GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
EverMind-AI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
EverMind-AI
Model Tree
Qwen/Qwen3-Reranker-0.6B
Input Modalities
Output Modalities
Supported Functionality
The model answers a yes/no question, and the relevance score is the difference
between the yes and no logits at the final position. sigmoid of this score
is P("yes") and gives the same ordering.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer MODEL = "EverMind-AI/skillrep-reranker-0.6b"tok = AutoTokenizer.from_pretrained(MODEL, padding_side="left")model = AutoModelForCausalLM.from_pretrained(MODEL, dtype=torch.bfloat16).cuda().eval() PREFIX = ('<|im_start|>system\nJudge whether the Document meets the requirements ' 'based on the Query and the Instruct provided. Note that the answer can ' 'only be "yes" or "no".<|im_end|>\n<|im_start|>user\n')SUFFIX = '<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n'INSTRUCT = ("Given a coding task description, judge whether the skill document " "is relevant and useful for completing the task") YES, NO = tok.convert_tokens_to_ids("yes"), tok.convert_tokens_to_ids("no")PRE = tok.encode(PREFIX, add_special_tokens=False)SUF = tok.encode(SUFFIX, add_special_tokens=False) def pair(task, skill): doc = f"{skill['name']} | {skill['description'][:500]} | {skill['body'][:2000]}" return f"<Instruct>: {INSTRUCT}\n\n<Query>: {task}\n\n<Document>: {doc}" def score(task, skills, max_length=4096): """One score per skill; higher means more relevant.""" budget = max_length - len(PRE) - len(SUF) # truncate the pair, never the template ids = [PRE + tok.encode(pair(task, s), add_special_tokens=False, truncation=True, max_length=budget) + SUF for s in skills] batch = tok.pad({"input_ids": ids}, return_tensors="pt").to(model.device) with torch.no_grad(): logits = model(**batch).logits[:, -1, :] return (logits[:, YES] - logits[:, NO]).float().tolist() task = "resolve conflicts after a git merge"skills = [ {"name": "resolve-conflicts", "description": "Resolve git merge conflicts.", "body": "# Resolving merge conflicts\n1. Run `git status` to list conflicted files ..."}, {"name": "sourdough", "description": "Bake sourdough bread.", "body": "# Sourdough\nMix flour, water and starter ..."},]print(score(task, skills))# -> [3.0, -4.06]Exact scores shift in the last decimal with dtype and hardware; the ordering is what matters.
Keep the PREFIX / SUFFIX template and the <Instruct> / <Query> /
<Document> layout, with blank lines between the parts, exactly as above. The
score is read off the final-position logits, so truncate the pair text, not the
template.
python
# candidates: the top 10 skills that skillrep-embedding-0.6b returns for `task`scores = score(task, candidates)reranked = [c for _, c in sorted(zip(scores, candidates), key=lambda x: -x[0])]chat_template.jinja reproduces the prompt string above, so the tokenizer can
assemble it instead. It reads three roles: system carries the instruction
(omit it to get the default shown above), query the task, and document the
skill:
python
prompt = tok.apply_chat_template([ {"role": "query", "content": task}, {"role": "document", "content": "resolve-conflicts | Resolve git merge conflicts. | ..."},], tokenize=False)| input | limit |
|---|---|
| task description | not cut by characters |
skill description | first 500 characters |
skill body | first 2,000 characters |
| whole prompt | 4,096 tokens, cutting the pair text and keeping the template |
Second-stage reranking of the top 10 candidates that skillrep-embedding-0.6b recalls for a task. Treat the output as a ranking signal rather than a calibrated probability: compare scores within one candidate list, not across different tasks.
Apache-2.0, inherited from the base model. Skills keep their own upstream licenses.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer MODEL = "EverMind-AI/skillrep-reranker-0.6b"tok = AutoTokenizer.from_pretrained(MODEL, padding_side="left")model = AutoModelForCausalLM.from_pretrained(MODEL, dtype=torch.bfloat16).cuda().eval() PREFIX = ('<|im_start|>system\nJudge whether the Document meets the requirements ' 'based on the Query and the Instruct provided. Note that the answer can ' 'only be "yes" or "no".<|im_end|>\n<|im_start|>user\n')SUFFIX = '<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n'INSTRUCT = ("Given a coding task description, judge whether the skill document " "is relevant and useful for completing the task") YES, NO = tok.convert_tokens_to_ids("yes"), tok.convert_tokens_to_ids("no")PRE = tok.encode(PREFIX, add_special_tokens=False)SUF = tok.encode(SUFFIX, add_special_tokens=False) def pair(task, skill): doc = f"{skill['name']} | {skill['description'][:500]} | {skill['body'][:2000]}" return f"<Instruct>: {INSTRUCT}\n\n<Query>: {task}\n\n<Document>: {doc}" def score(task, skills, max_length=4096): """One score per skill; higher means more relevant.""" budget = max_length - len(PRE) - len(SUF) # truncate the pair, never the template ids = [PRE + tok.encode(pair(task, s), add_special_tokens=False, truncation=True, max_length=budget) + SUF for s in skills] batch = tok.pad({"input_ids": ids}, return_tensors="pt").to(model.device) with torch.no_grad(): logits = model(**batch).logits[:, -1, :] return (logits[:, YES] - logits[:, NO]).float().tolist() task = "resolve conflicts after a git merge"skills = [ {"name": "resolve-conflicts", "description": "Resolve git merge conflicts.", "body": "# Resolving merge conflicts\n1. Run `git status` to list conflicted files ..."}, {"name": "sourdough", "description": "Bake sourdough bread.", "body": "# Sourdough\nMix flour, water and starter ..."},]print(score(task, skills))# -> [3.0, -4.06]# candidates: the top 10 skills that skillrep-embedding-0.6b returns for `task`scores = score(task, candidates)reranked = [c for _, c in sorted(zip(scores, candidates), key=lambda x: -x[0])]prompt = tok.apply_chat_template([ {"role": "query", "content": task}, {"role": "document", "content": "resolve-conflicts | Resolve git merge conflicts. | ..."},], tokenize=False)