初始化项目，由ModelHub XC社区提供模型

Model: wave-on-discord/silly-v0.2
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,21 @@
+---
+license: apache-2.0
+base_model:
+- mistralai/Mistral-Nemo-Base-2407
+library_name: transformers
+---
+# silly-v0.2
+
+Finetune of [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) designed to emulate the writing style of character.ai models.
+
+- 2 epochs of SFT on RP data, then about an hour of PPO on 8xH100 with [POLAR-7B RFT](https://github.com/RowitZou/POLAR_RFT)
+- Kind of wonky, if you're dealing with longer messages you may need to decrease your temperature
+- ChatML chat format
+- Reviews:
+
+> its typically good at writing, v good for 12b, coherent in RP, follows context and starts conversations well
+
+> I do legit like it, it feels good to use. When it gives me stable output the output is high quality and on task, its got small model stupid where basic logic holds but it invents things or forgets them (feels like small effective context window maybe?) which, to be clear, is like. Perfectly fine. Very good st synthesizing and inferring information provided in context on a higher level
+
+
+This is mostly a proof-of-concept, showcasing that POLAR reward models can be very useful for "out of distribution" tasks like roleplaying. If you're working on your own roleplay finetunes, please consider using POLAR!

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 131072,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "use_cache": false,
+  "vocab_size": 131074
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 131072,
+  "transformers_version": "4.55.2"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc4db50b9f23e2ce2fe698467fccc40a0a7492d12e61496de0dd815c9ce0f4f
+size 4917950744

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e9958fd6335766681b80d628d235e15e2d7a01409aea4256677ed49d36ec9f
+size 4980939392

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b87f8e11f89e1c0bda85d9716ed13983bf8ad5c6791cd90791c58fc7c5920b2
+size 4896958400

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5dbbd7f689793b2d565ebfbb79a99cdfb169ab0bf40e3f7cc30a1656ee5c20
+size 4960042056

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff13f607d12170a3a818a364b94ef5cfab1c53ac0103c5a0696dcfee1cd5dc91
+size 4739757440

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_parameters": 12247802880,
+    "total_size": 24495605760
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00003-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.norm.weight": "model-00002-of-00005.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fa2956478eaa353c6c4b1f47fdd6868cce6075e52e169c35ae8bd28524e7a8
+size 17078668