of SFW and NSFW Storywriting Data, thanks to [Gryphe](https://huggingface.co/datasets/Gryphe/Opus-WritingPrompts)
+<br>\- Included More Instruct / Assistant-Style Data
+<br>\- Further cleaned up Roleplaying Samples from c2 Logs -> A few terrible, really bad samples escaped heavy filtering. Manual pass fixed it.
+<br>\- Hyperparameter tinkering for training, resulting in lower loss levels.
+
+
+Testing Notes - Compared to v3.1
+<br>\- Handles SFW / NSFW seperately better. Not as overly excessive with NSFW now. Kinda balanced.
+<br>\- Better at Storywriting / Narration.
+<br>\- Better at Assistant-type Tasks.
+<br>\- Better Multi-Turn Coherency -> Reduced Issues?
+<br>\- Slightly less creative? A worthy tradeoff. Still creative.
+<br>\- Better prompt / instruction adherence.
+
+---
+
+**Recommended Samplers:**
+
+```
+Temperature - 1.12-1.22
+Min-P - 0.075
+Top-K - 50
+Repetition Penalty - 1.1
+```
+
+**Stopping Strings:**
+
+```
+\n\n{{User}} # Or Equivalent, depending on Frontend
+<|eot_id|>
+<|end_of_text|>
+```
+
+**Prompting Template - Llama-3-Instruct**
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+{output}<|eot_id|>
+```
+
+**Basic Roleplay System Prompt**
+```
+You are an expert actor that can fully immerse yourself into any role given. You do not break character for any reason, even if someone tries addressing you as an AI or language model.
+Currently your role is {{char}}, which is described in detail below. As {{char}}, continue the exchange with {{user}}.
+```
+
+---

Stheno.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a40b4bedb2836a236065fcf6e2b2b506667b920d32d9dd1654d9b0764763f1
+size 1878956

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Sao10K/Stheno-v3.2-Zeta",
+  "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": 8192,
+  "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": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f365d166e0646673e52c63afed86fa3e79816d6b33dad88367dc4b064b668901
+size 4953586384

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468f6174caea125d78fc025ddd2c7dbb11663caf42c0add8e36a1ae140f98bfc
+size 4999819336

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b23e82daef4502f036d62fd647e674716188bde23cd05466ab4d293d05521f
+size 4915916144

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921ab435fce288cc690e1f83c6e93f3b03ede45796e6143de7a9bbfdbb33f4dc
+size 1191234472

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "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
+  }
+}