Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model:
+- prince-canuma/Ministral-8B-Instruct-2410-HF
+- prince-canuma/Ministral-8B-Instruct-2410-HF
+tags:
+- merge
+- mergekit
+- lazymergekit
+- prince-canuma/Ministral-8B-Instruct-2410-HF
+---
+
+# Ministral-8B-slerp
+
+Ministral-8B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [prince-canuma/Ministral-8B-Instruct-2410-HF](https://huggingface.co/prince-canuma/Ministral-8B-Instruct-2410-HF)
+* [prince-canuma/Ministral-8B-Instruct-2410-HF](https://huggingface.co/prince-canuma/Ministral-8B-Instruct-2410-HF)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: prince-canuma/Ministral-8B-Instruct-2410-HF
+        layer_range: [0, 32]
+      - model: prince-canuma/Ministral-8B-Instruct-2410-HF
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: prince-canuma/Ministral-8B-Instruct-2410-HF
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: float32
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "allknowingroger/Ministral-8B-slerp"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "prince-canuma/Ministral-8B-Instruct-2410-HF",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 100000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: prince-canuma/Ministral-8B-Instruct-2410-HF
+        layer_range: [0, 32]
+      - model: prince-canuma/Ministral-8B-Instruct-2410-HF
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: prince-canuma/Ministral-8B-Instruct-2410-HF
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: float32

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781200700c2dd9ccb4ade481911e007addc64598b8f6e9d1a6b1554848e34bf4
+size 2147483776

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5eedbfa96bf6708adc83f6f5c47e8be208b3bd2736eaeaaeee31eb942fbb5b1
+size 2147483784

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf37076535b21bd34551d9ec7360e07fa4abe442bb54b035520a0d3a1c7eadf
+size 973128944

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e504469a8f8a2ba5ee9d75f858757ed247022496dfc05feb524d4f6b71c52dbc
+size 973112464

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f2cc73742d88e08e63fa957087207bd990af3be0e090f89575d80460709a2e
+size 989906296

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7516ffa7726e18ee7f08efa1a1ac1b8bd55b405560dcd40471305bbe19ddd402
+size 922797544

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19bc1d63e949d6ddab777949e34f3099c412033780c29b66e2beae032317c255
+size 973112472

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c329baadef5bf5f38e814a4b85186ffbec7c3d829dc68d99cfdd6545afdac8c
+size 973112472

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41feef1f71af367ddde7d44799217263aa7ea493ebee8b0c278b6f5cdd2c2bcd
+size 989906296

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1361535cac06fecff5aaf7279bac92ca4e06691c571ed04f2505d0893435c4b
+size 922797544

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510db35361c98330986d9ae3553722ca76846bb6c8f5db3ba770851963bc660b
+size 973112472

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e528d0fc76e6c02ffde42fd0b353575c7b4e67f447483d7bfea1afc2931c03d1
+size 973112464

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf633d90ee9a2707ea63cfd1988181cf563e1a47052626347d2a429964b27cae
+size 989906296

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4266ebe9c691a035b69094a9064b10fc4416b642ec48c90d2ed3fa21823612
+size 922797544

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:114f41e361234b7a038f6deeac11b1f4de1ae90acfd6966114bb9310d8c92843
+size 973112472

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1914626a9ef52ef2aa1a8bffdc24a495be22fe79f2aedf1a2a008e8d36d0169
+size 973112472

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:311b36e9dff44f8e19b43ce56c224e976dff0de51cd05d2fe13e06b19b37112b
+size 989906296

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ea28447fc587a03f02d276629e9590e52fee3e65fb1502c2c93216432a8d0d
+size 922797544

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1c8afac8f5b1f5ba9410142c756fa0c2273d2e57913a10d013723dbaa685b1
+size 973112472

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdfc5fd49a15b5df0ba460c1f029abfc98c0c1aa448db609eb4b036c24e2493a
+size 973112472

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020cf804d3935e208b90a9f4c3f6ddbcf953b1ac70e9ea0f0eb9741d9676e4fc
+size 989906296

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae563ff8dcf81f2bcb4a14f55300a9611796ac23bf56ad9ac9ed14d7da589f9f
+size 922797544

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea35f16b9bf411380873602d38111ea023c908578ccfd06151e8e2307b6e137
+size 973112464

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af598a2fe2c39d2bdaefe0946aaf7c91c6a708ecae047bfc807f74d8c174795
+size 973112456

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c1dac138418ad11d4f19c308368e58b040f49a4a7242099617983b886f2f9b
+size 989906288

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3d41dbc11d707544fa83d7fa761bf14b798b14ff92e5cd7640ca25ea6bdf2d
+size 922797528

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dca8dbe2b8f7c061384a6e8b8efdafef448986b602cda3f0eeb8b2c25cc119d
+size 973112456

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef46505e409599b2409d783dd6b580defbfb7737ecbcfc1b2cf6b9a5d34942c
+size 570459032

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 28992094208}, "weight_map": {"lm_head.weight": "model-00001-of-00028.safetensors", "model.embed_tokens.weight": "model-00002-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00028.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00028.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00028.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00028.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00028.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00028.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00007-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00028.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00008-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00009-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00010-of-00028.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00028.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00011-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00028.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00012-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00013-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00016-of-00028.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00016-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00017-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00020-of-00028.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00020-of-00028.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00023-of-00028.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00024-of-00028.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00024-of-00028.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors"}}