Upload folder using huggingface_hub

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- nfaheem/Marcoroni-7b-DPO-Merge
+- EmbeddedLLM/Mistral-7B-Merge-14-v0.5
+---
+
+# MarcMistral-7B
+
+MarcMistral-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [nfaheem/Marcoroni-7b-DPO-Merge](https://huggingface.co/nfaheem/Marcoroni-7b-DPO-Merge)
+* [EmbeddedLLM/Mistral-7B-Merge-14-v0.5](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.5)
+
+As an experiment to find the best base merge to further fine-tuning, expect a lot of experiments named using parts of the component models until a clear winner emerges in the benchmarks
+
+In this case .
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: nfaheem/Marcoroni-7b-DPO-Merge
+        layer_range: [0, 32]
+      - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.5
+        layer_range: [0, 32]
+
+merge_method: slerp
+base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0.5
+
+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 # fallback for rest of tensors
+tokenizer_source: union
+
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "flemmingmiguel/MarcMistral-7B"
+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 +1,26 @@
+{
+  "_name_or_path": "EmbeddedLLM/Mistral-7B-Merge-14-v0.5",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "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": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32002
+}

mergekit_config.yml

@@ -0,0 +1,21 @@
+
+slices:
+  - sources:
+      - model: nfaheem/Marcoroni-7b-DPO-Merge
+        layer_range: [0, 32]
+      - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.5
+        layer_range: [0, 32]
+
+merge_method: slerp
+base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0.5
+
+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 # fallback for rest of tensors
+tokenizer_source: union
+
+dtype: bfloat16

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b1e5437fb37d361133be7256e2ed58436bfdaf05343c294dc7047124af7304
+size 1998671960

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4537cad8d531d1265cd540b44a22633b3eba8078e6e49051daac6531250aee
+size 1988178472

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be059d4bd5d811ebd41bd2a68a76db7270c691ce1527b3ff6bd6edb90711e66d
+size 1946243984

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f901110097bdaf2c3524409f26fa0424422ed5cf1b7baabc0abc79bf2ba3ade7
+size 1946227352

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f077a7b2175975cd509880f47f79c3ea3b41d6b26ccf5ca363aa51772c3b0c
+size 1988178456

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f837d5fff2d8a6c45e853a9ee9f135e69bb418cb23236395b41fedbb73b7918
+size 1998680264

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d2cd615de0d82152f829b1dba8a5f8f948581ddb60b4233b3af0be645b4ae5
+size 1979781456

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4649ecb4fbf1eeec44e3a30fad52ede8722a70b42f64bc3c9f9f0f7cd1614cd3
+size 637568832

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "lm_head.weight": "model-00006-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors"}}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}