Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+base_model:
+- shastraai/Shastra-LLAMA-Math-DPO
+- shastraai/Shastra-LLAMA2-Commonsense-SFT
+tags:
+- merge
+- mergekit
+- lazymergekit
+- shastraai/Shastra-LLAMA-Math-DPO
+- shastraai/Shastra-LLAMA2-Commonsense-SFT
+---
+
+# Shastra-LLAMA2-Math-Commonsense-TIES
+
+Shastra-LLAMA2-Math-Commonsense-TIES is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [shastraai/Shastra-LLAMA-Math-DPO](https://huggingface.co/shastraai/Shastra-LLAMA-Math-DPO)
+* [shastraai/Shastra-LLAMA2-Commonsense-SFT](https://huggingface.co/shastraai/Shastra-LLAMA2-Commonsense-SFT)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: shastraai/Shastra-LLAMA-Math-DPO
+    # no parameters necessary for base model
+  - model: shastraai/Shastra-LLAMA-Math-DPO
+    parameters:
+      density: 0.5
+      weight: 0.5
+  - model: shastraai/Shastra-LLAMA2-Commonsense-SFT
+    parameters:
+      density: 0.5
+      weight: 0.3
+merge_method: ties
+base_model: shastraai/Shastra-LLAMA-Math-DPO
+parameters:
+  normalize: true
+dtype: float16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "shastraai/Shastra-LLAMA2-Math-Commonsense-TIES"
+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 +1,31 @@
+{
+  "_name_or_path": "shastraai/Shastra-LLAMA-Math-DPO",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "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": "float16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+models:
+  - model: shastraai/Shastra-LLAMA-Math-DPO
+    # no parameters necessary for base model
+  - model: shastraai/Shastra-LLAMA-Math-DPO
+    parameters:
+      density: 0.5
+      weight: 0.5
+  - model: shastraai/Shastra-LLAMA2-Commonsense-SFT
+    parameters:
+      density: 0.5
+      weight: 0.3
+merge_method: ties
+base_model: shastraai/Shastra-LLAMA-Math-DPO
+parameters:
+  normalize: true
+dtype: float16

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03492c7b548fe34cbe6e1fe9194d52c2870cca223b68190e0a129eb05075e211
+size 929064264

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de9d7f1054fc28eaa3e35955f98f5069e708ab0286e20e39fd2b907567b07be
+size 989890808

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b7dc423d7d413bcd0835bb6d9db3892ac986d2cfd7caf6045884bdbc16bb70
+size 966830568

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6197c1ddd3165f793660c49f1859391ead0e6ee2fa38bdf7011fd11cd8a01901
+size 966830560

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae01be98cadbb25e94fb6ade8356956dbbe1d3a3b15dd0c194c3f0a8e0446a28
+size 989899128

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d377807a54fd1c3bee91e2b5de2350d74dbe581a60deaba50371f883d92032c
+size 943762000

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad02ff249b53dd31bd381a8df1848f5af581565be81d3ddf63288e744af307c
+size 989890816

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b53c0f8d59084f544c2ebf51c914e6eac4dcbc17aad8c243247f2e6faa24346
+size 966830568

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88be847012b4305c725f10bacbf8c44f28ac36075c054308952d26f22c76634b
+size 966830560

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b93c19bf12fb326faa1361e5561d0bf11409afe69b1c09972aea59296ba844
+size 989899128

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3042f8ed387cc98b243b78c74fae2a0a15af8ced094b36b885619ebdda8b9a28
+size 943762000

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff66ac420286d6b6bd12ca112038e1d5f7a4a564129f8d15b571878e3aac5b15
+size 989890808

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d90c3d70de2c07a3f3b2367a86c4986e644144379be94d6b3e48eaa4a2579f
+size 966830552

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a4030b22f86cc72066de412e149447fa8ed8887e1b786db8b5a76e50f88100
+size 876652872

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 13476831232}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.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_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}