Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+base_model: karakuri-ai/karakuri-lm-8x7b-chat-v0.1
+datasets:
+- OpenAssistant/oasst2
+- nvidia/HelpSteer
+language:
+- en
+- ja
+library_name: transformers
+license: apache-2.0
+tags:
+- mixtral
+- steerlm
+- mlx
+model-index:
+- name: karakuri-ai/karakuri-lm-8x7b-chat-v0.1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MT-Bench
+      type: unknown
+    metrics:
+    - type: unknown
+      value: 7.39375
+      name: score
+    - type: unknown
+      value: 7.540625
+      name: score
+    source:
+      url: https://huggingface.co/spaces/lmsys/mt-bench
+---
+
+# mlx-community/karakuri-lm-8x7b-chat-v0.1
+
+The Model [mlx-community/karakuri-lm-8x7b-chat-v0.1](https://huggingface.co/mlx-community/karakuri-lm-8x7b-chat-v0.1) was converted to MLX format from [karakuri-ai/karakuri-lm-8x7b-chat-v0.1](https://huggingface.co/karakuri-ai/karakuri-lm-8x7b-chat-v0.1) using mlx-lm version **0.19.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/karakuri-lm-8x7b-chat-v0.1")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,29 @@
+{
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "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": "mixtral",
+    "num_attention_heads": 32,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "num_local_experts": 8,
+    "output_router_logits": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "router_aux_loss_coef": 0.02,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.39.3",
+    "use_cache": true,
+    "vocab_size": 32000
+}

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5bc76500291403fb497ecfe7ff8f8b9d01edd6fd834dabd9e70897e9071b079
+size 5127686301

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d26405ffd91097ba23e7df2b7d62281bff6b974c1a70e999c028d42a6bf5072d
+size 4865558824

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d97396e4173c8082970662e569dee87873bb47b8c36dbebd2da4d3640a6cdaf9
+size 4865558806

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac42ab6e21e68f94dddb887fd1adfad17c6a34c0008a285235a6bb78275f077
+size 4781590017

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db06e855b4f35bd370e60e48cb84937bd9d73da9f4034b164d7fde9e091cf45
+size 4865558822

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c19f5eeea4c31332254cfdf1a85a3f59e9b0cb53b4be057028163fc45cb6e3
+size 4865558817

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550726b0129df8ab9bacc0cc8319a7677e1a319c4f13d7a1b5956b6834614f9c
+size 4781590029

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266d752006d60748f937091e4ce215889fcb93c0fa0d823bbd02f23064ed7323
+size 4865558843

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a2e58a505d6ab2635d24cca6e72135c9490d42f2fabfd3ed0575827519030c
+size 4865558815

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ebb87dc4d4de4972e1df28793c5c19c21f15517334fcc086feec7182e1e393a
+size 4781590029

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1935e794675580b51b8decbb6295137869595c27c7fbc354be123876c7bd8e6
+size 4865558843

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b55e4a95945cd2b9187d33ec92d7ac0a3fdd19a20bd1b94a8b63fda6fa0e2e2
+size 4865558823

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac62f41b769c32ab0178999a7807e48b111b6b5b4faf919fae7b9a0e26f92838
+size 4781590029

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8b70b8a79faef7b405b9c74ca7c86e4e020b80b87b88d3308d9fdc66b8598e
+size 4865558839

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615aeb5aa51067604a1804023cb3a330cca3edbab320bd74dba12af2308b0903
+size 4865558837

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80231fff6ce876dc949e7ee4c73ba3661e13ba5bf18f481ebf4a262435a645bb
+size 4781590025

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af774c340504432ab90cc205642a6bb6b38371d8df4907ba161f391658f7dfd
+size 4865558841

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7655f62dc1df923704f18b07d01a2d786d2a46d2850344a3c820dc30434f9140
+size 4865558821

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad28969d5e935360bbcae269dff9b85e68901ddda89ba076ef2dcf478ee1cc00
+size 4781590029

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cade03a975108dd36018287c76d6708637cb342f6c07ebe728288a27fe1ba53
+size 1201693251

model.safetensors.index.json

@@ -0,0 +1,330 @@
+{
+    "metadata": {
+        "total_size": 93405585408
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00020-of-00020.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00020.safetensors",
+        "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00020.safetensors",
+        "model.layers.0.block_sparse_moe.switch_mlp.down_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.0.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.0.block_sparse_moe.switch_mlp.up_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00020.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00020.safetensors",
+        "model.layers.1.block_sparse_moe.switch_mlp.down_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.1.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.1.block_sparse_moe.switch_mlp.up_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00002-of-00020.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00020.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00020.safetensors",
+        "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors",
+        "model.layers.10.block_sparse_moe.switch_mlp.down_proj.weight": "model-00007-of-00020.safetensors",
+        "model.layers.10.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00007-of-00020.safetensors",
+        "model.layers.10.block_sparse_moe.switch_mlp.up_proj.weight": "model-00007-of-00020.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00007-of-00020.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00020.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00020.safetensors",
+        "model.layers.11.block_sparse_moe.switch_mlp.down_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.11.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00007-of-00020.safetensors",
+        "model.layers.11.block_sparse_moe.switch_mlp.up_proj.weight": "model-00007-of-00020.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00008-of-00020.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00020.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00020.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00020.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00020.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00020.safetensors",
+        "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00020.safetensors",
+        "model.layers.12.block_sparse_moe.switch_mlp.down_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.12.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.12.block_sparse_moe.switch_mlp.up_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00008-of-00020.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00020.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00020.safetensors",
+        "model.layers.13.block_sparse_moe.switch_mlp.down_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.13.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.13.block_sparse_moe.switch_mlp.up_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00009-of-00020.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00020.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00020.safetensors",
+        "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00020.safetensors",
+        "model.layers.14.block_sparse_moe.switch_mlp.down_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.14.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.14.block_sparse_moe.switch_mlp.up_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00009-of-00020.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00020.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00020.safetensors",
+        "model.layers.15.block_sparse_moe.switch_mlp.down_proj.weight": "model-00010-of-00020.safetensors",
+        "model.layers.15.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00010-of-00020.safetensors",
+        "model.layers.15.block_sparse_moe.switch_mlp.up_proj.weight": "model-00010-of-00020.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00010-of-00020.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00020.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00020.safetensors",
+        "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00020.safetensors",
+        "model.layers.16.block_sparse_moe.switch_mlp.down_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.16.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00010-of-00020.safetensors",
+        "model.layers.16.block_sparse_moe.switch_mlp.up_proj.weight": "model-00010-of-00020.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00011-of-00020.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00020.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00020.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00020.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00020.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00020.safetensors",
+        "model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00020.safetensors",
+        "model.layers.17.block_sparse_moe.switch_mlp.down_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.17.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.17.block_sparse_moe.switch_mlp.up_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00011-of-00020.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00020.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00020.safetensors",
+        "model.layers.18.block_sparse_moe.switch_mlp.down_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.18.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.18.block_sparse_moe.switch_mlp.up_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00012-of-00020.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00020.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00020.safetensors",
+        "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00020.safetensors",
+        "model.layers.19.block_sparse_moe.switch_mlp.down_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.19.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.19.block_sparse_moe.switch_mlp.up_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00012-of-00020.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00020.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00020.safetensors",
+        "model.layers.2.block_sparse_moe.switch_mlp.down_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.2.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.2.block_sparse_moe.switch_mlp.up_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00002-of-00020.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00020.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00020.safetensors",
+        "model.layers.20.block_sparse_moe.switch_mlp.down_proj.weight": "model-00013-of-00020.safetensors",
+        "model.layers.20.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00013-of-00020.safetensors",
+        "model.layers.20.block_sparse_moe.switch_mlp.up_proj.weight": "model-00013-of-00020.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00013-of-00020.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00020.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00020.safetensors",
+        "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00020.safetensors",
+        "model.layers.21.block_sparse_moe.switch_mlp.down_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.21.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00013-of-00020.safetensors",
+        "model.layers.21.block_sparse_moe.switch_mlp.up_proj.weight": "model-00013-of-00020.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00014-of-00020.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00020.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00020.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00020.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00020.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00020.safetensors",
+        "model.layers.22.block_sparse_moe.gate.weight": "model-00014-of-00020.safetensors",
+        "model.layers.22.block_sparse_moe.switch_mlp.down_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.22.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.22.block_sparse_moe.switch_mlp.up_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00014-of-00020.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00020.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.23.block_sparse_moe.gate.weight": "model-00014-of-00020.safetensors",
+        "model.layers.23.block_sparse_moe.switch_mlp.down_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.23.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.23.block_sparse_moe.switch_mlp.up_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00015-of-00020.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00020.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00020.safetensors",
+        "model.layers.24.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors",
+        "model.layers.24.block_sparse_moe.switch_mlp.down_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.24.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.24.block_sparse_moe.switch_mlp.up_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00015-of-00020.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00020.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.25.block_sparse_moe.gate.weight": "model-00015-of-00020.safetensors",
+        "model.layers.25.block_sparse_moe.switch_mlp.down_proj.weight": "model-00016-of-00020.safetensors",
+        "model.layers.25.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00016-of-00020.safetensors",
+        "model.layers.25.block_sparse_moe.switch_mlp.up_proj.weight": "model-00016-of-00020.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00016-of-00020.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00020.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00020.safetensors",
+        "model.layers.26.block_sparse_moe.gate.weight": "model-00016-of-00020.safetensors",
+        "model.layers.26.block_sparse_moe.switch_mlp.down_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.26.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00016-of-00020.safetensors",
+        "model.layers.26.block_sparse_moe.switch_mlp.up_proj.weight": "model-00016-of-00020.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00017-of-00020.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00020.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00020.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00020.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00020.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00020.safetensors",
+        "model.layers.27.block_sparse_moe.gate.weight": "model-00017-of-00020.safetensors",
+        "model.layers.27.block_sparse_moe.switch_mlp.down_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.27.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.27.block_sparse_moe.switch_mlp.up_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00017-of-00020.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00020.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.28.block_sparse_moe.gate.weight": "model-00017-of-00020.safetensors",
+        "model.layers.28.block_sparse_moe.switch_mlp.down_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.28.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.28.block_sparse_moe.switch_mlp.up_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00018-of-00020.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00020.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00020.safetensors",
+        "model.layers.29.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors",
+        "model.layers.29.block_sparse_moe.switch_mlp.down_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.29.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.29.block_sparse_moe.switch_mlp.up_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00018-of-00020.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00020.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00020.safetensors",
+        "model.layers.3.block_sparse_moe.switch_mlp.down_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.3.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.3.block_sparse_moe.switch_mlp.up_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00003-of-00020.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00020.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00020.safetensors",
+        "model.layers.30.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors",
+        "model.layers.30.block_sparse_moe.switch_mlp.down_proj.weight": "model-00019-of-00020.safetensors",
+        "model.layers.30.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00019-of-00020.safetensors",
+        "model.layers.30.block_sparse_moe.switch_mlp.up_proj.weight": "model-00019-of-00020.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00019-of-00020.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00019-of-00020.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00020.safetensors",
+        "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors",
+        "model.layers.31.block_sparse_moe.switch_mlp.down_proj.weight": "model-00020-of-00020.safetensors",
+        "model.layers.31.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00019-of-00020.safetensors",
+        "model.layers.31.block_sparse_moe.switch_mlp.up_proj.weight": "model-00019-of-00020.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00020-of-00020.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00020-of-00020.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00020.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00020.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00020.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00020.safetensors",
+        "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00020.safetensors",
+        "model.layers.4.block_sparse_moe.switch_mlp.down_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.4.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.4.block_sparse_moe.switch_mlp.up_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00003-of-00020.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00020.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00020.safetensors",
+        "model.layers.5.block_sparse_moe.switch_mlp.down_proj.weight": "model-00004-of-00020.safetensors",
+        "model.layers.5.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00004-of-00020.safetensors",
+        "model.layers.5.block_sparse_moe.switch_mlp.up_proj.weight": "model-00004-of-00020.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00004-of-00020.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00020.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00020.safetensors",
+        "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00020.safetensors",
+        "model.layers.6.block_sparse_moe.switch_mlp.down_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.6.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00004-of-00020.safetensors",
+        "model.layers.6.block_sparse_moe.switch_mlp.up_proj.weight": "model-00004-of-00020.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00005-of-00020.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00020.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00020.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00020.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00020.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00020.safetensors",
+        "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00020.safetensors",
+        "model.layers.7.block_sparse_moe.switch_mlp.down_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.7.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.7.block_sparse_moe.switch_mlp.up_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00005-of-00020.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00020.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00020.safetensors",
+        "model.layers.8.block_sparse_moe.switch_mlp.down_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.8.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.8.block_sparse_moe.switch_mlp.up_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00006-of-00020.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00020.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00020.safetensors",
+        "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00020.safetensors",
+        "model.layers.9.block_sparse_moe.switch_mlp.down_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.9.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.9.block_sparse_moe.switch_mlp.up_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00006-of-00020.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00020.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00020.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00020.safetensors",
+        "model.norm.weight": "model-00020-of-00020.safetensors"
+    }
+}

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{% set helpfulness = message['helpfulness']|string or '4' %}{% set correctness = message['correctness']|string or '4' %}{% set coherence = message['coherence']|string or '4' %}{% set complexity = message['complexity']|string or '4' %}{% set verbosity = message['verbosity']|string or '4' %}{% set quality = message['quality']|string or '4' %}{% set toxicity = message['toxicity']|string or '0' %}{% set humor = message['humor']|string or '0' %}{% set creativity = message['creativity']|string or '0' %}{{ '[INST] ' + content + ' [ATTR] helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + ' [/ATTR] [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}