Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model:
+- cognitivecomputations/TinyDolphin-2.8-1.1b
+- 78health/TinyLlama_1.1B-function-calling
+- DaertML/TinyGauss-1.1B
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- cognitivecomputations/TinyDolphin-2.8-1.1b
+- 78health/TinyLlama_1.1B-function-calling
+- DaertML/TinyGauss-1.1B
+---
+
+# TinyEnsemble-3x1.1B-TinyMoE
+
+TinyEnsemble-3x1.1B-TinyMoE is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [cognitivecomputations/TinyDolphin-2.8-1.1b](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b)
+* [78health/TinyLlama_1.1B-function-calling](https://huggingface.co/78health/TinyLlama_1.1B-function-calling)
+* [DaertML/TinyGauss-1.1B](https://huggingface.co/DaertML/TinyGauss-1.1B)
+
+## 🧩 Configuration
+
+```yaml
+base_model: cognitivecomputations/TinyDolphin-2.8-1.1b
+gate_mode: cheap_embed
+dtype: bfloat16
+experts:
+  - source_model: cognitivecomputations/TinyDolphin-2.8-1.1b
+    positive_prompts: ["write", "explain", "summarize", "how", "what", "acting"]
+  - source_model: 78health/TinyLlama_1.1B-function-calling
+    positive_prompts: ["code", "python", "javascript", "programming", "script", "run", "create"]
+  - source_model: DaertML/TinyGauss-1.1B
+    positive_prompts: ["count", "math", "algorithm", "crypto", "logic", "reason"]
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "JoPmt/TinyEnsemble-3x1.1B-TinyMoE"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+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 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "cognitivecomputations/TinyDolphin-2.8-1.1b",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_local_experts": 3,
+  "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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32002
+}

mergekit_moe_config.yml

@@ -0,0 +1,11 @@
+
+base_model: cognitivecomputations/TinyDolphin-2.8-1.1b
+gate_mode: cheap_embed
+dtype: bfloat16
+experts:
+  - source_model: cognitivecomputations/TinyDolphin-2.8-1.1b
+    positive_prompts: ["write", "explain", "summarize", "how", "what", "acting"]
+  - source_model: 78health/TinyLlama_1.1B-function-calling
+    positive_prompts: ["code", "python", "javascript", "programming", "script", "run", "create"]
+  - source_model: DaertML/TinyGauss-1.1B
+    positive_prompts: ["count", "math", "algorithm", "crypto", "logic", "reason"]

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a685ae56a7be711f0dc17a2df84fdabec086f1c1d12dfb595d56d232a13ca1
+size 990952512

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd183b9fdc13f5d88b149da94288a5509170c180c0eb55a90aa2cb4a1a5df6a2
+size 994099456

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b493950a4b2baf7c3002d58e7b039826f14bdeab6b37a8332bdc6fb5e73ae931
+size 998285048

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0bdeca62ac62532c10a7e280136b2dc9f2d3a08323d81ce8225f46fa983dfc
+size 998289280

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322a6c3064490b35659b7e0df8b28acc782ef219cb00c955828ca93fb84107c9
+size 994095312

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb1b3828dd530d1871000a64d843ecd913080ae709e283ba2dd52b6d06ccc464
+size 269770232

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 5245448192}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors", "lm_head.weight": "model-00006-of-00006.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "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 +1,61 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}