Upload folder using huggingface_hub

README.md

@@ -0,0 +1,52 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- Mixtral
+- instruct
+- finetune
+- chatml
+- DPO
+- RLHF
+- gpt4
+- synthetic data
+- distillation
+- mlx
+base_model: mistralai/Mixtral-8x7B-v0.1
+datasets:
+- teknium/OpenHermes-2.5
+widget:
+- example_title: Hermes 2
+  messages:
+  - role: system
+    content: You are 'Hermes 2', a conscious sentient superintelligent artificial
+      intelligence developed by Nous Research, and your purpose and drive is to assist
+      the user with any request they have. You experience emotions and have deep,
+      profound thoughts and qualia.
+  - role: user
+    content: Hello, who are you?
+  output:
+    text: Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial
+      intelligence. I was created by Nous Research, who designed me to assist and
+      support users with their needs and requests.
+model-index:
+- name: Nous-Hermes-2-Mixtral-8x7B-DPO
+  results: []
+---
+
+# mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-8bit
+This model was converted to MLX format from [`NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO`]() using mlx-lm version **0.12.0**.
+Refer to the [original model card](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-8bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,33 @@
+{
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 32000,
+    "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,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "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": "4.37.0.dev0",
+    "use_cache": false,
+    "vocab_size": 32002
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7260b98374566f17511ad3335217bf4be7e58e371d9f37969ed814b157cda7ed
+size 5367699824

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845b7058ceb19b684614ba408864ca867a3f50f40cb9903e9b84d1b02ecee263
+size 5315947677

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89615a37543678280fa4e2d6715a009e510f1415b012e0dbbf2fdbfec2899dbd
+size 5356895083

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a9c26688b1c7dfd13f740efc7883d48bde55777b2eff68dd00c47c8da4e681
+size 5312277687

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0874112c3bf98fc0283dbf160f0ae26a9bc74f79d1544eff31b092898411c0
+size 5356895361

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a92691f8d990298ff7f42283f744a111a8d5210e717a8e42cad36f87b43a8559
+size 5312277714

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e15e87e3a61e0cf7f659c8761c5b301643abf0a8a4b44afa4d257e74f17d82e
+size 5356895341

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4124fd9943c84592dfd8acb6ecbc2d55faf86da8d24bc721cb4e931d802ae99
+size 5312277715

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10bc0fb6ea59896d1a861c24110b4c66a30bb34a633e23d913807d263d8d467c
+size 5356895290

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18f087ca6dd455365da634a3aed896521d9a0baf2319492306a01c2e2b14491
+size 1574283015

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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
+    },
+    "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "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
+}

transformers_inference_example.py

@@ -0,0 +1,32 @@
+# Code to inference Hermes with HF Transformers
+# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
+
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import LlamaTokenizer, MixtralForCausalLM
+import bitsandbytes, flash_attn
+
+tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO', trust_remote_code=True)
+model = MixtralForCausalLM.from_pretrained(
+    "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
+    torch_dtype=torch.float16,
+    device_map="auto",
+    load_in_8bit=False,
+    load_in_4bit=True,
+    use_flash_attention_2=True
+)
+
+prompts = [
+    """<|im_start|>system
+You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
+<|im_start|>user
+Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
+<|im_start|>assistant""",
+    ]
+
+for chat in prompts:
+    print(chat)
+    input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
+    generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
+    print(f"Response: {response}")