08f3c3f236cf13359636ad4082457459348189b7707eec3d8212e6046452faa0

.gitattributes

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

README.md

@@ -0,0 +1,46 @@
+---
+language:
+- en
+- zh
+- ja
+- de
+license: gpl-3.0
+tags:
+- mlx
+datasets:
+- JosephusCheung/GuanacoDataset
+- meta-math/MetaMathQA
+- jondurbin/airoboros-3.1
+- WizardLM/WizardLM_evol_instruct_V2_196k
+- RyokoAI/ShareGPT52K
+- RyokoAI/Fandom23K
+- milashkaarshif/MoeGirlPedia_wikitext_raw_archive
+- wikipedia
+- wiki_lingua
+- garage-bAInd/Open-Platypus
+- LDJnr/Puffin
+- BAAI/COIG
+- TigerResearch/tigerbot-zhihu-zh-10k
+- liwu/MNBVC
+- teknium/openhermes
+- CausalLM/Refined-Anime-Text
+- microsoft/orca-math-word-problems-200k
+- m-a-p/CodeFeedback-Filtered-Instruction
+---
+
+# mlx-community/35b-beta-long-8bit
+
+The Model [mlx-community/35b-beta-long-8bit](https://huggingface.co/mlx-community/35b-beta-long-8bit) was converted to MLX format from [CausalLM/35b-beta-long](https://huggingface.co/CausalLM/35b-beta-long) using mlx-lm version **0.12.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/35b-beta-long-8bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,32 @@
+{
+    "architectures": [
+        "CohereForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 5,
+    "eos_token_id": 6,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 22528,
+    "layer_norm_eps": 1e-05,
+    "logit_scale": 0.0625,
+    "max_position_embeddings": 8192,
+    "model_type": "cohere",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 64,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 8000000.0,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.38.2",
+    "use_cache": true,
+    "vocab_size": 256000
+}

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095fa4e273c3f4e5f29b0415873c7d230552a1222d5af1bb10e379689a1223e4
+size 392201065

model.safetensors.index.json

@@ -0,0 +1,891 @@
+{
+    "metadata": {
+        "total_size": 37167448064
+    },
+    "weight_map": {
+        "model.embed_tokens.biases": "model-00001-of-00008.safetensors",
+        "model.embed_tokens.scales": "model-00001-of-00008.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.down_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.up_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.27.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.27.mlp.gate_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.27.self_attn.k_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.o_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.q_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.v_proj.biases": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.down_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.down_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.up_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.up_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.33.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.33.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.33.mlp.gate_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.33.mlp.gate_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.33.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.33.self_attn.k_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.k_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.o_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.o_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.q_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.q_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.v_proj.biases": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.v_proj.scales": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.down_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.down_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.up_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.up_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.39.mlp.down_proj.biases": "model-00008-of-00008.safetensors",
+        "model.layers.39.mlp.down_proj.scales": "model-00008-of-00008.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.39.mlp.gate_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.39.mlp.gate_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.mlp.up_proj.biases": "model-00008-of-00008.safetensors",
+        "model.layers.39.mlp.up_proj.scales": "model-00008-of-00008.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.39.self_attn.k_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.k_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.o_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.o_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.q_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.q_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.v_proj.biases": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.v_proj.scales": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model-00003-of-00008.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model-00003-of-00008.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.norm.weight": "model-00008-of-00008.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec24d1fe80ac960489b2004b7399ea561799de2fae774bd5a9234c13e6a0726
+size 12777306

tokenizer_config.json

@@ -0,0 +1,314 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|EXTRA_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|EXTRA_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|EXTRA_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255022": {
+      "content": "<|EXTRA_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255023": {
+      "content": "<|EXTRA_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|EXTRA_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|EXTRA_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|EXTRA_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|EXTRA_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}