Create README.md

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+language:
+- ja
+- en
+pipeline_tag: text-generation
+datasets:
+- NTQAI/sharegpt-clean-ja
+---
+
+# chatntq-7b-jpntuned Card
+
+## Model Details
+
+ChatNTQ-7B-Japanese is a chat assistant trained by fine-tuning [BlinkDL/rwkv-4-world](https://huggingface.co/BlinkDL/rwkv-4-world) on user-shared conversations collected from ShareGPT.
+
+- **Developed by:** [NTQAI](https://huggingface.co/NTQAI)
+- **Model type:** An auto-regressive language model based on the transformer architecture.
+- **License:** Commercial license
+- **Finetuned from model:** [BlinkDL/rwkv-4-world/JPNtuned-7B-v1](https://huggingface.co/BlinkDL/rwkv-4-world/blob/main/RWKV-4-World-JPNtuned-7B-v1-OnlyForTest_76%25_trained-20230714-ctx4096.pth).
+
+## Uses
+
+```python
+import os, gc, copy, torch
+import gradio as gr
+os.environ["RWKV_JIT_ON"] = '1'
+os.environ["RWKV_CUDA_ON"] = '1'
+from rwkv.model import RWKV
+model_path = "chatntq-7b-jpntuned/ChatNTQ-7B-RWKV-world-JPNtuned-ctx2048.pth"
+WORD_NAME = "rwkv_vocab_v20230424" # copy rwkv_vocab_v20230424.txt in ChatNTQ-7B-Japanese to the same folder test
+ctx_limit = 1024
+model = RWKV(model=model_path, strategy='cuda fp16i8 *24 -> cuda fp16')
+from rwkv.utils import PIPELINE, PIPELINE_ARGS
+pipeline = PIPELINE(model, WORD_NAME)
+def generate_prompt(instruction):
+    return f"\x00Human: {instruction}\x00Assistant:  "
+
+def evaluate(
+    prompt,
+    token_count=1024,
+    temperature=1.2,
+    top_p=0.5,
+    presencePenalty = 0.4,
+    countPenalty = 0.4,
+):
+    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 = [0,1]) # stop generation whenever you see any token here
+
+    all_tokens = []
+    out_last = 0
+    out_str = ''
+    occurrence = {}
+    state = None
+    prompt = generate_prompt(prompt)
+    print(prompt)
+    for i in range(int(token_count)):
+        out, state = model.forward(pipeline.encode(prompt)[-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
+            out_last = i + 1
+    gc.collect()
+    torch.cuda.empty_cache()
+    return out_str
+if __name__ == "__main__":
+  question = "東京の人口はどれくらいですか?"
+  response = evaluate(question)
+```
+### Contact information
+For personal communication related to this project, please contact Nha Nguyen Van (nha282@gmail.com).