Upload folder using huggingface_hub

README.md

@@ -0,0 +1,70 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- SciPhi/SciPhi-Self-RAG-Mistral-7B-32k
+base_model:
+- SciPhi/SciPhi-Self-RAG-Mistral-7B-32k
+---
+
+# SciPhi-Mistral-RAG-Hermes-7B-32k
+
+SciPhi-Mistral-RAG-Hermes-7B-32k is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [SciPhi/SciPhi-Self-RAG-Mistral-7B-32k](https://huggingface.co/SciPhi/SciPhi-Self-RAG-Mistral-7B-32k)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: SciPhi/SciPhi-Self-RAG-Mistral-7B-32k
+        layer_range: [0, 7]
+  - sources:
+      - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+        layer_range: [8, 16]
+  - sources: 
+      - model: SciPhi/SciPhi-Self-RAG-Mistral-7B-32k 
+        layer_range: [17, 24]
+  - sources:
+      - model: teknium/OpenHermes-2.5-Mistral-7B
+        layer_range: [25, 32]
+
+merge_method: slerp
+base_model: SciPhi/SciPhi-Self-RAG-Mistral-7B-32k
+parameters:
+  t:
+  - filter: self_attn
+    value: [0, 0.5, 0.3, 0.7, 1]
+  - filter: mlp
+    value: [1, 0.5, 0.7, 0.3, 0]
+  - value: 0.5
+dtype: float16
+tokenizer_source: base
+
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "jtatman/SciPhi-Mistral-RAG-Hermes-7B-32k"
+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"])
+```

added_tokens.json

@@ -0,0 +1,18 @@
+{
+  "</paragraph>": 32013,
+  "<pad>": 32015,
+  "<paragraph>": 32005,
+  "[Continue to Use Evidence]": 32006,
+  "[Fully supported]": 32014,
+  "[Irrelevant]": 32011,
+  "[No Retrieval]": 32010,
+  "[No support / Contradictory]": 32003,
+  "[Partially supported]": 32000,
+  "[Relevant]": 32007,
+  "[Retrieval]": 32004,
+  "[Utility:1]": 32001,
+  "[Utility:2]": 32002,
+  "[Utility:3]": 32008,
+  "[Utility:4]": 32012,
+  "[Utility:5]": 32009
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "SciPhi/SciPhi-Self-RAG-Mistral-7B-32k",
+  "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": 29,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": false,
+  "vocab_size": 32016
+}

mergekit_config.yml

@@ -0,0 +1,27 @@
+
+slices:
+  - sources:
+      - model: SciPhi/SciPhi-Self-RAG-Mistral-7B-32k
+        layer_range: [0, 7]
+  - sources:
+      - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
+        layer_range: [8, 16]
+  - sources: 
+      - model: SciPhi/SciPhi-Self-RAG-Mistral-7B-32k 
+        layer_range: [17, 24]
+  - sources:
+      - model: teknium/OpenHermes-2.5-Mistral-7B
+        layer_range: [25, 32]
+
+merge_method: slerp
+base_model: SciPhi/SciPhi-Self-RAG-Mistral-7B-32k
+parameters:
+  t:
+  - filter: self_attn
+    value: [0, 0.5, 0.3, 0.7, 1]
+  - filter: mlp
+    value: [1, 0.5, 0.7, 0.3, 0]
+  - value: 0.5
+dtype: float16
+tokenizer_source: base
+

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a2fbbb3dba0e32249a7ecd8530cda5ae13d81a4d8e92e321eae8b15081b0e94
+size 1979773088

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dde44b73349dc35537ab12db026737f9203b348f067e695fecfcb8b8339b069
+size 1946235600

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f5935de3d59bf6d80c9d3a2d9c20e949f183bcf42101cb3179dec1b46a17bc
+size 1950559696

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ee40d0801006de84caa05c5b0d81c0f2fbb10eca09feb7239e0955f2651b00
+size 1996575936

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aeb1a40fbab2cc0797955ec386e378c01a0aa1dc329d23917f8afd3054add9f
+size 1895895336

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e54a5b74e9a15efb66c51510507bca5bf1155036e8bbc1195ee953cedc1cf21
+size 1979789736

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338ddbf96b0b449755b0674907bd02b609905044bace5aaf5518d12791f2976d
+size 1426140648

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.embed_tokens.weight": "model-00003-of-00007.safetensors", "lm_head.weight": "model-00003-of-00007.safetensors", "model.norm.weight": "model-00003-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00007.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,50 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[Partially supported]",
+    "[Utility:1]",
+    "[Utility:2]",
+    "[No support / Contradictory]",
+    "[Retrieval]",
+    "<paragraph>",
+    "[Continue to Use Evidence]",
+    "[Relevant]",
+    "[Utility:3]",
+    "[Utility:5]",
+    "[No Retrieval]",
+    "[Irrelevant]",
+    "[Utility:4]",
+    "</paragraph>",
+    "[Fully supported]"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,189 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[Partially supported]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "[Utility:1]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "[Utility:2]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "[No support / Contradictory]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "[Retrieval]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<paragraph>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "[Continue to Use Evidence]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "[Relevant]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "[Utility:3]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "[Utility:5]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "[No Retrieval]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "[Irrelevant]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "[Utility:4]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "</paragraph>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "[Fully supported]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[Partially supported]",
+    "[Utility:1]",
+    "[Utility:2]",
+    "[No support / Contradictory]",
+    "[Retrieval]",
+    "<paragraph>",
+    "[Continue to Use Evidence]",
+    "[Relevant]",
+    "[Utility:3]",
+    "[Utility:5]",
+    "[No Retrieval]",
+    "[Irrelevant]",
+    "[Utility:4]",
+    "</paragraph>",
+    "[Fully supported]"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}