Duplicate from BlinkDL/Raven-RWKV-7B

Co-authored-by: BlinkDL <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Raven RWKV 7B
+emoji: 🚀
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 3.23.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: BlinkDL/Raven-RWKV-7B
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,124 @@
+import gradio as gr
+import os, gc, torch
+from datetime import datetime
+from huggingface_hub import hf_hub_download
+from pynvml import *
+nvmlInit()
+gpu_h = nvmlDeviceGetHandleByIndex(0)
+ctx_limit = 1024
+title = "RWKV-4-Raven-7B-v8-Eng-20230408-ctx4096"
+
+os.environ["RWKV_JIT_ON"] = '1'
+os.environ["RWKV_CUDA_ON"] = '1' # if '1' then use CUDA kernel for seq mode (much faster)
+
+from rwkv.model import RWKV
+model_path = hf_hub_download(repo_id="BlinkDL/rwkv-4-raven", filename=f"{title}.pth")
+model = RWKV(model=model_path, strategy='cuda fp16i8 *8 -> cuda fp16')
+from rwkv.utils import PIPELINE, PIPELINE_ARGS
+pipeline = PIPELINE(model, "20B_tokenizer.json")
+
+def generate_prompt(instruction, input=None):
+    if input:
+        return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+# Instruction:
+{instruction}
+
+# Input:
+{input}
+
+# Response:
+"""
+    else:
+        return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+# Instruction:
+{instruction}
+
+# Response:
+"""
+
+def evaluate(
+    instruction,
+    input=None,
+    token_count=200,
+    temperature=1.0,
+    top_p=0.7,
+    presencePenalty = 0.1,
+    countPenalty = 0.1,
+):
+    args = PIPELINE_ARGS(temperature = max(0.2, float(temperature)), top_p = float(top_p),
+                     alpha_frequency = countPenalty,
+                     alpha_presence = presencePenalty,
+                     token_ban = [], # ban the generation of some tokens
+                     token_stop = [0]) # stop generation whenever you see any token here
+
+    instruction = instruction.strip()
+    input = input.strip()
+    ctx = generate_prompt(instruction, input)
+    
+    gpu_info = nvmlDeviceGetMemoryInfo(gpu_h)
+    print(f'vram {gpu_info.total} used {gpu_info.used} free {gpu_info.free}')
+    
+    all_tokens = []
+    out_last = 0
+    out_str = ''
+    occurrence = {}
+    state = None
+    for i in range(int(token_count)):
+        out, state = model.forward(pipeline.encode(ctx)[-ctx_limit:] if i == 0 else [token], state)
+        for n in occurrence:
+            out[n] -= (args.alpha_presence + occurrence[n] * args.alpha_frequency)
+
+        token = pipeline.sample_logits(out, temperature=args.temperature, top_p=args.top_p)
+        if token in args.token_stop:
+            break
+        all_tokens += [token]
+        if token not in occurrence:
+            occurrence[token] = 1
+        else:
+            occurrence[token] += 1
+        
+        tmp = pipeline.decode(all_tokens[out_last:])
+        if '\ufffd' not in tmp:
+            out_str += tmp
+            yield out_str.strip()
+            out_last = i + 1
+    gc.collect()
+    torch.cuda.empty_cache()
+    yield out_str.strip()
+
+examples = [
+    ["Tell me about ravens.", "", 150, 1.0, 0.5, 0.4, 0.4],
+    ["Write a python function to mine 1 BTC, with details and comments.", "", 150, 1.0, 0.5, 0.2, 0.2],
+    ["Write a song about ravens.", "", 150, 1.0, 0.5, 0.4, 0.4],
+    ["Explain the following metaphor: Life is like cats.", "", 150, 1.0, 0.5, 0.4, 0.4],
+    ["Write a story using the following information", "A man named Alex chops a tree down", 150, 1.0, 0.5, 0.4, 0.4],
+    ["Generate a list of adjectives that describe a person as brave.", "", 150, 1.0, 0.5, 0.4, 0.4],
+    ["You have $100, and your goal is to turn that into as much money as possible with AI and Machine Learning. Please respond with detailed plan.", "", 150, 1.0, 0.5, 0.4, 0.4],
+]
+
+g = gr.Interface(
+    fn=evaluate,
+    inputs=[
+        gr.components.Textbox(lines=2, label="Instruction", value="Tell me about ravens."),
+        gr.components.Textbox(lines=2, label="Input", placeholder="none"),
+        gr.components.Slider(minimum=10, maximum=200, step=10, value=150), # token_count
+        gr.components.Slider(minimum=0.2, maximum=2.0, step=0.1, value=1.0), # temperature
+        gr.components.Slider(minimum=0, maximum=1, step=0.05, value=0.5), # top_p
+        gr.components.Slider(0.0, 1.0, step=0.1, value=0.4),  # presencePenalty
+        gr.components.Slider(0.0, 1.0, step=0.1, value=0.4),  # countPenalty        
+    ],
+    outputs=[
+        gr.inputs.Textbox(
+            lines=5,
+            label="Output",
+        )
+    ],
+    title=f"🐦Raven - {title}",
+    description="Raven is [RWKV 7B](https://github.com/BlinkDL/ChatRWKV) 100% RNN [RWKV-LM](https://github.com/BlinkDL/RWKV-LM) finetuned to follow instructions. *** Please try examples first (bottom of page) *** (edit them to use your question). Demo limited to ctxlen 1024. It is finetuned on [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca), codealpaca and more. For best results, *** keep you prompt short and clear ***.",
+    examples=examples,
+    cache_examples=False,
+)
+g.queue(concurrency_count=1, max_size=10)
+g.launch(share=False)

requirements.txt

@@ -0,0 +1,7 @@
+torch
+ninja
+tokenizers
+rwkv==0.6.2
+pynvml
+huggingface_hub
+gradio>=3.17.1