Upload folder using huggingface_hub

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- meta-math/MetaMath-Mistral-7B
+- EleutherAI/llemma_7b
+base_model:
+- meta-math/MetaMath-Mistral-7B
+- EleutherAI/llemma_7b
+---
+
+# MM-SL
+
+MM-SL is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
+* [EleutherAI/llemma_7b](https://huggingface.co/EleutherAI/llemma_7b)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+    - model: meta-math/MetaMath-Mistral-7B
+      layer_range: [0, 32]
+  - sources:
+    - model: EleutherAI/llemma_7b
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "confettiwap/MM-SL"
+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 +1,29 @@
+{
+  "_name_or_path": "EleutherAI/llemma_7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 32016
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+slices:
+  - sources:
+    - model: meta-math/MetaMath-Mistral-7B
+      layer_range: [0, 32]
+  - sources:
+    - model: EleutherAI/llemma_7b
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33af856d02b1efa2f137130a2ab9bae85852fb9e65b886ebe2fb627d7119e4d4
+size 960660816

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f0bd01ddaa3762a581d94a8132d18983a1fd777eb8798da67041d5084319a7
+size 989890720

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31202f521b1379ece2b889b9f472b7c799e5f0834874f650ffde0d4b267dfdbe
+size 989890728

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ecbb1ac2a4b5956636f32d81a03ee22d769d827ed5be8fa16fc3d6374fcf2e
+size 998287760

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc40307df2d9b6f1ac5304c16b9bc0a757a4548d53e54b8b48464d728265a097
+size 947956216

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bde21ea837f48e414f179a09c1a179b887897b26af89d3017048508b9f893a4
+size 989890728

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3f0eb30e780ad2045d6a4db5089a681f6261f5616e8fc3493165493357457d
+size 989890720

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb711a8ca4d8aecfb2abe1bd948478f6b7220435646011799c1342b49ba5e7c
+size 998287760

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fdf6569700f9278cda373d185b4acf791f24ebd1be647f711f1375b498138c
+size 916507240

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03174a077c0665face024a6efb221e7e7359b93a6888f6f1565f31d08a7c5acc
+size 931170472

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0703df1fb50a9f1bea282498b2eb88ad9402316222b207a503a9dd6f807b69
+size 958433448

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e7f129449b2943d656436a234e4646490307538390498a3e221f48c7a49d646
+size 931170472

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e9b5475dda07a11e2fad73299d8b23c05eee0a46ee08f5309781ea824792b3d
+size 958433448

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e0986d5e2ee1de745940b9a187ac1811f6fd2c18da41dfd31d3ec036cfe691
+size 952158944

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f331ec87d41a64841c4d0f9af9258557c938fb6d933e5d7e0b1deeb67ce8c8d
+size 958433448

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8383d3bd07c7d49eeb35cb39a037a2b5de18cf9c2e9dd02d8a17410392eaccb
+size 994085152

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e14e345a7f56ef240b57cd3f0de1ccf78d04ebd4b49a74ceb0d5392462e16305
+size 947956192

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9ca7e9b1580ad7d039133e65be3dcdb8b43391cc455a215bbc592b7a973fbd
+size 989890712

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7839f6ed19e83ef20559d405ae6498bdad836a40b440e74f65fbbdf40b7cffe0
+size 318784416

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 17721737216}, "weight_map": {"lm_head.weight": "model-00001-of-00019.safetensors", "model.embed_tokens.weight": "model-00001-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.33.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.34.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.35.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.38.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.norm.weight": "model-00019-of-00019.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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}