init

README.md

@@ -1,3 +1,54 @@
 ---
-license: cc-by-sa-4.0
+language:
+- en
+tags:
+- causal-lm
+license: cc-by-nc-sa-4.0
+datasets:
+- dmayhem93/ChatCombined
+- tatsu-lab/alpaca
+- nomic-ai/gpt4all_prompt_generations
+- Dahoas/full-hh-rlhf
+- jeffwan/sharegpt_vicuna
+- HuggingFaceH4/databricks_dolly_15k
 ---
+
+# StableLM-Tuned-Alpha 16-bit
+
+## Model Description
+
+16-bit version of `StableLM-Tuned-Alpha` compressed for the sake of speed and memory usage. No other changes were made. Original model: https://huggingface.co/stabilityai/stablelm-tuned-alpha-3b
+
+## Usage
+
+Get started chatting with `StableLM-Tuned-Alpha 16-bit` by using the following code snippet:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList
+tokenizer = AutoTokenizer.from_pretrained("vvsotnikov/stablelm-tuned-alpha-3b-16bit")
+model = AutoModelForCausalLM.from_pretrained("vvsotnikov/stablelm-tuned-alpha-3b-16bit")
+model.cuda()
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [50278, 50279, 50277, 1, 0]
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+system_prompt = """<|SYSTEM|># StableLM Tuned (Alpha version)
+- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
+- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
+- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
+- StableLM will refuse to participate in anything that could harm a human.
+"""
+prompt = f"{system_prompt}<|USER|>What's your mood today?<|ASSISTANT|>"
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+tokens = model.generate(
+  **inputs,
+  max_new_tokens=64,
+  temperature=0.7,
+  do_sample=True,
+  stopping_criteria=StoppingCriteriaList([StopOnTokens()])
+)
+print(tokenizer.decode(tokens[0], skip_special_tokens=True))
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stablelm-tuned-alpha-3b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50688
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d771cb399d04e2cdbd436235dec9b780475f91f6c0b936c84889563d12639b
+size 7543162373

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}