初始化项目，由ModelHub XC社区提供模型

Model: chartreuse-verte/orb-human-typeahead-1b-v2
Source: Original Platform

README.md

@@ -0,0 +1,125 @@
+---
+license: apache-2.0
+base_model: ibm-granite/granite-4.0-1b-base
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- typeahead
+- autocomplete
+- roleplay
+- granite
+- gguf
+library_name: transformers
+---
+
+# orb-human-typeahead-1b-v2
+
+A 1.6B typeahead model that predicts **the human's next few words** in a
+roleplay chat — inline "ghost text" for the person typing, not a reply
+generator for the character. Full fine-tune of
+[ibm-granite/granite-4.0-1b-base](https://huggingface.co/ibm-granite/granite-4.0-1b-base).
+
+Most small LMs asked to continue a user's half-typed roleplay message produce
+fluent but irrelevant text. This model is trained specifically on
+(conversation context + partial user message → the words the user actually
+typed next), so its suggestions stay on-scene and in-voice.
+
+## Variants
+
+| Path | Format | Use with |
+|---|---|---|
+| `/` | safetensors bf16, plain `granite` arch | transformers |
+| `GGUF/orb-human-typeahead-1b-v2-Q4_0.gguf` | GGUF Q4_0 (default) | llama.cpp / llama-cpp-python |
+| `GGUF/orb-human-typeahead-1b-v2-Q8_0.gguf` | GGUF Q8_0 | llama.cpp / llama-cpp-python |
+
+The original fine-tune used the `granitemoehybrid` architecture; since this
+variant is attention-only and dense, the weights are republished here as the
+equivalent plain `granite` architecture (logit-identical, verified), which
+loads everywhere without extras.
+
+## Prompt format
+
+Plain text, no chat template. Optional character summary, a marker line,
+name-prefixed turns, and finally the user's draft — the model continues the
+draft. Cut the suggestion at the first newline.
+
+```
+<character summary, optional>
+***Roleplay chat below***
+Sylvara: *She looks down from the watchtower and sees you.*
+Traveler: *I approach the encampment.*
+Sylvara: *She lowers her bow as you approach the gate.* "State your business, traveler."
+Traveler: *I raise both hands slowly and
+```
+
+A completion looks like ` step into the torchlight, keeping my voice low.*`
+
+Notes:
+- Trained to trigger at **word boundaries** only (draft ends on a whole word,
+  or on a trailing space). Mid-word completion is out of scope.
+- Trained context: up to ~4 recent turns, summaries ≤400 chars (prune tail), turns ≤500 chars (prune head).
+
+## Serving recipe
+
+Greedy, short budget, stop at newline — mirrors how it was trained and evaluated:
+
+```python
+from llama_cpp import Llama
+
+llm = Llama("GGUF/orb-human-typeahead-1b-v2-Q4_0.gguf", n_ctx=1024)
+out = llm.create_completion(prompt, max_tokens=12, stop=["\n"], temperature=0.0)
+print(out["choices"][0]["text"])
+```
+
+Or with transformers:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tok = AutoTokenizer.from_pretrained("chartreuse-verte/orb-human-typeahead-1b-v2")
+model = AutoModelForCausalLM.from_pretrained("chartreuse-verte/orb-human-typeahead-1b-v2")
+ids = tok(prompt, return_tensors="pt").input_ids
+out = model.generate(ids, max_new_tokens=12, do_sample=False)
+print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True).split("\n")[0])
+```
+
+## Evaluation
+
+Scored on a held-out validation set of real roleplay conversations (120
+prompts, conversation-disjoint from training; greedy, 12-token budget,
+suggestions cut at newline). word-EM@k = fraction of prompts where the first
+k words of the suggestion exactly match what the user really typed next;
+prefix-chars = mean length of the exactly-matching leading characters.
+
+| Metric | orb-human-typeahead-350m-v1 | this model |
+|---|---|---|
+| word-EM@1 | 0.300 | **0.417** |
+| word-EM@2 | 0.083 | **0.258** |
+| word-EM@3 | 0.033 | **0.175** |
+| prefix-chars | 2.89 | **6.03** |
+| completion perplexity | 12.97 | **7.40** |
+
+v2 is both larger than the 350M v1 and trained on ~80k more synthetic roleplay
+samples; word-EM@1 rises 0.300 → 0.417 and completion perplexity nearly halves
+(12.97 → 7.40). Absolute numbers stay modest by design — creative roleplay is
+high-entropy, so even a perfect suggester can't guess most continuations.
+
+## Training
+
+Two-stage full fine-tune of granite-4.0-1b-base: stage 1 on a large, mostly-synthetic
+roleplay corpus (self-chat generated to cover the on-scene, in-voice register real
+users type in — human prompters are too sparse to learn from directly; v2 adds
+~80k more synthetic samples than the 350M v1), then stage 2 on a smaller private
+in-domain set in the serve-time prompt format (with stage-1 replay to limit forgetting). Examples are user turns split at word boundaries; loss is on
+the continuation. Suggestions are single-line by construction (completions end
+at newline).
+
+## Limitations
+
+- English-centric, roleplay register (asterisk actions, quoted dialogue).
+  Out of domain for assistant chat, code, or formal prose.
+- Roleplay corpora include mature themes; suggestions can reflect that.
+  Intended as a typing aid for consenting adult users of RP chat apps.
+- Not an instruction follower — it only continues drafts in the format above.
+- Suggests at word boundaries; won't complete a half-typed word.