Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- aipib/Tinyllama-moe3
+- aipib/karasu-moe
+base_model:
+- aipib/Tinyllama-moe3
+- aipib/karasu-moe
+---
+
+# karasu-moexdareties
+
+karasu-moexdareties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [aipib/Tinyllama-moe3](https://huggingface.co/aipib/Tinyllama-moe3)
+* [aipib/karasu-moe](https://huggingface.co/aipib/karasu-moe)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+- sources:
+  - layer_range: [0, 22]
+    model: aipib/Tinyllama-moe3
+    parameters:
+      density: [1, 0.7, 0.1]
+      weight: 1.0
+  - layer_range: [0, 22]
+    model: aipib/karasu-moe
+    parameters:
+      density: 0.33
+      weight:
+        - filter: mlp
+          value: 0.5
+        - value: 0
+merge_method: dare_ties
+base_model: aipib/Tinyllama-moe3
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "aipib/karasu-moexdareties"
+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 +1,34 @@
+{
+  "_name_or_path": "aipib/Tinyllama-moe3",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+
+slices:
+- sources:
+  - layer_range: [0, 22]
+    model: aipib/Tinyllama-moe3
+    parameters:
+      density: [1, 0.7, 0.1]
+      weight: 1.0
+  - layer_range: [0, 22]
+    model: aipib/karasu-moe
+    parameters:
+      density: 0.33
+      weight:
+        - filter: mlp
+          value: 0.5
+        - value: 0
+merge_method: dare_ties
+base_model: aipib/Tinyllama-moe3
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b768cb57c7af9d3d52a90d13521a771b4c45ae4687e439f10473c8b481adcb0d
+size 1992492416

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7e0bc85e3e2e8af942cc43d07fd64e4716bd1070bc0d62c2f693124ed36773
+size 1730352272

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 3722809344}, "weight_map": {"lm_head.weight": "model-00001-of-00002.safetensors", "model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "max_length": null,
+  "model_max_length": 2048,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}