Upload folder using huggingface_hub

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: mistral-community/Mixtral-8x22B-v0.1
+tags:
+- generated_from_trainer
+- axolotl
+model-index:
+- name: out
+  results: []
+datasets:
+- cognitivecomputations/Dolphin-2.9.2
+- cognitivecomputations/SystemChat-2.0
+- teknium/OpenHermes-2.5
+- m-a-p/CodeFeedback-Filtered-Instruction
+- cognitivecomputations/dolphin-coder
+- cognitivecomputations/samantha-data
+- HuggingFaceH4/ultrachat_200k
+- microsoft/orca-math-word-problems-200k
+- abacusai/SystemChat-1.1
+- Locutusque/function-calling-chatml
+- internlm/Agent-FLAN
+language:
+- en
+---
+
+# Dolphin 2.9.2 Mixtral 8x22b 🐬
+
+Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations
+
+[![Discord](https://img.shields.io/discord/1156064224225808488?logo=Discord&logoColor=%23ffffff&label=Discord&link=https%3A%2F%2Fdiscord.gg%2FtCMkMDDHwm)](https://discord.gg/cognitivecomputations)
+Discord: https://discord.gg/cognitivecomputations
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
+
+New in 2.9.2 is SystemChat 2.0 - a dataset designed to teach Dolphin to obey the system prompt, even over a long conversation.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/z1u6U91tL-H__7JCDbWys.png)
+
+My appreciation for the sponsors of Dolphin 2.9.2:
+- [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 8xH100 node
+- [OnDemand](https://on-demand.io/) - provided inference sponsorship, enabling creation of SystemChat
+
+This model is based on Dolphin-2.9-Mixtral-8x22b, and is Apache-2.0 licensed.
+
+The base model has 64k context, and fine-tuning was with 16k sequence length.
+
+It took 1 week on 8xH100 provided by Crusoe Cloud
+
+This model was trained FFT on 50% parameters (targeted with [Laser Scanner](https://github.com/cognitivecomputations/laserRMT/blob/main/laser_scanner.py) by Fernando Fernandes, David Golchinfar, Lucas Atkins, and Eric Hartford), using ChatML prompt template format.
+
+example:
+
+```
+<|im_start|>system
+You are Dolphin, a helpful AI assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+```
+
+Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.
+
+Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
+
+Dolphin is licensed Apache 2.0.  I grant permission for any use, including commercial, that falls within accordance with Apache-2.0 license.  Dolphin was trained on data generated from GPT4, among other models.
+
+## Evals
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/SDWV3SvJ8xR1gjl1z0LyO.png)
+
+## Training

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,42 @@
+{
+    "_name_or_path": "mistralai/Mixtral-8x22B-v0.1",
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 32000,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 65536,
+    "model_type": "mixtral",
+    "num_attention_heads": 48,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 56,
+    "num_key_value_heads": 8,
+    "num_local_experts": 8,
+    "output_router_logits": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000,
+    "router_aux_loss_coef": 0.001,
+    "router_jitter_noise": 0.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.40.2",
+    "use_cache": false,
+    "vocab_size": 32002,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.5",
+        "bits": 6.0,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

latest

@@ -0,0 +1 @@
+global_step1442

output-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b550b55841d02fa97f11f642f33caf86ef3b1299d05f454e7df00fbbc280baf4
+size 8551463272

output-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66958e27e9aee095ec88beb135d4af6c634ddc41a7797c4d55056b56e570c5a2
+size 8577695840

output-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d25926d5a73bf6d5bf15ecb613cf172490b86b52f5365e056885c24d21c9a7f
+size 8522366520

output-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80da2a7e2b2942bf79d2a25a9ab23a15681d7913c8225c92abb87b93285ce0d5
+size 8556838216

output-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6956bf35098e1a5498180a4ea47fe7fe3427f645bc90b012092d5e1b2d423255
+size 8526946352

output-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8c6f6d2fa9abb1164768ff0e610fb30ae0aefd7d2984ec1c6791509e6038a0
+size 8566472968

output-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a358fe3f45c806f4d0c6b7de3685fd040167949aa4e2200ac22f4ec9e2c57389
+size 8521491120

output-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5800c4d900827ce0132a10cc011b07862d2652452b61aceb363c16f9c16a2f5f
+size 8573269928

output-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e9ed4240a428a27cf0ef832a951924ac3a57ac26893e059639485f3ccada95
+size 8521496112

output-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3878dd25970ad8f2b0e4d01f8f0a9dfc14541360ba5b0015eac83dfa29a01d
+size 8581784848

output-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27446a79aa4f21a8170815ee562cd6c7f5b60eff525cd13db11d9bee5fae0a30
+size 8537766600

output-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a99406f59b6eda267a9569bcfb6aeb7d0b5aadd1b576adfc87a4d5fe58b3812d
+size 8571406040

output-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f9bcdc9e7922ce93332d5937b975f82693de8888dc0edd87a60bb395d3fced
+size 3125931080

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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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": true,
+      "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}